Introduction

AI Prompts for SEM FESEM TEM & HRTEM are becoming increasingly popular among researchers who want to accelerate the interpretation of electron microscopy images and improve the quality of their scientific writing. With the rapid advancement of artificial intelligence, many scientists now use AI tools such as ChatGPT to analyze SEM, FESEM, TEM, and HRTEM results, generate figure captions, prepare Results and Discussion sections, and compare their findings with published literature.

However, an important question remains:

Can artificial intelligence truly analyze electron microscopy images with the same accuracy as an experienced materials scientist?

The short answer is no.

Although AI has become an excellent assistant for interpreting microscopy results and generating scientific text, it still cannot replace expert image analysis. Tasks such as particle size measurement, grain size distribution, HRTEM lattice fringe analysis, SAED indexing, STEM elemental mapping interpretation, and quantitative morphology analysis require specialized software, scientific expertise, and careful human judgment.

This distinction is particularly important because many researchers mistakenly assume that AI can directly analyze microscopy images and provide publication-ready quantitative results. In reality, current AI models primarily interpret the information provided by the user rather than performing rigorous image analysis comparable to ImageJ, DigitalMicrograph, or other dedicated microscopy software.

In this comprehensive guide, you will discover 200 carefully designed AI prompts for SEM, FESEM, TEM, and HRTEM analysis. These prompts are intended to help researchers:

• Interpret microscopy observations more effectively
• Generate publication-quality Results and Discussion sections
• Compare microscopy findings with previous studies
• Write professional figure captions
• Respond to reviewer comments
• Correlate microscopy data with XRD, XPS, FTIR, BET, Raman, and other characterization techniques
• Improve the overall quality of scientific manuscripts

At the same time, we explain the current limitations of AI and demonstrate when expert analysis is still essential.

At AnalyzeTest AI, we combine artificial intelligence with human expertise. While AI assists in scientific interpretation and academic writing, our specialists perform advanced microscopy analyses including particle size measurement, ImageJ quantification, HRTEM lattice analysis, SAED indexing, STEM/EDS interpretation, and publication-ready image processing.

Whether you are working with nanomaterials, thin films, batteries, catalysts, MOFs, MXenes, polymers, biomaterials, or corrosion-resistant coatings, this guide will help you use AI more effectively while understanding where professional expertise remains indispensable.

Can AI Really Analyze SEM, FESEM, TEM & HRTEM Images?

Artificial intelligence has transformed scientific research by helping researchers interpret experimental results, generate publication-quality discussions, summarize literature, and improve academic writing. Naturally, many scientists now ask whether AI can also perform SEM, FESEM, TEM, and HRTEM image analysis automatically.

The answer is both yes and no.

AI can successfully assist researchers in understanding microscopy images after the necessary measurements and observations have already been obtained. For example, if you provide particle size values, lattice spacing, elemental composition, or morphological observations, AI can explain the results, compare them with published literature, identify possible mechanisms, and even generate a complete Results and Discussion section suitable for scientific publication.

However, AI cannot directly replace professional electron microscopy analysis.

Unlike experienced microscopists or specialized image-processing software, current AI models cannot accurately determine particle size distributions, identify grain boundaries, calculate lattice fringe spacing from HRTEM images, index SAED diffraction patterns, or perform quantitative morphology measurements directly from raw microscopy images with publication-grade reliability.

This limitation exists because modern large language models primarily analyze textual information rather than performing rigorous scientific image processing. Although multimodal AI systems can recognize general image features, they are not designed to replace dedicated microscopy software such as ImageJ, DigitalMicrograph, Gatan Microscopy Suite, or other specialized analysis platforms.

Therefore, the most effective workflow is to combine human expertise with AI-assisted scientific interpretation.

Researchers first obtain reliable quantitative measurements using appropriate microscopy software and expert analysis. These validated results can then be provided to AI for:

• Scientific interpretation
• Literature comparison
• Mechanism discussion
• Figure caption generation
• Reviewer response preparation
• Publication-ready academic writing

This collaborative approach combines the strengths of both technologies: the precision of expert microscopy analysis and the efficiency of artificial intelligence.

At AnalyzeTest AI, we follow exactly this philosophy. Instead of relying solely on AI, we combine advanced AI-assisted interpretation with expert microscopy analysis to deliver accurate, publication-ready scientific reports.

3. What AI Can Do for Electron Microscopy?

Although artificial intelligence cannot replace expert microscopy analysis, it has become an exceptionally powerful assistant for interpreting electron microscopy results and preparing scientific manuscripts. When provided with accurate experimental observations and quantitative measurements, AI can significantly reduce the time required for data interpretation and scientific writing while improving the overall quality of the manuscript.

Morphology Interpretation

AI can interpret qualitative morphological features observed in SEM, FESEM, TEM, and HRTEM images. For example, it can describe:

• Particle shape and morphology
• Surface roughness
• Agglomeration or dispersion
• Porosity
• Layered or sheet-like structures
• Core–shell morphologies
• Nanorods, nanowires, nanotubes, nanospheres, and nanosheets

Instead of simply describing what appears in the image, AI can also explain the possible formation mechanisms responsible for the observed morphology.

Scientific Discussion

One of the strongest applications of AI is generating publication-quality Results and Discussion sections.

Based on microscopy observations, AI can:

• Explain the scientific significance of the observed morphology
• Relate structural features to synthesis conditions
• Discuss possible growth mechanisms
• Connect morphology with material properties
• Produce well-written academic paragraphs suitable for journal manuscripts

Figure Captions

Writing informative figure captions can be surprisingly time-consuming.

AI can generate professional captions for:

• SEM images
• FESEM micrographs
• TEM images
• HRTEM lattice images
• SAED patterns
• STEM images
• EDS elemental mapping

The generated captions can be easily adapted to the style required by different scientific journals.

Literature Comparison

AI can compare your microscopy observations with previously published studies.

For example, it can discuss:

• Similar particle sizes reported in the literature
• Comparable morphologies
• Different synthesis routes
• Advantages and limitations of your material compared with previous reports
• Possible reasons for discrepancies between different studies

This greatly simplifies writing the discussion section.

Reviewer Responses

AI is extremely useful for preparing responses to reviewers.

It can help researchers:

• Explain microscopy observations more clearly
• Address reviewer concerns
• Strengthen scientific arguments
• Improve the clarity and professionalism of response letters
• Revise manuscript sections according to reviewer comments

Correlating Electron Microscopy with Other Characterization Techniques

Scientific publications rarely rely on microscopy alone.

AI can effectively correlate microscopy observations with results obtained from:

• XRD
• XPS
• FTIR
• Raman spectroscopy
• BET surface area analysis
• TGA
• EDS elemental analysis
• UV–Vis spectroscopy
• Electrochemical measurements

This integrated interpretation often produces a much stronger scientific discussion than analyzing each characterization technique independently.

Writing Publication-Ready Sections

Perhaps the greatest advantage of AI is its ability to transform experimental observations into clear, logical, publication-ready scientific writing.

AI can assist researchers in preparing:

• Results and Discussion
• Figure captions
• Abstracts
• Conclusions
• Graphical Abstract descriptions
• Cover letters
• Reviewer response letters
• Supplementary Information
• Thesis chapters
• Research reports

When combined with accurate experimental data and expert validation, AI becomes a powerful scientific writing assistant that can substantially accelerate manuscript preparation while maintaining high academic quality.

4. What AI Cannot Do in Electron Microscopy

Despite the impressive capabilities of modern artificial intelligence, there is a common misconception that AI can completely replace expert electron microscopy analysis. In reality, current AI models are designed primarily for scientific interpretation and academic writing, not for performing rigorous quantitative image analysis.

Many tasks in SEM, FESEM, TEM, and HRTEM require specialized image-processing software, advanced algorithms, and the expertise of experienced microscopists. These analyses cannot be performed reliably by simply uploading a microscopy image to a general-purpose AI model.

The following examples illustrate some of the most important limitations of current AI systems.

Particle Size Measurement

AI may estimate whether particles appear “small” or “large,” but it cannot accurately measure particle size distributions from microscopy images.

Reliable particle size analysis requires:

• Image calibration
• Particle detection
• Boundary identification
• Statistical measurements
• Histogram generation
• Mean, median, standard deviation, and distribution analysis

These tasks are typically performed using software such as ImageJ, not by language models.

Grain Size Analysis

Determining grain size is far more complex than visually inspecting an image.

Accurate grain analysis requires:

• Grain boundary identification
• Threshold optimization
• Image segmentation
• Statistical evaluation
• ASTM-compliant grain size measurements

Current AI models cannot perform these quantitative analyses with publication-grade accuracy.

Image Segmentation

Separating particles, pores, grains, or phases from the background is one of the most critical steps in microscopy image analysis.

Professional segmentation often requires:

• Threshold adjustment
• Edge detection
• Morphological filtering
• Watershed algorithms
• Manual correction

Without proper segmentation, quantitative measurements become unreliable.

HRTEM Lattice Fringe Analysis

One of the most specialized applications of electron microscopy is HRTEM lattice fringe analysis.

This involves:

• Measuring interplanar spacing (d-spacing)
• Identifying crystal planes
• Evaluating crystal defects
• Assessing crystallinity
• Comparing measured values with crystallographic databases

General AI assistants cannot perform these measurements directly from raw HRTEM images with scientific reliability.

SAED Pattern Indexing

Selected Area Electron Diffraction (SAED) analysis requires crystallographic expertise.

A proper SAED interpretation includes:

• Measuring diffraction ring or spot spacing
• Indexing crystal planes
• Identifying crystal structures
• Determining zone axes
• Comparing experimental patterns with reference databases

These tasks require dedicated crystallographic analysis and cannot be replaced by generic AI tools.

STEM and Elemental Mapping Analysis

Although AI can describe the colors observed in elemental maps, it cannot perform quantitative elemental mapping analysis.

Professional interpretation requires evaluation of:

• Elemental distribution
• Homogeneity
• Phase segregation
• Interface composition
• Local enrichment or depletion
• Correlation with EDS spectra

These analyses depend on experimental data rather than visual appearance alone.

Digital Image Processing

Publication-quality microscopy images frequently undergo professional image processing before analysis.

Typical processing steps include:

• Noise reduction
• Contrast enhancement
• Brightness correction
• Scale calibration
• FFT analysis
• Image filtering
• False-color mapping
• Measurement calibration

These operations require dedicated microscopy software and expert supervision.

Why Human Expertise Still Matters

Artificial intelligence is an outstanding assistant for interpreting microscopy results, explaining observed phenomena, comparing findings with published literature, and preparing scientific manuscripts. However, it should not be considered a replacement for quantitative microscopy analysis.

The most reliable workflow combines expert image analysis with AI-assisted scientific interpretation.

At AnalyzeTest, we integrate both approaches. In addition to AI-powered interpretation and scientific writing support, our specialists provide professional microscopy image analysis, including:

• Particle size measurement
• Grain size analysis
• ImageJ-based quantitative measurements
• Image segmentation
• HRTEM lattice fringe analysis
• SAED indexing
• STEM/EDS mapping interpretation
• Digital image processing
• Publication-ready figure preparation

This combination of human expertise and artificial intelligence ensures that researchers receive results that are not only scientifically accurate but also suitable for publication in high-impact journals.

5. Common Mistakes Researchers Make When Using AI for SEM/TEM

Artificial intelligence can dramatically improve scientific writing and data interpretation, but only when it is used correctly. Many researchers expect AI to perform tasks that are beyond its current capabilities, often leading to inaccurate conclusions or misleading discussions.

The following are some of the most common mistakes researchers make when using AI for SEM, FESEM, TEM, and HRTEM analysis.

1. Uploading a Microscopy Image Without Any Context

One of the most frequent mistakes is asking AI to analyze an electron microscopy image without providing any background information.

Instead, always include details such as:

• Material composition
• Synthesis method
• Magnification
• Scale bar
• Experimental objective
• Any quantitative measurements already obtained

The more scientific context AI receives, the more accurate and meaningful its interpretation becomes.

2. Expecting AI to Measure Particle Size

Many users assume AI can accurately calculate particle size directly from a microscopy image.

In reality, reliable particle size analysis requires calibrated image processing using specialized software such as ImageJ. AI can explain the significance of measured particle sizes, but it should not be used as a substitute for quantitative measurements.

3. Asking AI to Identify Crystal Planes from HRTEM Images

HRTEM lattice fringe analysis requires precise measurement of lattice spacing, FFT analysis, and comparison with crystallographic databases.

Without these quantitative data, AI cannot reliably determine crystal planes or crystallographic orientations.

4. Using AI Without Verifying the Results

AI-generated interpretations should always be reviewed by the researcher.

Peak assignments, morphology descriptions, crystallographic discussions, and proposed mechanisms should be compared with:

• Experimental observations
• Published literature
• Reference databases
• Scientific judgment

AI should assist scientific reasoning—not replace it.

5. Ignoring the Scale Bar

A microscopy image without considering the scale bar provides very limited quantitative information.

Particle size, pore size, grain size, and layer thickness all depend on proper image calibration. AI cannot accurately estimate these values from appearance alone.

6. Requesting Overly General Interpretations

Questions such as:

“Analyze this SEM image.”

usually produce generic answers.

Instead, ask focused questions, for example:

• Explain the observed morphology.
• Compare the particle size with similar published materials.
• Discuss the effect of agglomeration on electrochemical performance.
• Correlate the SEM observations with XRD and BET results.

Specific prompts produce significantly better scientific responses.

7. Using AI Without Combining Other Characterization Techniques

Electron microscopy should rarely be interpreted in isolation.

A much stronger scientific discussion is obtained when microscopy observations are correlated with complementary techniques such as:

• XRD
• XPS
• FTIR
• Raman spectroscopy
• BET analysis
• EDS elemental mapping
• Electrochemical measurements

Providing these additional results enables AI to generate more comprehensive and scientifically meaningful interpretations.

8. Copying AI-Generated Text Directly into a Manuscript

Although AI can produce high-quality scientific writing, its output should always be carefully reviewed, edited, and adapted to your own experimental findings.

Every manuscript should reflect the actual data, the relevant literature, and the author’s scientific interpretation rather than relying solely on automatically generated text.

Best Practice

The most effective workflow combines expert microscopy analysis with AI-assisted interpretation and scientific writing.

Use dedicated microscopy software for quantitative measurements, verify experimental observations carefully, and then employ AI to interpret the results, compare them with published studies, prepare reviewer responses, and write publication-ready manuscript sections.

This approach maximizes both scientific accuracy and research productivity while avoiding the common pitfalls associated with overreliance on artificial intelligence.

6. Before vs. After: Poor and Excellent Microscopy Prompts

One of the biggest factors affecting the quality of AI-generated responses is prompt quality. Even the most advanced AI model cannot provide accurate scientific interpretations if the prompt is vague, incomplete, or lacks experimental context.

The examples below demonstrate how a small improvement in prompt design can dramatically increase the quality and usefulness of the AI-generated output.

Example 1: General SEM Image Interpretation

❌ Poor Prompt

Analyze this SEM image.

Why it is poor

• No material information
• No synthesis method
• No magnification
• No research objective
• Produces only generic observations

✅ Excellent Prompt

Analyze the attached SEM image of acid-treated COOH-functionalized multi-walled carbon nanotubes synthesized by nitric acid oxidation. Discuss the observed morphology, particle agglomeration, surface defects, and the influence of functionalization on the nanotube structure. Compare the observations with similar studies published during the last five years and write the discussion in the style of a Q1 journal.

Example 2: TEM Image Analysis

❌ Poor Prompt

Explain this TEM image.

Why it is poor

The AI has no information about the material, imaging conditions, or the scientific purpose of the analysis.

✅ Excellent Prompt

The attached TEM image belongs to Fe₃O₄ nanoparticles synthesized by a hydrothermal method. The average particle size measured using ImageJ is 18 ± 4 nm. Interpret the particle morphology, dispersion, and crystallinity. Compare these observations with published Fe₃O₄ nanoparticles and generate a publication-ready Results and Discussion section.

Example 3: HRTEM Interpretation

❌ Poor Prompt

Analyze this HRTEM image and identify the crystal planes.

Why it is poor

AI cannot accurately determine lattice planes directly from a raw HRTEM image without quantitative measurements.

✅ Excellent Prompt

The measured lattice fringe spacing obtained from DigitalMicrograph is 0.252 nm. The material is TiO₂ anatase nanoparticles. Explain which crystallographic plane this spacing most likely corresponds to, discuss its significance, and compare it with reported values in the literature.

Example 4: Correlating SEM with Other Characterization Techniques

❌ Poor Prompt

Discuss this SEM image.

✅ Excellent Prompt

Correlate the attached SEM image with the following experimental results:

• XRD confirms single-phase spinel CuFe₂O₄.
• BET surface area is 126.4 m² g⁻¹.
• FTIR confirms metal–oxygen bonding.
• XPS indicates Cu²⁺ and Fe³⁺ oxidation states.

Explain how these characterization techniques support the observed morphology and prepare a publication-ready discussion.

Example 5: Reviewer Response

❌ Poor Prompt

Reply to the reviewer.

✅ Excellent Prompt

Reviewer Comment:
“The SEM images are descriptive but lack scientific discussion regarding particle agglomeration.”

Prepare a polite, point-by-point response explaining the observed agglomeration mechanism, relate it to the synthesis method, cite relevant literature, and provide revised manuscript text suitable for insertion into the Results and Discussion section.

What Makes an Excellent Microscopy Prompt?

High-quality prompts usually contain most of the following information:

• Material name and composition
• Synthesis or fabrication method
• Microscopy technique (SEM, FESEM, TEM, HRTEM, STEM, etc.)
• Magnification or scale bar
• Available quantitative measurements (particle size, d-spacing, etc.)
• Research objective
• Desired output (discussion, caption, comparison, reviewer response, conclusion, etc.)
• Writing style (journal article, thesis, report, conference paper)

The more scientific context you provide, the more accurate, detailed, and publication-ready the AI-generated response will be.

7. How to Customize These Prompts

The 200 prompts presented in this guide are designed as professional templates, not rigid instructions. Every research project is unique, and the quality of AI-generated responses depends largely on how well the prompt reflects your experimental conditions and research objectives.

Instead of copying a prompt exactly as written, you should customize it by incorporating your own experimental details. The more specific and scientifically accurate your prompt is, the more useful and publication-ready the AI output will be.

Step 1. Specify Your Material

Always begin by clearly identifying the material under investigation.

Examples

• COOH-functionalized multi-walled carbon nanotubes
• TiO₂ nanoparticles
• MXene nanosheets
• CuFe₂O₄ nanospheres
• Ni-MOF nanostructures
• ZnO thin films

Step 2. Describe the Synthesis Method

The morphology observed in microscopy images strongly depends on the preparation method.

Include information such as:

• Hydrothermal synthesis
• Sol-gel process
• Electrospinning
• Chemical vapor deposition (CVD)
• Magnetron sputtering
• Ball milling
• Chemical etching

This allows AI to explain the possible growth mechanism behind the observed morphology.

Step 3. Mention the Microscopy Technique

Different microscopy techniques provide different types of information.

Examples include:

• SEM for surface morphology
• FESEM for high-resolution surface features
• TEM for internal nanostructure
• HRTEM for lattice fringes
• STEM for elemental contrast
• SAED for crystallographic information
• EDS mapping for elemental distribution

Always specify which technique was used.

Step 4. Include Quantitative Results

AI produces significantly better interpretations when quantitative measurements are available.

Examples include:

• Average particle size
• Grain size
• Layer thickness
• d-spacing
• Crystal plane assignment
• Porosity
• Surface roughness
• Elemental composition

These measurements should come from experimental analysis rather than AI estimation.

Step 5. Define Your Objective

Tell AI exactly what you expect.

For example:

• Interpret the morphology
• Explain the growth mechanism
• Compare with published literature
• Write the Results and Discussion section
• Generate a figure caption
• Prepare a reviewer response
• Correlate microscopy observations with XRD, XPS, FTIR, or BET

Clear objectives lead to more focused and scientifically relevant responses.

Step 6. Request the Desired Writing Style

Specify the format of the output.

Examples:

• Publication-ready discussion
• PhD thesis writing
• Scientific report
• Conference paper
• Supplementary Information
• Reviewer response
• Abstract
• Conclusion

AI adapts its writing style according to your request.

Example of a Customized Prompt

Instead of writing:

Analyze this SEM image.

Write:

Analyze the attached FESEM image of hydrothermally synthesized CuFe₂O₄ nanoparticles. The average particle size measured using ImageJ is 42 ± 8 nm. Discuss particle morphology, agglomeration, and porosity, compare the observations with recent literature, correlate the morphology with XRD and BET results, and write a publication-ready Results and Discussion section suitable for a Q1 materials science journal.

Pro Tip

The most effective prompts combine:

• Material information
• Experimental conditions
• Quantitative measurements
• Characterization results
• Scientific objective
• Desired output format

This combination enables AI to generate responses that are significantly more accurate, detailed, and publication-ready than generic prompts.

8. Why AnalyzeTest AI Is Different

Many AI platforms can generate scientific text, summarize articles, or provide general explanations about electron microscopy. However, AnalyzeTest AI goes far beyond conventional AI tools by combining artificial intelligence with expert microscopy analysis.

Instead of relying solely on AI-generated interpretations, AnalyzeTest integrates professional image analysis performed by experienced materials scientists. This hybrid approach ensures that researchers receive scientifically accurate, quantitative, and publication-ready results.

AI-Assisted Scientific Interpretation

AnalyzeTest AI can help researchers:

• Interpret SEM, FESEM, TEM, and HRTEM observations
• Generate publication-ready Results and Discussion sections
• Write professional figure captions
• Compare experimental results with published literature
• Correlate microscopy observations with XRD, XPS, FTIR, BET, Raman, EDS, and other characterization techniques
• Prepare reviewer response letters
• Improve scientific writing for journal submission

These AI-powered capabilities significantly reduce manuscript preparation time while maintaining a high standard of academic writing.

Expert Microscopy Analysis Beyond AI

Unlike general-purpose AI tools, AnalyzeTest also provides professional microscopy image analysis performed by specialists.

Our expert services include:

Particle Size Analysis

Using calibrated microscopy images and ImageJ-based workflows, we provide:

• Particle size measurement
• Particle size distribution
• Statistical analysis
• Histograms
• Mean, median, standard deviation, and size range

These quantitative measurements are essential for publication in high-impact journals.

HRTEM Lattice Fringe Analysis

Our specialists perform detailed HRTEM analysis, including:

• Lattice fringe measurement
• d-spacing calculation
• Crystal plane identification
• Crystallinity assessment
• FFT interpretation
• Comparison with crystallographic databases

SAED Pattern Indexing

Selected Area Electron Diffraction (SAED) patterns are analyzed by experienced researchers through:

• Ring and spot indexing
• Crystal structure identification
• Zone axis determination
• Phase verification
• Crystallographic interpretation

This level of analysis cannot be reliably achieved using general AI tools alone.

ImageJ-Based Quantitative Measurements

We perform quantitative image analysis using professional software, including:

• Particle counting
• Grain size analysis
• Circularity
• Aspect ratio
• Surface coverage
• Porosity estimation
• Image calibration
• Statistical measurements

These results are suitable for publication in peer-reviewed journals.

Morphology Quantification

Beyond qualitative descriptions, AnalyzeTest provides quantitative evaluation of microscopy images, including:

• Agglomeration analysis
• Particle dispersion assessment
• Shape factor determination
• Surface roughness evaluation
• Pore morphology characterization
• Nanostructure classification

This transforms microscopy images into meaningful numerical data that can be correlated with other characterization techniques.

Human Expertise + Artificial Intelligence

The philosophy of AnalyzeTest is simple:

AI accelerates scientific interpretation, while experts ensure scientific accuracy.

Rather than replacing human expertise, we combine advanced AI-assisted writing with professional microscopy analysis to deliver results that are:

• Scientifically accurate
• Quantitatively reliable
• Literature-supported
• Publication-ready
• Suitable for high-impact journals

Whether you need particle size analysis, HRTEM lattice interpretation, SAED indexing, ImageJ measurements, morphology quantification, or AI-assisted scientific writing, AnalyzeTest provides a complete solution from raw microscopy images to publication-ready manuscripts.

General Morphology

Prompt 1 – General Morphology Interpretation

Analyze the attached electron microscopy image (SEM/FESEM/TEM/HRTEM) and describe the overall morphology, particle shape, surface texture, agglomeration, porosity, dispersion, and any visible structural features. Explain how these morphological characteristics may influence the material’s physical or chemical properties.

Prompt 2 – Publication-Ready Discussion

Write a publication-quality Results and Discussion section based on the attached microscopy image. Discuss the observed morphology, possible growth mechanism, and scientific significance using formal academic language suitable for a Q1 journal.

Prompt 3 – Morphology Comparison

Compare the morphology observed in the attached microscopy image with similar nanomaterials reported in recent scientific literature. Discuss similarities, differences, and possible reasons for the observed morphology.

Prompt 4 – Growth Mechanism

Based on the observed morphology in the attached microscopy image and the synthesis method described below, explain the possible particle growth mechanism and formation process.

Material:
[SAMPLE NAME]

Synthesis Method:
[SYNTHESIS METHOD]

Prompt 5 – Scientific Figure Caption

Generate a professional figure caption for the attached microscopy image suitable for publication in an international scientific journal.

Prompt 6 – Structure–Property Relationship

Explain how the observed morphology in the microscopy image could affect mechanical, optical, catalytic, electrochemical, adsorption, or corrosion properties of the material.

Prompt 7 – Defect Analysis

Identify possible structural defects visible in the microscopy image, including agglomeration, pores, cracks, particle coalescence, irregular morphology, or surface imperfections. Discuss their possible origins.

Prompt 8 – Reviewer Response

A reviewer commented:

“The microscopy images are descriptive but lack scientific discussion.”

Prepare a professional response explaining the observed morphology, its formation mechanism, and its relationship with the material’s performance.

Prompt 9 – Correlation with Other Characterization Techniques

Correlate the morphology observed in the microscopy image with the following characterization results:

• XRD:
• XPS:
• FTIR:
• BET:
• Raman:
• EDS:

Generate a coherent scientific discussion explaining how these techniques support one another.

Prompt 10 – Manuscript Improvement

Rewrite the following microscopy discussion to improve scientific accuracy, readability, grammar, logical flow, and publication quality while preserving the original scientific meaning.

[Paste your discussion here.]

SEM

Prompt 1 – General SEM Interpretation

Analyze the attached SEM image and describe the surface morphology, particle shape, particle distribution, agglomeration, porosity, surface roughness, and structural uniformity. Explain the possible formation mechanism and discuss how these features may influence the material’s performance.

Prompt 2 – Publication-Ready Results & Discussion

Write a publication-quality Results and Discussion section based on the attached SEM image. Use formal scientific language suitable for submission to a Q1 materials science journal. Discuss the morphology, synthesis–structure relationship, and potential applications.

Prompt 3 – Particle Agglomeration Analysis

Evaluate the degree of particle agglomeration observed in the SEM image. Discuss the possible causes of agglomeration, its effect on material properties, and strategies to minimize particle clustering during synthesis.

Prompt 4 – Surface Defect Analysis

Identify and discuss any visible surface defects in the SEM image, including cracks, pores, voids, fractures, particle coalescence, or irregular surface features. Explain how these defects may influence the material’s mechanical, catalytic, electrochemical, or corrosion behavior.

Prompt 5 – Morphology Comparison with Literature

Compare the morphology observed in the attached SEM image with similar materials reported in recent scientific literature. Discuss similarities, differences, and possible reasons for the observed morphological characteristics.

Prompt 6 – Correlation with XRD

Correlate the morphology observed in the SEM image with the following XRD results. Explain how the crystal structure, crystallite size, and phase composition support the observed surface morphology.

XRD Results:
[Paste XRD results here.]

Prompt 7 – Correlation with BET

The measured BET surface area is [VALUE] m²/g with an average pore diameter of [VALUE] nm. Explain how these BET results relate to the morphology observed in the attached SEM image and discuss the implications for adsorption or catalytic performance.

Prompt 8 – Correlation with EDS Mapping

Analyze the SEM image together with the accompanying EDS elemental mapping results. Discuss the relationship between morphology and elemental distribution, evaluate compositional homogeneity, and explain how the elemental mapping supports the SEM observations.

Prompt 9 – Reviewer Response

Reviewer Comment:

“The SEM images are descriptive but lack sufficient scientific interpretation.”

Prepare a professional point-by-point response explaining the observed morphology, discussing the formation mechanism, and providing revised manuscript text suitable for inclusion in the Results and Discussion section.

Prompt 10 – Figure Caption

Generate a concise but publication-quality figure caption for the attached SEM image. Describe the observed morphology, important structural features, magnification, and the scientific significance of the image without repeating information already presented in the main text.

FESEM

Prompt 1 – High-Resolution Surface Morphology Analysis

Analyze the attached FESEM image and provide a detailed interpretation of the surface morphology. Describe particle shape, particle size uniformity, surface roughness, agglomeration, porosity, grain boundaries, and nanoscale structural features. Discuss how these characteristics may influence the material’s performance.

Prompt 2 – Publication-Ready Results & Discussion

Write a publication-quality Results and Discussion section based on the attached FESEM image. Explain the observed nanostructure, morphology evolution, synthesis–structure relationship, and potential influence on the material’s physical or chemical properties using the writing style of a Q1 journal.

Prompt 3 – Nanostructure Identification

Examine the attached FESEM image and identify the dominant nanostructure (nanoparticles, nanosheets, nanorods, nanowires, nanotubes, nanoflowers, porous structures, etc.). Explain the possible formation mechanism responsible for this morphology.

Prompt 4 – Surface Uniformity and Agglomeration

Evaluate the degree of particle dispersion and agglomeration observed in the FESEM image. Discuss whether the particles appear uniformly distributed and explain the possible reasons for particle aggregation or clustering.

Prompt 5 – Comparison with Published Literature

Compare the morphology observed in the attached FESEM image with similar materials reported in recent peer-reviewed publications. Discuss similarities, differences, and possible explanations based on synthesis conditions.

Prompt 6 – Correlation with XRD and BET

Correlate the FESEM observations with the following characterization results:

• XRD:
• BET Surface Area:
• Average Pore Diameter:

Explain how the crystal structure and textural properties support the observed nanoscale morphology.

Prompt 7 – Defect Analysis

Identify any visible nanoscale defects in the FESEM image, including pores, cracks, grain boundaries, voids, fractured particles, or irregular surface features. Discuss their possible origin and their influence on the material’s properties.

Prompt 8 – Correlation with EDS Mapping

Interpret the FESEM image together with the corresponding EDS elemental mapping results. Discuss the relationship between morphology and elemental distribution, evaluate compositional homogeneity, and explain whether the mapping supports successful material synthesis.

Prompt 9 – Reviewer Response

Reviewer Comment:

“The FESEM images provide only qualitative observations without sufficient scientific discussion.”

Prepare a professional point-by-point response explaining the observed nanoscale morphology, discussing the formation mechanism, and providing revised manuscript text suitable for inclusion in the Results and Discussion section.

Prompt 10 – Scientific Figure Caption

Generate a concise, publication-ready figure caption for the attached FESEM image. Describe the nanoscale morphology, important structural features, magnification, and the scientific significance of the observed microstructure without repeating information already discussed in the manuscript.

TEM

Prompt 1 – General TEM Interpretation

Analyze the attached TEM image and provide a detailed interpretation of the nanoparticle morphology. Discuss particle shape, particle size, dispersion, agglomeration, internal structure, crystallinity, and any visible structural features. Explain how these characteristics may influence the material’s performance.

Prompt 2 – Publication-Ready Results & Discussion

Write a publication-quality Results and Discussion section based on the attached TEM image. Discuss the observed morphology, nanoparticle distribution, crystallinity, synthesis–structure relationship, and the implications for the material’s physical, chemical, or electrochemical properties.

Prompt 3 – Particle Dispersion Analysis

Evaluate the dispersion of nanoparticles observed in the TEM image. Discuss whether the particles are well dispersed or agglomerated, explain the possible reasons for the observed distribution, and describe how particle dispersion may affect the material’s performance.

Prompt 4 – Core–Shell Structure Interpretation

Analyze the attached TEM image and determine whether the particles exhibit a core–shell morphology. Discuss the evidence supporting your conclusion, explain the possible formation mechanism, and describe how the core–shell structure may influence the material’s properties.

Prompt 5 – Crystallinity Evaluation

Based on the TEM image, discuss the apparent crystallinity of the nanoparticles. Explain whether the particles appear crystalline or partially amorphous and describe the limitations of conventional TEM for confirming crystal structure without HRTEM or SAED analysis.

Prompt 6 – Correlation with XRD

Correlate the TEM observations with the following XRD results:

• Crystal phases:
• Average crystallite size:
• Preferred orientation (if applicable):

Explain how the TEM morphology supports or complements the XRD findings.

Prompt 7 – Correlation with BET and Particle Size

The average particle size measured from ImageJ is [VALUE] nm, while the BET surface area is [VALUE] m²/g.

Discuss the relationship between particle size, particle morphology, agglomeration, and surface area. Explain whether the TEM observations are consistent with the BET results.

Prompt 8 – Comparison with Published Literature

Compare the morphology and particle size observed in the attached TEM image with similar materials reported in recent scientific publications. Discuss similarities, differences, and possible reasons for the observed structural characteristics.

Prompt 9 – Reviewer Response

Reviewer Comment:

“The TEM images are presented without sufficient discussion regarding nanoparticle morphology and crystallinity.”

Prepare a professional point-by-point response explaining the observed TEM features, discussing their scientific significance, and providing revised manuscript text suitable for inclusion in the Results and Discussion section.

Prompt 10 – Scientific Figure Caption

Generate a publication-ready figure caption for the attached TEM image. Describe the observed nanoparticle morphology, particle dispersion, internal structural features, and the scientific importance of the TEM observations without repeating information already discussed in the manuscript.

HRTEM

Prompt 1 – HRTEM Lattice Fringe Interpretation

Analyze the attached HRTEM image and discuss the observed lattice fringes, crystallinity, particle morphology, and crystal quality. Explain the significance of the visible atomic lattice and how it reflects the structural characteristics of the material.

Prompt 2 – Publication-Ready Results & Discussion

Write a publication-quality Results and Discussion section based on the attached HRTEM image. Discuss lattice fringes, crystallinity, crystal defects, interplanar spacing (d-spacing), and the relationship between the observed microstructure and the material’s properties using the writing style of a Q1 journal.

Prompt 3 – d-Spacing Interpretation

The measured lattice fringe spacing obtained from HRTEM is [VALUE] nm.

Explain which crystallographic plane this spacing most likely corresponds to, compare it with reported literature values, and discuss its significance for confirming the crystal structure.

Prompt 4 – Crystal Quality Evaluation

Evaluate the crystal quality observed in the attached HRTEM image. Discuss whether the nanoparticles appear highly crystalline, partially crystalline, or contain amorphous regions. Explain how the observed crystal quality may influence the material’s functional properties.

Prompt 5 – Crystal Defect Analysis

Analyze the HRTEM image for possible crystal defects such as lattice distortion, stacking faults, dislocations, grain boundaries, twin boundaries, or amorphous regions. Discuss the possible origin of these defects and their influence on the material’s performance.

Prompt 6 – Correlation with XRD

Correlate the HRTEM observations with the following XRD results:

• Crystal phases:
• Average crystallite size:
• Preferred orientation:
• Crystal structure:

Explain how the measured lattice fringes and crystallinity support the XRD analysis and discuss any agreement or discrepancies.

Prompt 7 – Correlation with SAED

Interpret the HRTEM image together with the corresponding SAED pattern. Explain how the lattice fringes support the diffraction pattern, discuss crystal orientation, and evaluate whether the material exhibits single-crystalline or polycrystalline characteristics.

Prompt 8 – Literature Comparison

Compare the measured lattice spacing, crystallinity, and microstructural features observed in the HRTEM image with similar materials reported in recent scientific literature. Discuss similarities, differences, and possible reasons for the observed structural characteristics.

Prompt 9 – Reviewer Response

Reviewer Comment:

“The HRTEM images are presented without sufficient discussion regarding lattice fringes and crystallographic confirmation.”

Prepare a professional point-by-point response explaining the significance of the observed lattice fringes, d-spacing measurements, crystal quality, and their agreement with XRD and SAED results. Include revised manuscript text suitable for the Results and Discussion section.

Prompt 10 – Scientific Figure Caption

Generate a concise, publication-ready figure caption for the attached HRTEM image. Describe the observed lattice fringes, measured interplanar spacing (if available), crystal quality, and the scientific significance of the HRTEM observations without repeating information already discussed in the manuscript.

SAED (Selected Area Electron Diffraction)

Prompt 1 – General SAED Pattern Interpretation

Analyze the attached SAED pattern and explain whether the material exhibits a single-crystalline, polycrystalline, or amorphous structure. Discuss the diffraction features, ring or spot patterns, and their scientific significance.

Prompt 2 – Publication-Ready Results & Discussion

Write a publication-quality Results and Discussion section based on the attached SAED pattern. Discuss crystallinity, diffraction characteristics, crystal structure, and how the SAED results support the overall structural characterization of the material.

Prompt 3 – Crystal Structure Confirmation

Interpret the attached SAED pattern and explain how it confirms the crystal structure of the material. Correlate the diffraction pattern with the reported crystal phase and discuss the reliability of the structural identification.

Prompt 4 – Correlation with HRTEM

Analyze the attached SAED pattern together with the corresponding HRTEM image. Explain how the measured lattice fringes and diffraction pattern complement each other in confirming the crystallinity and crystal structure of the material.

Prompt 5 – Correlation with XRD

Correlate the attached SAED pattern with the following XRD results:

• Crystal phases:
• Space group:
• Average crystallite size:

Explain how SAED and XRD complement each other in confirming the crystal structure and discuss any similarities or discrepancies.

Prompt 6 – Polycrystalline vs. Single-Crystal Analysis

Based on the attached SAED pattern, determine whether the sample is most likely single-crystalline, polycrystalline, or partially crystalline. Explain your reasoning using the diffraction features observed in the pattern.

Prompt 7 – Diffraction Ring Interpretation

Interpret the diffraction rings observed in the attached SAED pattern. Discuss what the ring sharpness, continuity, and intensity reveal about particle size, crystallinity, and crystal orientation.

Prompt 8 – Literature Comparison

Compare the attached SAED pattern with diffraction patterns reported for similar materials in recent scientific literature. Discuss similarities, differences, and possible reasons for any discrepancies.

Prompt 9 – Reviewer Response

Reviewer Comment:

“The SAED pattern is presented without sufficient discussion regarding crystallinity and crystal structure confirmation.”

Prepare a professional point-by-point response explaining the significance of the SAED results, their relationship with HRTEM and XRD analyses, and provide revised manuscript text suitable for the Results and Discussion section.

Prompt 10 – Scientific Figure Caption

Generate a publication-ready figure caption for the attached SAED pattern. Describe the diffraction features, crystallinity, crystal structure, and explain how the SAED pattern supports the structural characterization of the material without repeating information already discussed in the manuscript.

STEM (Scanning Transmission Electron Microscopy)

Prompt 1 – General STEM Interpretation

Analyze the attached STEM image and discuss the observed morphology, particle distribution, contrast variation, internal structure, and nanoscale features. Explain how the STEM observations contribute to understanding the material’s microstructure and properties.

Prompt 2 – Publication-Ready Results & Discussion

Write a publication-quality Results and Discussion section based on the attached STEM image. Discuss the observed nanostructure, structural homogeneity, particle morphology, and their relationship with the synthesis method and material performance.

Prompt 3 – Z-Contrast Interpretation (HAADF-STEM)

The attached image was acquired using HAADF-STEM.

Interpret the contrast differences observed in the image and explain how atomic number (Z-contrast) influences image intensity. Discuss what the contrast reveals about the material’s composition and structure.

Prompt 4 – Internal Structure Analysis

Analyze the attached STEM image and discuss any observable internal structural features, including core–shell structures, multilayer architectures, phase interfaces, hollow particles, or compositional variations. Explain their possible formation mechanisms.

Prompt 5 – Correlation with EDS Mapping

Interpret the attached STEM image together with the corresponding EDS elemental mapping. Discuss the relationship between morphology and elemental distribution, evaluate compositional homogeneity, and explain whether the mapping confirms successful synthesis.

Prompt 6 – Correlation with HRTEM and XRD

Correlate the STEM observations with the following characterization results:

• HRTEM:
• XRD:
• SAED:

Discuss how these complementary techniques collectively confirm the crystal structure, morphology, and microstructural characteristics of the material.

Prompt 7 – Interface Analysis

Analyze the interfaces visible in the STEM image. Discuss grain boundaries, phase boundaries, heterojunctions, or interfacial regions, and explain how these interfaces may influence the material’s mechanical, catalytic, electronic, or electrochemical performance.

Prompt 8 – Comparison with Published Literature

Compare the observed STEM morphology and structural characteristics with similar materials reported in recent scientific literature. Discuss similarities, differences, and possible reasons for the observed microstructure.

Prompt 9 – Reviewer Response

Reviewer Comment:

“The STEM images are presented without sufficient discussion regarding structural features and compositional contrast.”

Prepare a professional point-by-point response explaining the observed STEM features, discussing the scientific significance of the image contrast, and providing revised manuscript text suitable for inclusion in the Results and Discussion section.

Prompt 10 – Scientific Figure Caption

Generate a concise, publication-ready figure caption for the attached STEM image. Describe the observed morphology, internal structural features, image contrast, and the scientific significance of the STEM observations without repeating information already discussed in the manuscript.

EDS Mapping

Prompt 1 – General EDS Mapping Interpretation

Analyze the attached EDS elemental mapping images together with the corresponding SEM/TEM image. Describe the distribution of each detected element, evaluate elemental homogeneity, and discuss whether the mapping confirms successful synthesis of the material.

Prompt 2 – Publication-Ready Results & Discussion

Write a publication-quality Results and Discussion section based on the attached EDS elemental mapping results. Discuss elemental distribution, compositional uniformity, possible phase segregation, and explain how the mapping supports the proposed material structure.

Prompt 3 – Elemental Distribution Analysis

Interpret the attached EDS mapping images and discuss whether each element is uniformly distributed or exhibits localized enrichment. Explain the possible reasons for the observed elemental distribution and its influence on the material’s properties.

Prompt 4 – Correlation with SEM Morphology

Correlate the attached EDS elemental mapping results with the corresponding SEM image. Explain how the elemental distribution relates to the observed particle morphology, agglomeration, porosity, and surface structure.

Prompt 5 – Correlation with STEM

Interpret the attached STEM image together with the corresponding EDS elemental mapping. Discuss whether the elemental maps support the structural features observed in the STEM image and explain any compositional variations across the sample.

Prompt 6 – Correlation with XPS

Correlate the EDS mapping results with the following XPS data:

• Surface elemental composition:
• Oxidation states:
• Atomic percentages:

Discuss the similarities and differences between EDS and XPS results, considering their different analysis depths and detection principles.

Prompt 7 – Correlation with XRD

Interpret the EDS elemental mapping together with the following XRD results:

• Crystal phases:
• Phase composition:

Discuss whether the observed elemental distribution is consistent with the identified crystal phases and explain any discrepancies.

Prompt 8 – Multi-Element Composite Analysis

The material contains the following elements:

[Insert Elements]

Interpret the attached EDS maps and discuss whether the elemental distribution indicates successful composite formation, alloying, doping, or heterostructure formation. Evaluate the compositional homogeneity and identify any evidence of phase separation or elemental clustering.

Prompt 9 – Reviewer Response

Reviewer Comment:

“The EDS mapping images are presented without sufficient discussion regarding elemental distribution and compositional homogeneity.”

Prepare a professional point-by-point response explaining the elemental mapping results, discussing the scientific significance of the observed distributions, and providing revised manuscript text suitable for the Results and Discussion section.

Prompt 10 – Scientific Figure Caption

Generate a concise, publication-ready figure caption for the attached EDS elemental mapping images. Describe the elemental distribution, compositional uniformity, and explain how the mapping confirms the successful synthesis or homogeneous distribution of the material without repeating information already discussed in the manuscript.

Nanoparticles

Prompt 1 – Nanoparticle Morphology Analysis

Analyze the attached SEM/TEM/FESEM image of nanoparticles. Describe the particle morphology, shape, size uniformity, dispersion, agglomeration, and surface characteristics. Discuss how these features may influence the material’s physical, chemical, catalytic, or electrochemical properties.

Prompt 2 – Publication-Ready Results & Discussion

Write a publication-quality Results and Discussion section based on the attached nanoparticle microscopy image. Discuss particle morphology, particle size distribution, synthesis–structure relationship, and the potential impact of the observed nanostructure on material performance.

Prompt 3 – Particle Size Interpretation

The average particle size measured using ImageJ is [VALUE] ± [VALUE] nm.

Interpret this result, discuss whether the particles are considered nanoscale, compare the measured size with similar materials reported in the literature, and explain how particle size influences the material’s properties.

Prompt 4 – Agglomeration Analysis

Evaluate the degree of nanoparticle agglomeration observed in the attached microscopy image. Discuss the possible causes of particle aggregation, explain how agglomeration affects surface area and performance, and suggest methods to improve nanoparticle dispersion.

Prompt 5 – Growth Mechanism

The nanoparticles were synthesized using the following method:

[SYNTHESIS METHOD]

Based on the observed morphology, explain the probable nucleation and growth mechanism responsible for the formation of these nanoparticles.

Prompt 6 – Correlation with XRD and BET

Correlate the observed nanoparticle morphology with the following characterization results:

• XRD:
• BET Surface Area:
• Average Pore Diameter:

Explain how particle size, crystallinity, and surface area complement one another and support the observed morphology.

Prompt 7 – Comparison with Published Literature

Compare the morphology, particle size, and dispersion observed in the attached microscopy image with similar nanoparticles reported in recent scientific publications. Discuss similarities, differences, and possible reasons for the observed structural characteristics.

Prompt 8 – Structure–Property Relationship

Discuss how the observed nanoparticle morphology may influence the material’s properties, including catalytic activity, adsorption capacity, corrosion resistance, electrical conductivity, optical behavior, mechanical strength, or electrochemical performance.

Prompt 9 – Reviewer Response

Reviewer Comment:

“The manuscript presents nanoparticle images but lacks sufficient discussion regarding particle morphology and size distribution.”

Prepare a professional point-by-point response explaining the observed nanoparticle morphology, discussing the measured particle size, comparing the results with published literature, and providing revised manuscript text suitable for inclusion in the Results and Discussion section.

Prompt 10 – Scientific Figure Caption

Generate a concise, publication-ready figure caption for the attached nanoparticle microscopy image. Describe the particle morphology, size distribution, dispersion, and any notable structural features without repeating information already discussed in the manuscript.

Thin Films

Prompt 1 – Thin Film Morphology Analysis

Analyze the attached SEM/FESEM/TEM image of the thin film. Discuss the surface morphology, grain structure, film continuity, compactness, surface roughness, defects, and overall microstructural quality. Explain how these characteristics may influence the film’s functional performance.

Prompt 2 – Publication-Ready Results & Discussion

Write a publication-quality Results and Discussion section based on the attached microscopy image of the thin film. Discuss film morphology, grain growth, deposition quality, structural uniformity, and the relationship between deposition conditions and the observed microstructure.

Prompt 3 – Grain Structure Evaluation

Evaluate the grain morphology observed in the attached thin film image. Discuss grain size, grain boundaries, grain connectivity, and the possible effect of grain structure on the electrical, optical, mechanical, or corrosion properties of the film.

Prompt 4 – Surface Defect Analysis

Identify visible defects in the thin film, including cracks, pores, voids, pinholes, delamination, columnar structures, or surface irregularities. Explain their possible origin and discuss how they may affect film performance and long-term stability.

Prompt 5 – Correlation with Deposition Method

The thin film was prepared using the following deposition technique:

[Magnetron Sputtering / CVD / PVD / ALD / Sol-Gel / Spin Coating / Electrochemical Deposition / Other]

Discuss how the deposition method may have influenced the observed morphology, grain structure, and film quality.

Prompt 6 – Correlation with XRD

Correlate the observed thin-film morphology with the following XRD results:

• Crystal phases:
• Preferred orientation:
• Crystallite size:
• Residual strain:

Explain how the crystallographic characteristics support the observed microstructure and discuss any agreement or discrepancies.

Prompt 7 – Correlation with AFM

The AFM analysis reports:

• Surface roughness (Ra):
• RMS roughness:
• Maximum height:

Discuss how these AFM measurements relate to the morphology observed in the microscopy image and explain whether both techniques provide consistent information about the film surface.

Prompt 8 – Comparison with Published Literature

Compare the morphology and microstructure of the attached thin film with similar thin films reported in recent scientific literature. Discuss similarities, differences, and possible reasons based on deposition parameters, substrate type, or post-treatment conditions.

Prompt 9 – Reviewer Response

Reviewer Comment:

“The manuscript provides microscopy images of the thin film but lacks sufficient discussion regarding grain structure and film quality.”

Prepare a professional point-by-point response explaining the observed microstructure, discussing the deposition–structure relationship, and providing revised manuscript text suitable for inclusion in the Results and Discussion section.

Prompt 10 – Scientific Figure Caption

Generate a concise, publication-ready figure caption for the attached thin-film microscopy image. Describe the film morphology, grain structure, surface quality, and any notable structural features without repeating information already discussed in the manuscript.

MOFs (Metal–Organic Frameworks)

Prompt 1 – General MOF Morphology Analysis

Analyze the attached SEM/FESEM/TEM image of the MOF material. Describe the crystal morphology, particle shape, crystal size, surface texture, dispersion, agglomeration, and structural uniformity. Discuss how these morphological features may influence adsorption, catalysis, gas storage, or electrochemical performance.

Prompt 2 – Publication-Ready Results & Discussion

Write a publication-quality Results and Discussion section based on the attached microscopy image of the MOF. Explain the observed crystal morphology, particle distribution, synthesis–structure relationship, and discuss how the morphology contributes to the material’s functional properties.

Prompt 3 – Crystal Shape Identification

Analyze the attached microscopy image and identify the dominant crystal morphology (octahedral, cubic, rod-like, spherical, flower-like, plate-like, or irregular). Explain the possible crystal growth mechanism responsible for the observed morphology.

Prompt 4 – Crystal Growth Mechanism

The MOF was synthesized using the following conditions:

• Metal precursor:
• Organic linker:
• Solvent:
• Temperature:
• Reaction time:

Based on the observed morphology, explain the probable nucleation and crystal growth mechanism and discuss how the synthesis parameters influenced crystal formation.

Prompt 5 – Correlation with XRD

Correlate the observed MOF morphology with the following XRD results:

• Crystal phase:
• Crystallinity:
• Preferred orientation:
• Average crystallite size:

Explain how the diffraction results support the morphology observed in the microscopy images.

Prompt 6 – Correlation with BET

The BET analysis reports:

• Surface area:
• Total pore volume:
• Average pore diameter:

Discuss how the observed crystal morphology and particle arrangement contribute to the measured textural properties and explain whether the microscopy observations are consistent with the BET results.

Prompt 7 – Correlation with FTIR

Interpret the microscopy observations together with the FTIR spectrum. Explain how the formation of metal–ligand coordination bonds supports the observed crystal morphology and discuss whether the FTIR results confirm successful MOF synthesis.

Prompt 8 – Comparison with Published Literature

Compare the morphology of the attached MOF with similar MOFs reported in recent scientific literature. Discuss similarities, differences, and possible reasons for the observed crystal size, morphology, and structural characteristics.

Prompt 9 – Reviewer Response

Reviewer Comment:

“The microscopy images of the MOF are presented without sufficient discussion regarding crystal morphology and growth mechanism.”

Prepare a professional point-by-point response explaining the observed crystal morphology, discussing the formation mechanism, comparing the results with published literature, and providing revised manuscript text suitable for inclusion in the Results and Discussion section.

Prompt 10 – Scientific Figure Caption

Generate a concise, publication-ready figure caption for the attached microscopy image of the MOF. Describe the crystal morphology, particle size, structural uniformity, and any notable morphological features without repeating information already discussed in the manuscript.

MXenes

Prompt 1 – General MXene Morphology Analysis

Analyze the attached SEM/FESEM/TEM image of the MXene material. Describe the layered morphology, sheet size, surface texture, interlayer spacing, wrinkles, folds, defects, and stacking behavior. Discuss how these structural characteristics influence the material’s physical, chemical, and electrochemical properties.

Prompt 2 – Publication-Ready Results & Discussion

Write a publication-quality Results and Discussion section based on the attached microscopy image of the MXene. Explain the observed layered structure, exfoliation quality, sheet morphology, and discuss the relationship between synthesis conditions and the resulting microstructure.

Prompt 3 – Exfoliation Evaluation

Evaluate the degree of exfoliation observed in the attached microscopy image. Discuss whether the MXene sheets appear fully exfoliated, partially exfoliated, or restacked. Explain how the exfoliation quality may affect electrical conductivity, ion transport, and surface activity.

Prompt 4 – Layered Structure Interpretation

Analyze the attached microscopy image and discuss the characteristic two-dimensional layered morphology of the MXene. Explain the presence of stacked sheets, wrinkles, folded edges, and interlayer spacing, and discuss how these features influence the material’s performance.

Prompt 5 – Correlation with XRD

Correlate the observed MXene morphology with the following XRD results:

• MAX precursor phase:
• MXene phase:
• (002) peak position:
• Interlayer spacing:

Explain how the shift of the (002) diffraction peak supports successful etching and exfoliation, and discuss how these structural changes relate to the observed microscopy features.

Prompt 6 – Correlation with XPS

Interpret the microscopy observations together with the following XPS results:

• Surface terminations:
• Oxidation states:
• Elemental composition:

Discuss how the surface chemistry identified by XPS supports the morphology observed in the microscopy images and explain the influence of surface functional groups on MXene properties.

Prompt 7 – Correlation with BET

The BET analysis reports:

• Surface area:
• Total pore volume:
• Average pore diameter:

Discuss how the observed layered morphology, sheet separation, and restacking behavior influence the measured textural properties. Explain whether the microscopy observations are consistent with the BET results.

Prompt 8 – Comparison with Published Literature

Compare the morphology of the attached MXene with similar MXene materials reported in recent scientific literature. Discuss similarities, differences, exfoliation quality, sheet dimensions, and possible reasons for the observed structural characteristics.

Prompt 9 – Reviewer Response

Reviewer Comment:

“The microscopy images provide only qualitative observations and do not adequately discuss MXene exfoliation and layered morphology.”

Prepare a professional point-by-point response explaining the observed layered structure, exfoliation quality, sheet morphology, and their relationship with XRD, XPS, and BET results. Include revised manuscript text suitable for the Results and Discussion section.

Prompt 10 – Scientific Figure Caption

Generate a concise, publication-ready figure caption for the attached MXene microscopy image. Describe the layered morphology, sheet structure, exfoliation characteristics, and any notable structural features without repeating information already discussed in the manuscript.

Batteries

Prompt 1 – Electrode Morphology Analysis

Analyze the attached SEM/FESEM/TEM image of the battery electrode material. Describe the particle morphology, surface roughness, porosity, particle connectivity, agglomeration, and microstructural uniformity. Discuss how these features may influence ion transport, electrical conductivity, and electrochemical performance.

Prompt 2 – Publication-Ready Results & Discussion

Write a publication-quality Results and Discussion section based on the attached microscopy image of the battery electrode. Explain the observed morphology, discuss the relationship between microstructure and electrochemical properties, and write in the style of a high-impact battery journal.

Prompt 3 – Ion Transport Pathways

Based on the attached microscopy image, discuss how the observed morphology may facilitate or hinder ion diffusion and electrolyte penetration. Explain the relationship between pore structure, particle arrangement, and electrochemical kinetics.

Prompt 4 – Structural Stability During Cycling

Discuss how the morphology observed in the microscopy image may influence the structural stability of the electrode during repeated charge–discharge cycles. Explain the possible effects of particle cracking, agglomeration, or volume expansion on cycling performance.

Prompt 5 – Correlation with Electrochemical Performance

Correlate the observed electrode morphology with the following electrochemical results:

• Specific capacity:
• Coulombic efficiency:
• Rate capability:
• Capacity retention:
• Cycle life:

Explain how the morphology contributes to the observed electrochemical behavior.

Prompt 6 – Correlation with EIS

Interpret the attached microscopy image together with the following Electrochemical Impedance Spectroscopy (EIS) results:

• Solution resistance (Rs):
• Charge transfer resistance (Rct):
• Warburg impedance:
• Equivalent circuit:

Discuss how particle morphology, porosity, and particle connectivity influence charge transfer resistance and ion diffusion.

Prompt 7 – Correlation with XRD and BET

Correlate the electrode morphology with the following characterization results:

• XRD:
• BET surface area:
• Average pore diameter:

Explain how crystallinity, surface area, and pore structure collectively influence battery performance.

Prompt 8 – Comparison with Published Literature

Compare the observed electrode morphology with similar battery electrode materials reported in recent scientific literature. Discuss similarities, differences, and explain how the morphology may contribute to improved electrochemical performance.

Prompt 9 – Reviewer Response

Reviewer Comment:

“The microscopy images do not adequately explain the relationship between electrode morphology and battery performance.”

Prepare a professional point-by-point response discussing the observed morphology, its influence on ion transport, charge transfer, structural stability, and electrochemical performance. Include revised manuscript text suitable for the Results and Discussion section.

Prompt 10 – Scientific Figure Caption

Generate a concise, publication-ready figure caption for the attached microscopy image of the battery electrode. Describe the observed morphology, porosity, particle connectivity, and structural features, emphasizing their relevance to electrochemical performance without repeating information already discussed in the manuscript.

Batteries

Prompt 1 – Electrode Morphology Analysis

Analyze the attached SEM/FESEM/TEM image of the battery electrode material. Describe the particle morphology, surface roughness, porosity, particle connectivity, agglomeration, and microstructural uniformity. Discuss how these features may influence ion transport, electrical conductivity, and electrochemical performance.

Prompt 2 – Publication-Ready Results & Discussion

Write a publication-quality Results and Discussion section based on the attached microscopy image of the battery electrode. Explain the observed morphology, discuss the relationship between microstructure and electrochemical properties, and write in the style of a high-impact battery journal.

Prompt 3 – Ion Transport Pathways

Based on the attached microscopy image, discuss how the observed morphology may facilitate or hinder ion diffusion and electrolyte penetration. Explain the relationship between pore structure, particle arrangement, and electrochemical kinetics.

Prompt 4 – Structural Stability During Cycling

Discuss how the morphology observed in the microscopy image may influence the structural stability of the electrode during repeated charge–discharge cycles. Explain the possible effects of particle cracking, agglomeration, or volume expansion on cycling performance.

Prompt 5 – Correlation with Electrochemical Performance

Correlate the observed electrode morphology with the following electrochemical results:

• Specific capacity:
• Coulombic efficiency:
• Rate capability:
• Capacity retention:
• Cycle life:

Explain how the morphology contributes to the observed electrochemical behavior.

Prompt 6 – Correlation with EIS

Interpret the attached microscopy image together with the following Electrochemical Impedance Spectroscopy (EIS) results:

• Solution resistance (Rs):
• Charge transfer resistance (Rct):
• Warburg impedance:
• Equivalent circuit:

Discuss how particle morphology, porosity, and particle connectivity influence charge transfer resistance and ion diffusion.

Prompt 7 – Correlation with XRD and BET

Correlate the electrode morphology with the following characterization results:

• XRD:
• BET surface area:
• Average pore diameter:

Explain how crystallinity, surface area, and pore structure collectively influence battery performance.

Prompt 8 – Comparison with Published Literature

Compare the observed electrode morphology with similar battery electrode materials reported in recent scientific literature. Discuss similarities, differences, and explain how the morphology may contribute to improved electrochemical performance.

Prompt 9 – Reviewer Response

Reviewer Comment:

“The microscopy images do not adequately explain the relationship between electrode morphology and battery performance.”

Prepare a professional point-by-point response discussing the observed morphology, its influence on ion transport, charge transfer, structural stability, and electrochemical performance. Include revised manuscript text suitable for the Results and Discussion section.

Prompt 10 – Scientific Figure Caption

Generate a concise, publication-ready figure caption for the attached microscopy image of the battery electrode. Describe the observed morphology, porosity, particle connectivity, and structural features, emphasizing their relevance to electrochemical performance without repeating information already discussed in the manuscript.

Catalysts

Prompt 1 – Catalyst Morphology Analysis

Analyze the attached SEM/FESEM/TEM/HRTEM image of the catalyst. Describe the particle morphology, particle size, dispersion, porosity, agglomeration, exposed crystal facets, and surface characteristics. Discuss how these morphological features may influence catalytic activity, selectivity, and long-term stability.

Prompt 2 – Publication-Ready Results & Discussion

Write a publication-quality Results and Discussion section based on the attached catalyst microscopy image. Explain the observed morphology, discuss the synthesis–structure relationship, and describe how the microstructure contributes to catalytic performance using the writing style of a high-impact catalysis journal.

Prompt 3 – Active Site Discussion

Based on the observed morphology, discuss how the particle size, exposed surface area, pore structure, and crystal morphology may affect the number and accessibility of catalytic active sites.

Prompt 4 – Catalyst Dispersion Analysis

Evaluate the dispersion of catalyst nanoparticles observed in the microscopy image. Discuss whether the particles are uniformly distributed or agglomerated and explain how catalyst dispersion influences catalytic efficiency and stability.

Prompt 5 – Correlation with BET

The catalyst has the following BET characteristics:

• Surface area:
• Total pore volume:
• Average pore diameter:

Correlate these results with the observed morphology and discuss how surface area and pore structure contribute to catalytic performance.

Prompt 6 – Correlation with XRD and XPS

Correlate the observed catalyst morphology with the following characterization results:

• XRD:
• XPS:
• Crystal phases:
• Oxidation states:

Explain how the crystal structure, surface chemistry, and morphology collectively determine catalytic activity.

Prompt 7 – Correlation with Catalytic Performance

The catalyst exhibits the following performance:

• Conversion:
• Selectivity:
• Yield:
• Turnover frequency (TOF):
• Reaction rate:

Discuss how the observed morphology may explain the measured catalytic performance and identify the most important structure–activity relationships.

Prompt 8 – Comparison with Published Literature

Compare the morphology observed in the attached catalyst microscopy image with similar catalysts reported in recent scientific literature. Discuss similarities, differences, and explain how the morphology may contribute to improved catalytic performance compared with previous studies.

Prompt 9 – Reviewer Response

Reviewer Comment:

“The catalyst microscopy images are descriptive but do not adequately explain the relationship between morphology and catalytic performance.”

Prepare a professional point-by-point response discussing particle morphology, catalyst dispersion, active sites, and the correlation between microstructure and catalytic activity. Include revised manuscript text suitable for the Results and Discussion section.

Prompt 10 – Scientific Figure Caption

Generate a concise, publication-ready figure caption for the attached catalyst microscopy image. Describe the particle morphology, dispersion, porosity, and structural characteristics that are relevant to catalytic performance without repeating information already discussed in the manuscript.

Corrosion

Prompt 1 – Corrosion Surface Morphology Analysis

Analyze the attached SEM/FESEM image of the corroded sample. Describe the surface morphology, corrosion products, pits, cracks, voids, delamination, and other degradation features. Explain the possible corrosion mechanism responsible for the observed microstructure.

Prompt 2 – Publication-Ready Results & Discussion

Write a publication-quality Results and Discussion section based on the attached microscopy image of the corroded material. Discuss the observed corrosion morphology, corrosion mechanism, and the relationship between surface degradation and corrosion resistance using the writing style of a Q1 corrosion journal.

Prompt 3 – Pitting Corrosion Analysis

Evaluate the attached microscopy image for evidence of pitting corrosion. Describe pit morphology, pit density, pit distribution, and possible pit initiation sites. Discuss the mechanism of pitting corrosion and its influence on material durability.

Prompt 4 – Protective Coating Evaluation

Analyze the attached microscopy image of a coated metal surface after corrosion testing. Discuss coating integrity, cracks, pores, blistering, delamination, corrosion product formation, and evaluate the protective performance of the coating.

Prompt 5 – Correlation with Electrochemical Measurements

Correlate the observed corrosion morphology with the following electrochemical results:

• Open Circuit Potential (OCP)
• Polarization Curves
• Corrosion Potential (Ecorr)
• Corrosion Current Density (Icorr)
• Electrochemical Impedance Spectroscopy (EIS)

Explain how the electrochemical measurements support the observed corrosion morphology and degradation mechanism.

Prompt 6 – Correlation with EIS

The equivalent circuit fitting produced the following parameters:

• Rs:
• Rct:
• CPE:
• Warburg impedance:

Discuss how the observed surface morphology relates to the electrochemical impedance results. Explain how pits, pores, corrosion products, or protective films influence the charge transfer resistance and corrosion behavior.

Prompt 7 – Corrosion Product Identification

Analyze the attached microscopy image and discuss the morphology of the corrosion products. Explain whether the corrosion layer appears compact, porous, flaky, or cracked, and discuss how its morphology may influence the corrosion resistance of the material.

Prompt 8 – Correlation with XRD and XPS

Correlate the observed corrosion morphology with the following characterization results:

• XRD:
• XPS:
• EDS:

Discuss how the identified corrosion products, elemental composition, and oxidation states support the corrosion mechanism observed in the microscopy image.

Prompt 9 – Reviewer Response

Reviewer Comment:

“The SEM images of the corroded surface are descriptive but do not adequately explain the corrosion mechanism or relate the morphology to the electrochemical results.”

Prepare a professional point-by-point response explaining the observed corrosion morphology, discussing the corrosion mechanism, correlating the microscopy observations with electrochemical measurements, and providing revised manuscript text suitable for the Results and Discussion section.

Prompt 10 – Scientific Figure Caption

Generate a concise, publication-ready figure caption for the attached microscopy image of the corroded sample. Describe the observed corrosion morphology, corrosion products, pits, cracks, coating condition (if applicable), and the scientific significance of the image without repeating information already discussed in the manuscript.

Biomaterials

Prompt 1 – General Biomaterial Morphology Analysis

Analyze the attached SEM/FESEM/TEM image of the biomaterial. Describe the surface morphology, porosity, particle or fiber distribution, pore interconnectivity, roughness, and structural uniformity. Discuss how these characteristics may influence biocompatibility, cell attachment, tissue regeneration, and biomedical performance.

Prompt 2 – Publication-Ready Results & Discussion

Write a publication-quality Results and Discussion section based on the attached microscopy image of the biomaterial. Discuss the observed morphology, structural organization, fabrication–structure relationship, and explain how the microstructure contributes to the intended biomedical application.

Prompt 3 – Surface Topography and Cell Interaction

Evaluate the surface topography observed in the microscopy image. Discuss how the surface roughness, pore morphology, and micro/nanostructure may influence cell adhesion, proliferation, migration, differentiation, and tissue integration.

Prompt 4 – Scaffold Morphology Analysis

Analyze the attached microscopy image of a porous scaffold. Describe pore size, pore shape, pore distribution, pore interconnectivity, and scaffold architecture. Discuss whether the morphology is suitable for tissue engineering applications and explain the importance of interconnected porosity.

Prompt 5 – Fiber Morphology (Electrospun Biomaterials)

Analyze the attached microscopy image of electrospun fibers. Discuss fiber diameter, diameter distribution, fiber alignment, bead formation, fiber connectivity, and structural uniformity. Explain how these morphological characteristics influence the mechanical properties and biological performance of the scaffold.

Prompt 6 – Correlation with Mechanical Properties

Correlate the observed biomaterial morphology with the following mechanical properties:

• Tensile strength
• Young’s modulus
• Elongation at break
• Compression strength

Discuss how the observed microstructure contributes to the measured mechanical behavior.

Prompt 7 – Correlation with FTIR and XRD

Correlate the microscopy observations with the following characterization results:

• FTIR:
• XRD:
• EDS (if available)

Explain how the chemical composition and crystallinity support the observed morphology and discuss their combined influence on the biomaterial’s performance.

Prompt 8 – Comparison with Published Literature

Compare the morphology observed in the attached biomaterial microscopy image with similar biomaterials reported in recent scientific literature. Discuss similarities, differences, and explain how the observed morphology may improve biological performance compared with previous studies.

Prompt 9 – Reviewer Response

Reviewer Comment:

“The microscopy images provide only qualitative observations and do not sufficiently discuss how the morphology influences the biological performance of the biomaterial.”

Prepare a professional point-by-point response explaining the observed morphology, discussing its relationship with cell behavior, tissue engineering performance, and relevant characterization results. Include revised manuscript text suitable for the Results and Discussion section.

Prompt 10 – Scientific Figure Caption

Generate a concise, publication-ready figure caption for the attached microscopy image of the biomaterial. Describe the surface morphology, pore structure, fiber morphology (if applicable), and the structural characteristics relevant to biomedical applications without repeating information already discussed in the manuscript.

Polymers

Prompt 1 – Polymer Morphology Analysis

Analyze the attached SEM/FESEM/TEM image of the polymer sample. Describe the surface morphology, roughness, porosity, particle or fiber distribution, phase morphology, and structural homogeneity. Discuss how these features influence the mechanical, thermal, and functional properties of the polymer.

Prompt 2 – Publication-Ready Results & Discussion

Write a publication-quality Results and Discussion section based on the attached microscopy image of the polymer. Discuss the observed morphology, processing–structure relationship, and explain how the microstructure contributes to the polymer’s performance using the writing style of a Q1 polymer journal.

Prompt 3 – Fracture Surface Analysis

Analyze the attached SEM image of the fractured polymer surface. Discuss brittle or ductile fracture characteristics, crack propagation, void formation, fibrillation, and fracture mechanisms. Explain what the fracture morphology reveals about the mechanical behavior of the polymer.

Prompt 4 – Polymer Composite Morphology

Analyze the attached microscopy image of a polymer composite. Discuss the dispersion of fillers or nanoparticles, interfacial adhesion between the matrix and reinforcement, agglomeration, and structural uniformity. Explain how these morphological characteristics influence composite performance.

Prompt 5 – Electrospun Polymer Fibers

Analyze the attached microscopy image of electrospun polymer fibers. Discuss fiber diameter, diameter distribution, fiber alignment, bead formation, interconnected structure, and surface morphology. Explain how these characteristics influence filtration, tissue engineering, or mechanical performance.

Prompt 6 – Correlation with Mechanical Properties

Correlate the observed polymer morphology with the following mechanical properties:

• Tensile strength
• Young’s modulus
• Elongation at break
• Impact strength
• Hardness

Explain how the observed microstructure contributes to the measured mechanical behavior.

Prompt 7 – Correlation with FTIR, DSC, and XRD

Correlate the microscopy observations with the following characterization results:

• FTIR
• DSC
• XRD
• TGA (if available)

Discuss how the chemical structure, crystallinity, and thermal behavior support the observed morphology and explain their combined influence on polymer performance.

Prompt 8 – Comparison with Published Literature

Compare the morphology observed in the attached polymer microscopy image with similar polymer systems reported in recent scientific literature. Discuss similarities, differences, and explain how the observed morphology may improve the material’s mechanical, thermal, or functional properties.

Prompt 9 – Reviewer Response

Reviewer Comment:

“The microscopy images of the polymer are descriptive but do not adequately explain the relationship between morphology and material performance.”

Prepare a professional point-by-point response explaining the observed morphology, discussing its relationship with the polymer’s mechanical and thermal properties, and providing revised manuscript text suitable for inclusion in the Results and Discussion section.

Prompt 10 – Scientific Figure Caption

Generate a concise, publication-ready figure caption for the attached microscopy image of the polymer. Describe the surface morphology, fracture features, fiber or particle distribution (if applicable), and the structural characteristics relevant to polymer performance without repeating information already discussed in the manuscript.

Comparative Analysis

Prompt 1 – Comparative Morphology Analysis

Compare the attached microscopy images of Sample A and Sample B. Discuss differences in particle size, morphology, surface roughness, porosity, agglomeration, dispersion, and structural uniformity. Explain how these differences may influence the materials’ properties and performance.

Prompt 2 – Publication-Ready Comparative Discussion

Write a publication-quality comparative Results and Discussion section based on the attached microscopy images of multiple samples. Explain how changes in synthesis conditions affect the observed morphology and discuss the resulting differences in material performance.

Prompt 3 – Effect of Synthesis Parameters

The attached microscopy images correspond to samples prepared under different synthesis conditions.

Discuss how the following parameter influenced the observed morphology:

• Temperature
• Reaction time
• pH
• Precursor concentration
• Calcination temperature
• Etching time

Explain the possible growth mechanism responsible for the observed changes.

Prompt 4 – Before vs. After Modification

Compare the morphology of the pristine material and the modified material shown in the attached microscopy images. Discuss how the modification changed particle morphology, dispersion, porosity, or surface characteristics and explain the scientific significance of these changes.

Prompt 5 – Composite vs. Pure Material

Compare the microscopy images of the pure material and the corresponding composite. Explain how incorporating the secondary phase affected the morphology, particle distribution, interfacial structure, and overall microstructure.

Prompt 6 – Correlation with Performance

Compare the microscopy images together with the following experimental results:

• Electrochemical performance
• Catalytic activity
• Corrosion resistance
• Adsorption capacity
• Mechanical properties

Explain how the observed morphological differences account for the measured performance differences.

Prompt 7 – Multi-Technique Comparative Analysis

Compare the microscopy observations with the following characterization results for each sample:

• XRD
• XPS
• FTIR
• BET
• Raman
• EDS

Generate a comprehensive discussion explaining how structural, chemical, and morphological differences collectively explain the performance of each sample.

Prompt 8 – Literature Comparison

Compare the morphology of the attached samples with similar materials reported in recent scientific literature. Identify which sample exhibits the most desirable morphology and justify your conclusion based on published studies.

Prompt 9 – Reviewer Response

Reviewer Comment:

“The manuscript compares several samples but does not adequately explain the morphological differences among them.”

Prepare a professional point-by-point response explaining the observed differences in morphology, discussing their origin, correlating them with the experimental results, and providing revised manuscript text suitable for inclusion in the Results and Discussion section.

Prompt 10 – Comparative Summary Table

Based on the attached microscopy images, prepare a comparison table summarizing the key morphological characteristics of each sample, including:

• Particle shape
• Particle size
• Agglomeration
• Porosity
• Surface roughness
• Structural uniformity
• Expected effect on material performance

After the table, write a concise scientific discussion highlighting the most significant differences among the samples.

Scientific Writing

Prompt 1 – Results and Discussion

Based on the attached SEM/FESEM/TEM/HRTEM images, write a publication-ready Results and Discussion section suitable for submission to a Q1 journal. Discuss the observed morphology, correlate it with the synthesis method, and explain how the microstructure influences the material’s performance.

Prompt 2 – Figure Caption

Generate concise, publication-quality figure captions for the attached microscopy images. Use formal scientific language without repeating information already discussed in the manuscript.

Prompt 3 – Abstract Integration

Incorporate the findings from the attached microscopy images into the abstract of a scientific paper. Summarize the most important morphological observations and explain their significance in no more than three sentences.

Prompt 4 – Conclusion Writing

Write the conclusion section of a scientific paper using the attached microscopy results. Highlight the key morphological findings, explain their scientific significance, and discuss their relationship with the overall material performance.

Prompt 5 – Correlating Multiple Characterization Techniques

Using the attached microscopy images together with the following characterization results:

• XRD
• XPS
• FTIR
• BET
• Raman
• EDS

Write a coherent discussion explaining how all characterization techniques complement each other in confirming the material’s structure and properties.

Prompt 6 – Improve Scientific Writing

Rewrite the following microscopy discussion to improve scientific accuracy, grammar, readability, logical flow, and journal-quality writing while preserving the original scientific meaning.

[Paste your text here.]

Prompt 7 – Reviewer Response

Reviewer Comment:

“The discussion of the microscopy results is superficial and lacks scientific interpretation.”

Prepare a professional point-by-point response addressing the reviewer’s concern and provide revised manuscript text suitable for inclusion in the Results and Discussion section.

Prompt 8 – Literature Comparison

Compare the microscopy observations with similar studies published during the last five years. Highlight the novelty of the present work and explain how the observed morphology differs from or improves upon previously reported materials.

Prompt 9 – Graphical Summary

Based on the attached microscopy images, prepare a concise scientific summary describing the most important structural observations that could be used for a graphical abstract or a highlights section.

Prompt 10 – Journal-Specific Writing

Rewrite the microscopy discussion in the writing style typically used by high-impact journals such as Advanced Functional Materials, ACS Applied Materials & Interfaces, Chemical Engineering Journal, Journal of Colloid and Interface Science, or Applied Surface Science. Improve scientific depth, logical flow, and publication quality while maintaining factual accuracy.

Universal Prompts

Prompt 1 – Complete Microscopy Interpretation

Analyze the attached microscopy image (SEM, FESEM, TEM, HRTEM, STEM, or AFM) and provide a comprehensive scientific interpretation. Discuss the morphology, particle shape, particle size, surface texture, porosity, agglomeration, crystallinity (if visible), structural defects, and explain how these features may influence the material’s properties.

Prompt 2 – Journal-Ready Results & Discussion

Using the attached microscopy image and the material information below, write a publication-ready Results and Discussion section suitable for submission to a Q1 journal.

Material:
[Material Name]

Application:
[Application]

Synthesis Method:
[Synthesis Method]

Prompt 3 – Multi-Technique Correlation

Interpret the attached microscopy image together with the following characterization results:

• XRD
• XPS
• FTIR
• Raman
• BET
• EDS
• TGA
• Electrochemical measurements

Generate a comprehensive scientific discussion explaining how these techniques collectively confirm the structure, composition, and performance of the material.

Prompt 4 – Morphology–Property Relationship

Based on the attached microscopy image, explain how the observed morphology may influence the material’s:

• Mechanical properties
• Electrical conductivity
• Thermal stability
• Catalytic activity
• Electrochemical performance
• Corrosion resistance
• Adsorption capacity
• Optical properties

Provide a scientific explanation supported by established structure–property relationships.

Prompt 5 – Literature Comparison

Compare the observed morphology with similar materials reported in recent peer-reviewed literature (published within the last five years). Highlight similarities, differences, advantages, and the novelty of the present material.

Prompt 6 – Scientific Improvement

Rewrite my microscopy discussion to improve:

• Scientific accuracy
• Academic writing
• Grammar
• Logical flow
• Readability
• Journal quality

Do not change the scientific meaning.

Text:

[Paste your discussion here.]

Prompt 7 – Reviewer Response Generator

Act as an expert reviewer and prepare a professional response to the following reviewer comment regarding microscopy characterization.

Reviewer Comment:

[Paste reviewer comment]

Include both the response letter and the revised manuscript paragraph.

Prompt 8 – Figure Caption Generator

Generate a concise, publication-quality figure caption for the attached microscopy image. The caption should describe the key structural features, use formal scientific language, and avoid repeating information already presented in the manuscript.

Prompt 9 – Critical Evaluation

Act as a journal reviewer and critically evaluate the attached microscopy image and its interpretation. Identify missing analyses, unsupported claims, possible weaknesses, and suggest improvements that would strengthen the manuscript before journal submission.

Prompt 10 – AI Research Assistant

Act as an expert in materials science, nanotechnology, and electron microscopy. Analyze the attached microscopy image as if you were preparing a manuscript for a high-impact journal. Provide:

1. A detailed morphology interpretation.
2. The possible formation mechanism.
3. Correlation with complementary characterization techniques.
4. Comparison with published literature.
5. Scientific significance of the observed morphology.
6. A publication-ready Results and Discussion section.
7. Suggestions for improving the manuscript.
8. Potential reviewer comments and appropriate responses.

10. Expert Prompt Templates

The following templates are designed for researchers who want to obtain high-quality, publication-ready responses from AI models such as ChatGPT, Claude, Gemini, or AnalyzeTest AI. Simply replace the placeholders with your own information before submitting the prompt.

Template 1 – Complete Microscopy Analysis

Role: Act as an expert in materials science, nanotechnology, and electron microscopy.

Prompt:

I have attached a microscopy image of the following material:

Material:
[Material Name]

Characterization Technique:
[SEM / FESEM / TEM / HRTEM / STEM]

Application:
[Battery / Catalyst / MOF / MXene / Polymer / Biomaterial / Corrosion / etc.]

Please perform a comprehensive scientific analysis including:

1. Morphology interpretation
2. Particle shape and size
3. Agglomeration analysis
4. Surface roughness
5. Porosity
6. Structural defects
7. Growth mechanism
8. Influence on material performance
9. Comparison with recent literature
10. Publication-ready Results and Discussion section

Template 2 – Multi-Technique Characterization

Prompt:

Analyze my microscopy results together with the following characterization data:

• XRD:
• XPS:
• FTIR:
• Raman:
• BET:
• EDS:
• Electrochemical Results:

Generate a comprehensive scientific discussion explaining how all characterization techniques complement each other and support the proposed material structure.

Template 3 – Reviewer Response

Prompt:

Act as a scientific writing expert.

Reviewer Comment:

“[Paste reviewer comment]”

Using the attached microscopy image and my manuscript, prepare:

• A professional reviewer response.
• Revised manuscript text.
• Additional scientific discussion that addresses the reviewer’s concern.

Template 4 – Q1 Journal Writing

Prompt:

Rewrite the microscopy discussion in the writing style of a high-impact journal such as:

• Advanced Functional Materials
• ACS Applied Materials & Interfaces
• Chemical Engineering Journal
• Journal of Colloid and Interface Science
• Applied Surface Science

Improve scientific depth, logical flow, grammar, and readability while preserving the original meaning.

Template 5 – Comparative Analysis

Prompt:

I have attached microscopy images for multiple samples.

Please compare them with respect to:

• Particle size
• Morphology
• Agglomeration
• Surface roughness
• Porosity
• Structural defects
• Crystallinity (if applicable)

Explain how these differences influence the measured properties and determine which sample exhibits the best overall morphology.

Template 6 – Literature Comparison

Prompt:

Compare the morphology observed in my microscopy image with similar materials reported in peer-reviewed publications from the last five years.

Include:

• Similarities
• Differences
• Advantages of my material
• Scientific novelty
• Suggestions for strengthening the manuscript

Template 7 – Figure Caption Generator

Prompt:

Generate a concise, publication-quality figure caption for the attached microscopy image.

The caption should:

• Describe the morphology.
• Mention important structural features.
• Use formal scientific language.
• Be suitable for a Q1 journal.
• Avoid repeating information already presented in the manuscript.

Template 8 – AI Manuscript Assistant

Prompt:

Act as a senior professor in materials science.

Using the attached microscopy image and the following material information:

Material:
[Material Name]

Synthesis Method:
[Method]

Application:
[Application]

Generate:

• Scientific interpretation
• Growth mechanism
• Structure–property relationship
• Correlation with XRD/XPS/FTIR/BET
• Comparison with published literature
• Results and Discussion
• Conclusion paragraph
• Possible reviewer comments
• Suggested responses to reviewers

Template 9 – Thesis Writing Assistant

Prompt:

Rewrite the microscopy analysis as a PhD dissertation chapter.

Use an academic writing style appropriate for a doctoral thesis.

Include:

• Scientific interpretation
• Detailed discussion
• Literature support
• Logical transitions
• Professional formatting

Template 10 – AnalyzeTest AI Premium Prompt

Prompt:

Act as a senior materials scientist with expertise in electron microscopy, nanomaterials, crystallography, and scientific publishing.

Analyze the attached microscopy images as if you are preparing a manuscript for submission to a top-tier journal.

Your report should include:

1. Complete morphology analysis
2. Particle size interpretation
3. Agglomeration evaluation
4. Defect analysis
5. Growth mechanism
6. Correlation with XRD, XPS, FTIR, BET, Raman, and EDS
7. Literature comparison
8. Publication-ready Results and Discussion
9. Figure captions
10. Reviewer-response suggestions
11. Recommendations for improving the manuscript
12. Identification of missing analyses that would strengthen the study.

11. Frequently Asked Questions (FAQs)

1. Can AI accurately analyze SEM, FESEM, TEM, or HRTEM images?

AI can provide excellent qualitative interpretations of electron microscopy images, including morphology, particle shape, agglomeration, porosity, and structure–property relationships. However, AI cannot reliably perform quantitative image analysis such as particle size measurement, HRTEM lattice fringe analysis, or SAED indexing without specialized software and expert verification.

2. Can AI measure particle size from microscopy images?

Not accurately.

AI may estimate particle size visually, but publication-quality particle size measurements require dedicated image analysis software such as ImageJ, along with manual verification by an experienced researcher.

3. Can AI replace ImageJ?

No.

ImageJ remains the standard tool for quantitative microscopy analysis, including:

• Particle size measurement
• Grain size analysis
• Circularity
• Aspect ratio
• Feret diameter
• Surface coverage
• Image segmentation

AI is best used to interpret the results obtained from ImageJ—not replace them.

4. Can AI analyze HRTEM lattice fringes?

Not reliably.

Determining lattice spacing (d-spacing), identifying crystal planes, and confirming crystal structures from HRTEM images require expert analysis and specialized image-processing tools.

5. Can AI index SAED patterns?

No.

Accurate SAED indexing requires diffraction analysis, crystallographic calculations, and comparison with reference databases. AI can explain an indexed SAED pattern but should not be relied upon for indexing itself.

6. Can AI interpret EDS elemental mapping?

Yes.

AI can explain elemental distribution, compositional homogeneity, phase segregation, and correlate EDS mapping with SEM, TEM, XRD, or XPS results. However, quantitative elemental analysis should always rely on the original EDS data.

7. Can AI generate publication-ready Results and Discussion sections?

Yes.

One of AI’s greatest strengths is generating well-written scientific discussions, figure captions, reviewer responses, and publication-ready manuscript sections when provided with accurate experimental data.

8. Which AI model works best for microscopy interpretation?

Modern large language models such as ChatGPT, Claude, Gemini, and AnalyzeTest AI can all generate high-quality scientific discussions. The quality of the output depends primarily on the quality of the prompt and the experimental information provided.

9. Can AI compare my microscopy results with published literature?

Yes.

AI can compare your observations with published studies, identify similarities and differences, discuss novelty, and explain possible reasons for discrepancies. For the most reliable results, provide your material details and request comparison with recent literature.

10. Why use AnalyzeTest AI instead of a general AI chatbot?

AnalyzeTest AI is specifically designed for researchers in materials science and nanotechnology. In addition to AI-assisted interpretation, AnalyzeTest also provides expert services including:

• Particle size analysis
• Grain size measurement
• ImageJ quantitative analysis
• HRTEM lattice fringe analysis
• SAED indexing
• STEM/EDS mapping interpretation
• Publication-ready scientific writing
• Reviewer response preparation
• Complete characterization correlation (SEM, TEM, XRD, XPS, FTIR, BET, Raman, EIS, and more)

This combination of AI assistance and expert scientific review produces results that are significantly more reliable for research publications than AI alone.

12. Why AnalyzeTest AI Is Different

Hundreds of AI tools can generate scientific text, but very few truly understand materials characterization. AnalyzeTest AI was developed specifically for researchers working with advanced characterization techniques, combining artificial intelligence with expert scientific analysis to produce publication-ready results.

Unlike general-purpose AI chatbots, AnalyzeTest AI focuses on interpreting characterization data used in materials science, nanotechnology, chemistry, corrosion, catalysis, energy storage, and polymer research.

AI-Assisted Scientific Interpretation

AnalyzeTest AI helps researchers:

• Interpret SEM, FESEM, TEM, HRTEM, STEM, and EDS Mapping results.
• Generate publication-ready Results and Discussion sections.
• Write professional figure captions.
• Compare experimental results with published literature.
• Correlate microscopy with XRD, XPS, FTIR, Raman, BET, EIS, and other characterization techniques.
• Prepare reviewer responses.
• Improve scientific writing for Q1 journals.

Expert Analysis Beyond AI

One of the biggest limitations of AI is that it cannot reliably perform quantitative microscopy analysis. AnalyzeTest bridges this gap by providing expert services performed by experienced researchers.

Our expert microscopy services include:

• Particle size analysis using ImageJ
• Grain size measurement
• Morphology quantification
• Image segmentation
• HRTEM lattice fringe analysis
• d-spacing measurement
• Crystal plane identification
• SAED pattern indexing
• STEM image interpretation
• EDS elemental mapping analysis
• Quantitative image analysis
• Professional publication-ready figures

Complete Characterization Support

AnalyzeTest is not limited to electron microscopy. Researchers can receive integrated interpretation of multiple characterization techniques, including:

• SEM / FESEM
• TEM / HRTEM
• STEM
• EDS Mapping
• XRD
• XPS
• FTIR
• Raman
• BET
• TGA
• UV–Vis
• EIS
• AFM
• NMR

This integrated approach produces a coherent scientific discussion rather than isolated interpretations of individual techniques.

Designed for Researchers

AnalyzeTest AI is built specifically for:

• Materials scientists
• Chemists
• Nanotechnology researchers
• Corrosion engineers
• Battery researchers
• Polymer scientists
• Catalysis researchers
• MOF and MXene researchers
• Graduate students
• PhD candidates
• Academic authors

Human Expertise + Artificial Intelligence

Rather than replacing scientific expertise, AnalyzeTest AI combines the speed of artificial intelligence with expert validation. Researchers benefit from faster manuscript preparation while maintaining the scientific accuracy required for publication in high-impact journals.

This hybrid workflow significantly reduces writing time, improves consistency across characterization sections, and helps produce manuscripts that meet the standards of leading international journals.

13. Conclusion

Artificial intelligence is rapidly transforming the way researchers analyze characterization data and prepare scientific manuscripts. For electron microscopy techniques such as SEM, FESEM, TEM, HRTEM, STEM, and EDS Mapping, AI has become a powerful assistant for interpreting morphology, improving scientific writing, comparing results with published literature, generating publication-ready discussions, and responding to reviewer comments.

However, AI is not a substitute for quantitative microscopy analysis. Critical tasks such as particle size measurement, grain size analysis, ImageJ-based quantification, HRTEM lattice fringe analysis, SAED indexing, and digital image processing still require specialized software and expert interpretation. Recognizing these limitations is essential for producing scientifically accurate and reliable research.

The 200 AI prompts presented in this guide provide researchers with a practical toolkit for obtaining higher-quality responses from AI systems. By combining well-designed prompts with accurate experimental data, researchers can significantly improve the efficiency of manuscript preparation while maintaining scientific rigor.

AnalyzeTest AI goes one step further by integrating AI-assisted scientific writing with professional microscopy analysis. This hybrid approach allows researchers to benefit from both the speed of artificial intelligence and the accuracy of expert validation. Whether you need qualitative interpretation, quantitative image analysis, multi-technique characterization, or publication-ready manuscript preparation, AnalyzeTest provides a comprehensive solution for modern materials research.

As AI continues to evolve, the most successful researchers will not be those who rely entirely on artificial intelligence, but those who combine human expertise, experimental evidence, and AI-assisted analysis to produce high-quality, reproducible, and impactful scientific research.

Ready to Improve Your Microscopy Analysis?

Explore AnalyzeTest AI to:

• Generate professional SEM, FESEM, TEM, and HRTEM interpretations
• Prepare publication-ready Results & Discussion sections
• Correlate microscopy with XRD, XPS, FTIR, BET, Raman, and EIS
• Perform expert particle size analysis using ImageJ
• Obtain HRTEM lattice fringe analysis and SAED indexing
• Improve manuscripts and prepare reviewer responses
• Accelerate your research with AI backed by expert scientific validation

Analyze smarter. Publish faster. Publish better.

Introduction

X-ray Diffraction (XRD) is one of the most powerful and widely used characterization techniques in materials science for identifying crystalline phases, evaluating crystal structures, estimating crystallite size, determining lattice parameters, analyzing microstrain, and investigating structural evolution in materials. From nanomaterials and catalysts to batteries, polymers, biomaterials, thin films, MOFs, MXenes, and corrosion-resistant coatings, XRD plays a critical role in understanding the relationship between structure and material performance.

With the rapid development of artificial intelligence, many researchers are now asking whether AI tools such as ChatGPT, Gemini, Claude, or specialized scientific assistants can analyze XRD data automatically. The answer is both yes and no.

Artificial intelligence is exceptionally good at interpreting processed XRD results, explaining diffraction patterns, improving scientific writing, generating publication-ready discussions, comparing multiple diffraction patterns, answering reviewers’ comments, and assisting researchers in understanding crystallographic concepts. However, many of the most important steps in XRD analysis are not AI tasks.

For example, reliable phase identification, search-match analysis, peak indexing, Rietveld refinement, lattice parameter calculation, quantitative phase analysis, Williamson–Hall analysis, and many other crystallographic procedures require specialized software and, more importantly, the expertise of experienced researchers. These analyses depend on experimental conditions, crystallographic databases, fitting strategies, and scientific judgment that current AI systems cannot replace.

At AnalyzeTest AI, we follow a hybrid approach that combines the strengths of expert crystallographic analysis with artificial intelligence. When necessary, phase identification, crystallographic calculations, and quantitative analyses are performed by experienced materials scientists using professional XRD software. AI is then used to transform these validated results into clear, publication-ready scientific interpretations, reviewer responses, and high-quality manuscript sections.

This approach provides researchers with the best of both worlds: the accuracy of expert XRD analysis and the speed and writing capabilities of modern AI.

In this comprehensive guide, you will discover 180 powerful AI prompts for XRD analysis, covering virtually every aspect of diffraction interpretation—from phase identification discussions and crystallite size analysis to thin films, batteries, catalysts, MOFs, polymers, nanomaterials, scientific writing, and reviewer responses. You will also learn when AI can accelerate your research, when expert crystallographic analysis is still essential, and how to combine both approaches to produce reliable, publication-quality XRD reports.

2. Can AI Really Analyze XRD Data?

The short answer is yes—but only to a certain extent.

Artificial intelligence has become an increasingly valuable assistant for researchers working with X-ray Diffraction (XRD) data. Modern AI tools can rapidly explain diffraction patterns, compare multiple samples, summarize structural changes, improve scientific writing, and generate publication-ready discussions. They can also help researchers understand crystallographic concepts, interpret the effects of synthesis parameters, and prepare responses to journal reviewers.

However, there is an important distinction that many researchers overlook:

AI can interpret XRD results, but it cannot reliably perform the complete XRD analysis workflow.

Many websites claim that AI can “analyze XRD data automatically.” In reality, the most critical parts of XRD analysis require specialized crystallographic software, reference databases, and scientific expertise. AI models do not directly access diffraction databases such as the ICDD PDF database, nor can they reliably perform complex crystallographic refinements from raw diffraction patterns.

For example, AI is generally well suited for tasks such as:

• Explaining diffraction peaks after phase identification
• Interpreting structural changes between samples
• Discussing crystallite size trends
• Relating XRD results to material properties
• Comparing multiple diffraction patterns
• Generating publication-ready Results and Discussion sections
• Improving scientific writing
• Drafting reviewer responses
• Integrating XRD findings with complementary techniques such as SEM, TEM, FTIR, Raman, or XPS

On the other hand, AI cannot reliably perform tasks such as:

• Accurate phase identification from raw diffraction patterns
• Search-match analysis using crystallographic databases
• Peak indexing
• Rietveld refinement
• Quantitative phase analysis
• Lattice parameter refinement
• Unit-cell determination
• Williamson–Hall analysis
• Residual stress calculations
• Texture analysis
• Instrumental broadening correction
• Validation of ambiguous phase mixtures

These procedures require specialized software (such as HighScore Plus, JADE, GSAS-II, FullProf, TOPAS, or MAUD), appropriate crystallographic databases, and expert interpretation of the results.

For this reason, AnalyzeTest AI follows a different philosophy from generic AI assistants. Instead of attempting to replace crystallographic analysis, it complements it. Expert researchers first perform the necessary crystallographic calculations and validations when required, and AI is then used to convert those validated results into clear, accurate, and publication-ready scientific interpretations.

This hybrid workflow offers significant advantages. Researchers benefit from the efficiency of artificial intelligence while maintaining the scientific reliability that only expert crystallographic analysis can provide. As a result, the final report is not only technically accurate but also written in a style suitable for submission to high-impact scientific journals.

The most effective use of AI in XRD research is therefore not replacing the researcher, but empowering the researcher—automating repetitive writing tasks while leaving critical crystallographic decisions to experienced scientists.

3. What AI Cannot Do in XRD Analysis

Artificial intelligence has become an invaluable tool for interpreting XRD results and improving scientific writing. However, despite its impressive capabilities, there are several critical aspects of X-ray diffraction analysis that cannot currently be performed reliably by AI alone. Understanding these limitations is essential for avoiding incorrect conclusions and ensuring the scientific accuracy of your research.

Many researchers mistakenly assume that AI can take a raw diffraction pattern and automatically produce a complete crystallographic analysis. In reality, the most important steps of XRD analysis still require specialized crystallographic software, reference databases, and expert judgment.

1. Reliable Phase Identification

One of the most common misconceptions is that AI can accurately identify crystalline phases directly from an XRD pattern.

In practice, phase identification requires comparison with crystallographic reference databases such as the ICDD Powder Diffraction File (PDF), consideration of experimental conditions, possible peak overlaps, preferred orientation, impurities, and instrument-related effects. Generic AI models do not have direct access to these databases and cannot reliably distinguish between phases with highly similar diffraction patterns.

2. Search-Match Analysis

Professional XRD software performs sophisticated search-match algorithms to compare experimental diffraction patterns against thousands of reference patterns.

This process considers:

• Peak positions
• Relative intensities
• Background subtraction
• Instrumental corrections
• Candidate phase ranking

AI chatbots cannot reproduce this workflow with sufficient reliability.

3. Peak Indexing

Assigning Miller indices (hkl) to diffraction peaks requires crystallographic calculations based on crystal symmetry, lattice parameters, and space groups.

Although AI can explain what peak indexing is, it cannot reliably perform the calculations required for unknown materials.

4. Rietveld Refinement

Rietveld refinement is one of the most powerful techniques in crystallography.

It simultaneously refines:

• Crystal structure
• Lattice parameters
• Atomic positions
• Phase fractions
• Peak shapes
• Instrumental parameters
• Preferred orientation
• Microstructural effects

This iterative optimization process requires dedicated software and expert supervision. AI cannot replace this refinement procedure.

5. Quantitative Phase Analysis

Determining the percentage of each crystalline phase in a multiphase sample depends on accurate refinement of the diffraction pattern.

Without proper crystallographic refinement, any phase percentage suggested by AI would simply be speculation.

6. Crystallite Size Calculation from Raw Data

AI understands equations such as the Scherrer equation and Williamson–Hall method.

However, it cannot determine crystallite size unless researchers first provide:

• Correct peak positions
• FWHM values
• Instrumental broadening correction
• Shape factor
• X-ray wavelength

Incorrect input inevitably leads to incorrect results.

7. Lattice Parameter Refinement

Determining lattice constants requires crystallographic refinement rather than simple mathematical calculations.

Small experimental errors in peak position can significantly affect lattice parameters, making expert validation essential.

8. Microstrain and Residual Stress Analysis

Methods such as Williamson–Hall analysis or residual stress calculations require careful selection of diffraction peaks, instrumental corrections, and appropriate fitting models.

These analyses remain beyond the capabilities of general AI systems.

9. Distinguishing Instrumental Artifacts from Real Features

Experienced diffraction analysts can recognize whether unusual peaks originate from:

• Instrumental noise
• Sample holders
• Fluorescence
• Kβ radiation
• Preferred orientation
• Sample displacement
• Secondary phases

AI frequently lacks the contextual information needed to distinguish these artifacts from genuine diffraction features.

10. Scientific Judgment

Perhaps the most important limitation is that AI does not possess scientific judgment.

Experienced crystallographers routinely evaluate questions such as:

• Is this phase physically reasonable?
• Does the proposed structure agree with the synthesis route?
• Are the XRD results consistent with SEM, TEM, Raman, FTIR, or XPS?
• Could peak broadening result from strain rather than crystallite size?
• Is a secondary phase chemically plausible?

These decisions require domain expertise developed through years of research and cannot currently be replaced by artificial intelligence.

How AnalyzeTest AI Bridges This Gap

Rather than replacing crystallographic expertise, AnalyzeTest AI combines expert XRD analysis with AI-assisted scientific interpretation.

For projects requiring advanced analysis, our specialists can perform:

• Phase identification
• Search-match analysis
• Peak indexing
• Crystallite size calculation
• Lattice parameter determination
• Williamson–Hall analysis
• Quantitative phase analysis
• Publication-ready interpretation

Once these scientifically validated results are obtained, AI is used to generate high-quality discussions, reviewer responses, figure captions, and manuscript-ready text.

This hybrid workflow provides both scientific reliability and the speed of modern AI, allowing researchers to prepare accurate, publication-ready XRD reports with confidence.

4. How AnalyzeTest AI Combines Human Expertise with AI

Artificial intelligence has dramatically improved the efficiency of scientific research, but X-ray diffraction remains a discipline where expert knowledge and specialized crystallographic software are indispensable. The most reliable workflow is not to replace the researcher with AI, but to combine the strengths of both.

That is the philosophy behind AnalyzeTest AI.

Unlike generic AI platforms that attempt to answer every scientific question, AnalyzeTest AI is specifically designed for researchers working in materials science, chemistry, nanotechnology, corrosion engineering, catalysis, batteries, polymers, biomaterials, ceramics, thin films, MOFs, and MXenes. Our workflow integrates professional crystallographic analysis with AI-powered scientific interpretation, ensuring both technical accuracy and publication-quality writing.

Step 1 – Professional XRD Analysis

For projects requiring advanced analysis, experienced materials scientists first perform the necessary crystallographic work using industry-standard software such as HighScore Plus, JADE, GSAS-II, FullProf, TOPAS, or MAUD.

Depending on the project, this may include:

• Phase identification
• Search-match analysis
• Peak indexing
• Rietveld refinement
• Quantitative phase analysis
• Crystallite size calculation
• Lattice parameter refinement
• Williamson–Hall analysis
• Microstrain estimation
• Preferred orientation analysis
• Residual stress evaluation

These procedures require scientific judgment and cannot be reliably automated by current AI systems.

Step 2 – AI-Assisted Scientific Interpretation

Once the crystallographic analysis has been completed and validated, AnalyzeTest AI uses artificial intelligence to transform numerical results into clear, scientifically rigorous interpretations.

AI can rapidly generate:

• Publication-ready Results and Discussion sections
• Phase evolution discussions
• Structure–property relationship analysis
• Comparative analysis of multiple XRD patterns
• Scientific explanations of crystallographic changes
• Reviewer responses
• Figure captions
• Abstract summaries
• Conclusions written in the style of high-impact journals

This saves researchers many hours of writing while maintaining a consistent scientific style.

Step 3 – Integration with Other Characterization Techniques

A single XRD pattern rarely tells the whole story.

AnalyzeTest AI can integrate XRD results with complementary characterization techniques, including:

• SEM
• TEM
• EDS
• FTIR
• Raman spectroscopy
• XPS
• BET
• AFM
• UV–Vis spectroscopy
• TGA/DSC
• Electrochemical measurements
• Mechanical testing

By combining structural, morphological, chemical, thermal, and electrochemical information, the final interpretation becomes much stronger and more suitable for publication in leading scientific journals.

Why This Hybrid Approach Matters

Researchers often encounter one of two extremes:

• Generic AI tools, which generate fluent text but may lack crystallographic accuracy.
• Traditional crystallographic software, which produces numerical results but offers little assistance with scientific interpretation or manuscript preparation.

AnalyzeTest AI bridges this gap by combining the strengths of both approaches. Expert crystallographic analysis ensures that the technical results are accurate, while AI accelerates interpretation, scientific writing, and manuscript preparation.

This hybrid workflow minimizes errors, improves productivity, and allows researchers to focus on scientific discovery rather than repetitive writing tasks.

Designed for Research, Not Just Conversation

AnalyzeTest AI is more than a chatbot. It is a research assistant developed specifically for materials characterization.

Researchers can receive assistance with:

• Professional XRD interpretation
• Publication-ready scientific writing
• Reviewer-response preparation
• Comparative analysis of multiple samples
• AI prompt optimization
• Complete characterization reports
• Expert-supported crystallographic analysis when advanced calculations are required

Whether you are investigating nanomaterials, catalysts, battery electrodes, thin films, ceramics, biomaterials, or advanced functional materials, AnalyzeTest AI combines the efficiency of artificial intelligence with the reliability of expert crystallography, helping you produce accurate, publication-quality XRD analyses with confidence.

5. What Makes a Good AI Prompt for XRD?

The quality of an AI-generated XRD interpretation depends far more on the quality of the prompt than on the AI model itself. Even the most advanced AI systems cannot produce reliable scientific interpretations if they receive incomplete or ambiguous information. Conversely, a well-structured prompt can generate detailed, publication-ready discussions that significantly reduce the time required to prepare a scientific manuscript.

A common misconception is that researchers can simply upload an XRD pattern and ask, “Analyze this spectrum.” In reality, XRD interpretation requires context. The more information you provide, the more accurate and scientifically meaningful the AI response will be.

Start with Material Information

Every good XRD prompt should begin by clearly identifying the material being studied. This gives AI the scientific context needed to interpret structural changes correctly.

Include information such as:

• Material or sample name
• Chemical composition
• Doping elements and concentrations
• Composite components (if applicable)
• Crystal structure (if already known)

For example, a prompt that begins with “Interpret the XRD pattern of Fe-doped TiO₂ nanoparticles” is far more informative than simply asking AI to analyze an unknown diffraction pattern.

Describe the Experimental Conditions

Many structural changes observed in XRD are directly related to synthesis or processing conditions.

Whenever possible, include:

• Synthesis method
• Calcination temperature
• Annealing conditions
• Deposition technique
• Reaction time
• Milling conditions
• Heat treatment
• Pressure or atmosphere

These details help AI explain why diffraction peaks shift, broaden, or change in intensity.

Provide Processed Results Instead of Raw Patterns

Current AI models are much better at interpreting processed XRD results than raw diffraction data.

Instead of uploading only an image of the diffraction pattern, provide information such as:

• Identified phases
• Peak positions (2θ)
• Relative intensities
• FWHM values
• Crystallite size
• Lattice parameters
• Microstrain
• Phase percentages (if available)

This allows AI to focus on scientific interpretation rather than attempting unreliable crystallographic analysis.

Explain What You Want

Many users simply ask:

“Analyze my XRD.”

This request is too vague.

Instead, specify the exact task. For example:

• Interpret phase evolution.
• Compare multiple samples.
• Explain peak shifts.
• Discuss crystallite size changes.
• Correlate XRD with SEM or TEM.
• Prepare a publication-ready Results and Discussion section.
• Generate a reviewer response.
• Improve scientific writing.

Clear objectives produce far more useful AI outputs.

Include Complementary Characterization

The strongest scientific discussions combine XRD with other characterization techniques.

Whenever available, include results from:

• SEM
• TEM
• EDS
• FTIR
• Raman
• XPS
• BET
• AFM
• UV–Vis
• TGA/DSC
• Electrochemical measurements

AI can then build a coherent structure–property relationship rather than discussing XRD in isolation.

Mention the Target Journal

Different journals expect different writing styles.

If you are preparing a manuscript, specify your target journal, for example:

• Applied Surface Science
• Journal of Alloys and Compounds
• Ceramics International
• ACS Applied Materials & Interfaces
• Chemical Engineering Journal
• Advanced Functional Materials

AI can then adapt the discussion to match the scientific tone and level of detail expected by that journal.

Be Aware of AI’s Limitations

A good prompt also recognizes what AI should not be asked to do.

Do not expect AI to:

• Perform phase identification from raw diffraction patterns.
• Conduct Rietveld refinement.
• Calculate lattice parameters from unprocessed data.
• Perform search-match analysis.
• Replace professional crystallographic software.

Instead, use AI where it excels: interpreting validated results, improving scientific writing, comparing datasets, and explaining crystallographic phenomena.

The Best XRD Prompt Combines Expertise and Context

The most effective XRD prompts combine validated crystallographic results, experimental context, and clear research objectives. This enables AI to generate scientifically meaningful interpretations rather than generic descriptions.

At AnalyzeTest AI, our prompts are specifically engineered for materials characterization. They are designed to work alongside expert crystallographic analysis, helping researchers transform processed XRD results into publication-ready discussions, reviewer responses, and high-quality scientific manuscripts. By combining detailed prompts with validated experimental data, researchers can obtain faster, clearer, and far more reliable XRD interpretations than would be possible with generic AI requests.

6. Common Mistakes Researchers Make When Using AI for XRD

Artificial intelligence has become a valuable assistant for XRD interpretation, but obtaining accurate and scientifically meaningful results depends largely on how AI is used. Many disappointing AI responses are not caused by the AI itself—they result from incomplete information, unrealistic expectations, or misunderstandings about the capabilities of modern AI systems.

Below are the most common mistakes researchers make when using AI for X-ray diffraction analysis and how to avoid them.

1. Asking AI to Analyze a Raw XRD Pattern

One of the most frequent mistakes is uploading a diffraction pattern and asking:

“Analyze my XRD.”

While AI can describe visible features, it cannot reliably perform phase identification, search-match analysis, or crystallographic refinement directly from a raw diffraction pattern.

A much better approach is to first identify the phases using professional XRD software and then ask AI to interpret the validated results.

2. Expecting AI to Perform Phase Identification

Many researchers assume AI has access to crystallographic databases such as the ICDD Powder Diffraction File (PDF).

It does not.

Reliable phase identification requires comparison with reference diffraction patterns, consideration of impurities, preferred orientation, instrumental effects, and crystallographic expertise. Generic AI models cannot replace this process.

3. Expecting AI to Perform Rietveld Refinement

Rietveld refinement is an iterative optimization procedure involving crystallographic models, peak shapes, lattice parameters, preferred orientation, and numerous refinement constraints.

Current AI systems cannot perform this analysis.

Researchers should complete the refinement using specialized software before requesting AI-assisted interpretation.

4. Providing Too Little Information

Poor prompts often contain nothing more than:

“Interpret this XRD.”

Without information about the material, synthesis method, processing conditions, or identified phases, AI can only produce generic explanations.

High-quality prompts should include:

• Material composition
• Synthesis conditions
• Phase identification results
• Peak positions
• Crystallite size
• Experimental objectives

The more context provided, the better the interpretation.

5. Ignoring Complementary Characterization

XRD rarely provides the complete picture.

Researchers sometimes ask AI to explain material performance using only diffraction data while ignoring available information from:

• SEM
• TEM
• FTIR
• Raman
• XPS
• BET
• Thermal analysis
• Electrochemical measurements

Combining multiple characterization techniques allows AI to produce much stronger scientific discussions.

6. Assuming Every Peak Shift Has the Same Meaning

Small peak shifts can result from many different factors, including:

• Lattice distortion
• Dopant incorporation
• Residual stress
• Instrument calibration
• Thermal expansion
• Solid solution formation

AI should not be expected to determine the correct explanation without sufficient experimental context.

7. Blindly Accepting AI-Generated Interpretations

Although AI can generate convincing scientific text, it may occasionally:

• Overinterpret weak evidence
• Suggest chemically unreasonable phases
• Misidentify oxidation mechanisms
• Generalize beyond the available data

Researchers should always verify AI-generated conclusions using experimental evidence and published literature.

8. Ignoring Instrumental Broadening

Many users ask AI to calculate crystallite size without correcting for instrumental broadening.

This produces inaccurate results because peak broadening originates from both the instrument and the sample.

Reliable crystallite-size analysis requires proper instrumental correction before applying methods such as the Scherrer equation or Williamson–Hall analysis.

9. Using Generic Prompts Instead of Specialized Ones

Generic prompts usually produce generic answers.

Prompts specifically designed for:

• Nanomaterials
• Thin films
• Catalysts
• MOFs
• MXenes
• Batteries
• Corrosion-resistant coatings

typically generate much more relevant and publication-quality interpretations.

That is one of the primary reasons this guide contains 180 specialized XRD prompts covering different research fields.

10. Expecting AI to Replace an XRD Expert

Perhaps the biggest misconception is believing that AI eliminates the need for crystallographic expertise.

Artificial intelligence is an excellent research assistant, but it cannot replace:

• Crystallographers
• Materials scientists
• Experienced diffraction analysts
• Professional XRD software

The most successful workflow combines expert crystallographic analysis with AI-assisted interpretation and scientific writing.

Best Practice: Combine Expert Analysis with AI

The most reliable approach is to divide the workflow into two stages:

1. Perform the crystallographic analysis using professional software and expert judgment (phase identification, refinement, peak indexing, crystallite size calculations, etc.).
2. Use AI to interpret and communicate the results, generating publication-ready discussions, reviewer responses, figure captions, and scientifically sound explanations.

This hybrid strategy is the foundation of AnalyzeTest AI. Rather than attempting to replace crystallographic expertise, AnalyzeTest AI combines validated XRD analysis with advanced AI-powered scientific writing, allowing researchers to produce accurate, efficient, and publication-quality XRD reports with confidence.

7. Before vs. After: Poor and Excellent XRD Prompts

One of the biggest factors affecting the quality of AI-generated XRD interpretations is the quality of the prompt itself. A vague prompt forces AI to guess important details, often leading to generic or inaccurate responses. In contrast, a well-structured prompt provides sufficient scientific context, allowing AI to generate a detailed, publication-ready interpretation.

The examples below illustrate how a small improvement in prompt design can dramatically enhance the quality of AI-assisted XRD analysis.

Example 1 – General XRD Interpretation

❌ Poor Prompt

Analyze my XRD pattern.

✅ Excellent Prompt

I synthesized ZnO nanoparticles using a hydrothermal method at 180°C for 12 hours. XRD analysis identified the hexagonal wurtzite structure (JCPDS No. 36-1451), with no detectable impurity phases. The average crystallite size calculated using the Scherrer equation is 28 nm. Please write a publication-ready Results and Discussion section explaining phase purity, crystallinity, and the significance of the crystallite size.

Example 2 – Comparative Analysis

❌ Poor Prompt

Compare these XRD patterns.

✅ Excellent Prompt

Compare the XRD patterns of pure TiO₂ and Fe-doped TiO₂ nanoparticles. Explain the observed peak shifts, changes in peak intensity, crystallite size evolution, and discuss how Fe incorporation influences the crystal structure. Write the discussion in the style of an SCI journal.

Example 3 – Thin Films

❌ Poor Prompt

Explain my thin-film XRD.

✅ Excellent Prompt

These XRD patterns correspond to CoFeNi thin films deposited by RF magnetron sputtering at 75 W, 100 W, and 130 W. Discuss the preferred orientation, crystallinity, peak broadening, and structural evolution with increasing sputtering power. Relate the structural changes to the expected magnetic properties.

Example 4 – Nanomaterials

❌ Poor Prompt

Interpret my nanoparticle XRD.

✅ Excellent Prompt

The sample consists of CeO₂ nanoparticles synthesized by the sol-gel method. XRD confirms the fluorite cubic structure without secondary phases. The crystallite size decreased from 32 nm to 18 nm after Sm doping. Explain the effect of Sm incorporation on crystallinity, lattice distortion, and potential oxygen-vacancy formation.

Example 5 – Rietveld Results

❌ Poor Prompt

Explain my refinement.

✅ Excellent Prompt

Rietveld refinement confirmed that the sample contains 82 wt.% anatase TiO₂ and 18 wt.% rutile TiO₂ with excellent fitting statistics (Rwp = 7.8%). Please prepare a publication-ready discussion explaining the significance of the phase composition, refinement quality, and possible effects on photocatalytic performance.

Example 6 – Batteries

❌ Poor Prompt

Analyze my battery XRD.

✅ Excellent Prompt

Compare the XRD patterns of LiFePO₄ electrodes before cycling and after 200 charge–discharge cycles. Discuss phase stability, peak shifts, crystallinity changes, and possible structural degradation responsible for capacity fading.

Example 7 – Catalysts

❌ Poor Prompt

Explain catalyst XRD.

✅ Excellent Prompt

XRD analysis of Ni/Al₂O₃ catalysts before and after hydrogen reduction shows increased metallic Ni diffraction peaks and decreased NiO reflections. Explain the structural evolution during reduction and discuss its implications for catalytic activity.

Example 8 – Corrosion Studies

❌ Poor Prompt

Analyze corrosion XRD.

✅ Excellent Prompt

XRD patterns of carbon steel before and after 30 days of exposure to a 3.5 wt.% NaCl solution reveal the formation of Fe₂O₃ and FeOOH corrosion products. Discuss the corrosion mechanisms, phase evolution, and implications for corrosion resistance.

Example 9 – Multi-Technique Interpretation

❌ Poor Prompt

Explain these characterization results.

✅ Excellent Prompt

Integrate the XRD, SEM, FTIR, and XPS results of ZnO/graphene nanocomposites into a coherent publication-ready discussion. Explain how the structural, morphological, and surface chemical analyses support the enhanced photocatalytic performance of the composite.

Example 10 – Reviewer Response

❌ Poor Prompt

Answer the reviewer’s comment.

✅ Excellent Prompt

A reviewer requested a clearer explanation of the XRD peak shift observed after Mn doping in ZnO nanoparticles. Write a professional reviewer response explaining the origin of the peak shift, citing lattice distortion, ionic radius differences, and crystallographic evidence while maintaining a polite scientific tone.

Why Excellent Prompts Produce Better Results

The strongest XRD prompts typically include:

• Material composition
• Synthesis or processing method
• Experimental conditions
• Phase identification results
• Crystallographic calculations (if available)
• The specific objective of the analysis
• Desired output (discussion, reviewer response, comparison, figure caption, etc.)

The more scientific context you provide, the more accurate, relevant, and publication-ready the AI-generated interpretation becomes.

At AnalyzeTest AI, our prompt library has been specifically engineered for XRD research. Instead of relying on generic instructions, researchers can use optimized prompts tailored to crystallography, phase analysis, nanomaterials, thin films, batteries, catalysts, polymers, and many other materials systems. When combined with expert crystallographic analysis, these prompts enable AI to produce reliable, high-quality scientific content suitable for publication in leading journals.

8. How to Customize These Prompts for Your Own Research

The 180 AI prompts presented in this guide are designed as practical starting points rather than fixed templates. Every research project is unique, and the quality of an AI-generated interpretation depends on how well the prompt reflects your specific material, experimental conditions, and research objectives.

By customizing these prompts with your own data, you can obtain responses that are more accurate, scientifically relevant, and suitable for publication.

Step 1 – Replace the Material Name

Always begin by specifying the exact material under investigation.

Instead of writing:

Analyze my XRD results.

Write:

Analyze the XRD results of nitrogen-doped TiO₂ nanoparticles.

or

Interpret the XRD pattern of CoFeNi thin films deposited by RF magnetron sputtering.

Providing the material name immediately gives AI the scientific context needed for a meaningful interpretation.

Step 2 – Describe the Synthesis or Processing Method

Structural properties are strongly influenced by processing conditions.

Whenever possible, include information such as:

• Hydrothermal synthesis
• Sol-gel method
• Solid-state reaction
• Chemical precipitation
• RF magnetron sputtering
• Electrospinning
• Ball milling
• Annealing temperature
• Calcination conditions
• Reaction time

These details help AI explain structural evolution more accurately.

Step 3 – Include Your Crystallographic Results

AI performs best when it interprets validated crystallographic results rather than raw diffraction patterns.

Useful information includes:

• Identified crystalline phases
• Peak positions (2θ)
• Miller indices (hkl)
• Crystallite size
• Lattice parameters
• Microstrain
• Phase percentages
• Rietveld refinement results
• Williamson–Hall analysis
• Peak shifts

The more quantitative information provided, the better the final discussion.

Step 4 – Explain Your Research Goal

Tell AI exactly what you want it to do.

Examples include:

• Write a publication-ready Results and Discussion section.
• Compare two XRD patterns.
• Explain peak shifts after doping.
• Discuss crystallite size evolution.
• Correlate XRD with electrochemical performance.
• Prepare a reviewer response.
• Improve scientific writing.
• Generate a figure caption.

Clear objectives produce significantly better responses than vague requests.

Step 5 – Add Complementary Characterization

XRD rarely tells the entire story.

If available, include results from complementary techniques such as:

• SEM
• TEM
• EDS
• FTIR
• Raman spectroscopy
• XPS
• BET
• AFM
• UV–Vis spectroscopy
• Thermal analysis
• Electrochemical measurements

AI can then generate a more comprehensive structure–property relationship rather than interpreting XRD data in isolation.

Step 6 – Specify the Writing Style

If the goal is manuscript preparation, tell AI the style you need.

For example:

• Publication-ready discussion
• SCI journal style
• Nature-style writing
• Reviewer response
• Thesis chapter
• Scientific report
• Conference paper

This helps AI adapt the tone, level of detail, and writing style to your intended audience.

Step 7 – Know When Expert Analysis Is Required

It is equally important to recognize when AI should not be used as the primary analysis tool.

Do not ask AI to perform:

• Phase identification from raw diffraction patterns
• Search-match analysis
• Peak indexing
• Rietveld refinement
• Quantitative phase analysis
• Lattice parameter refinement

These tasks require professional crystallographic software and expert interpretation.

At AnalyzeTest AI, these analyses can be performed by experienced materials scientists. Once the crystallographic analysis is complete, AI is then used to generate publication-ready discussions, reviewer responses, and scientifically accurate interpretations.

A Simple Prompt Template

A well-structured XRD prompt can often be written using the following format:

Material: [Material name]
Synthesis: [Preparation method]
Experimental Conditions: [Calcination, annealing, deposition, etc.]
XRD Results: [Phases, crystallite size, lattice parameters, peak shifts, refinement results]
Complementary Characterization: [SEM, TEM, FTIR, Raman, XPS, etc.]
Task: [Interpret the results, compare samples, prepare a publication-ready discussion, answer reviewer comments, etc.]

Using this structure provides AI with the context necessary to generate accurate and meaningful responses.

The Best Results Come from Combining Expert Analysis with AI

The most successful researchers use AI after obtaining reliable crystallographic results. By combining validated XRD analysis with carefully designed prompts, AI becomes a powerful assistant for scientific interpretation rather than a substitute for crystallographic expertise.

This is the workflow adopted by AnalyzeTest AI—combining expert XRD analysis with advanced AI-powered scientific writing to help researchers produce accurate, efficient, and publication-ready manuscripts.

9. 180 AI Prompts for XRD Analysis

Artificial intelligence can significantly improve the efficiency of X-ray Diffraction (XRD) interpretation when used with well-designed prompts. The prompts in this guide are intended to help researchers generate publication-ready discussions, compare diffraction patterns, explain crystallographic changes, prepare reviewer responses, and connect XRD findings with complementary characterization techniques.

It is important to understand that these prompts are designed for interpreting validated XRD results, not for replacing professional crystallographic analysis. Before using AI, researchers should first perform essential analyses such as phase identification, search-match analysis, peak indexing, Rietveld refinement, crystallite size calculations, lattice parameter determination, or Williamson–Hall analysis using appropriate crystallographic software and expert judgment.

Once these analyses have been completed, AI becomes a powerful research assistant capable of transforming numerical results into clear, accurate, and publication-ready scientific interpretations.

The following 180 XRD prompts are organized into practical categories covering nearly every major application of XRD in materials science, chemistry, nanotechnology, energy storage, catalysis, corrosion engineering, biomaterials, polymers, ceramics, and thin-film research.

The categories include:

• Phase Identification Prompts
• Peak Assignment and Indexing Prompts
• Crystallite Size and Microstructure Prompts
• Lattice Parameter and Strain Analysis Prompts
• Rietveld Refinement Interpretation Prompts
• Thin Films and Coatings Prompts
• Nanomaterials Prompts
• Catalysts and Photocatalysts Prompts
• MOFs and MXenes Prompts
• Battery Materials Prompts
• Corrosion and Protective Coatings Prompts
• Polymers and Composite Materials Prompts
• Biomaterials and Ceramics Prompts
• Comparative XRD Analysis Prompts
• Scientific Writing and Reviewer Response Prompts
• Advanced Universal XRD Prompts

Each prompt can be customized by replacing the material name, synthesis conditions, crystallographic results, and research objective with your own experimental data. This simple customization enables AI to generate responses that are tailored to your specific research project rather than producing generic explanations.

If your project requires phase identification, Rietveld refinement, quantitative phase analysis, crystallite-size determination, or other advanced crystallographic calculations, AnalyzeTest AI also provides expert-assisted XRD services. In this workflow, experienced materials scientists first perform the required crystallographic analysis using professional software, after which AI is used to generate publication-ready discussions, reviewer responses, figure captions, and complete scientific reports.

The following sections present 180 carefully engineered AI prompts that can help you accelerate XRD interpretation while maintaining the scientific rigor expected in high-quality research publications.

Phase Identification AI Prompts (1–10)

Prompt 1

Identify the crystalline phases present in my XRD pattern based on the validated phase identification results. Explain the significance of each phase and discuss how they may influence the material’s physical and chemical properties.

Prompt 2

The identified phases are [Phase A], [Phase B], and [Phase C]. Write a publication-ready discussion explaining the formation mechanism of these phases during synthesis.

Prompt 3

Compare the identified crystalline phases before and after heat treatment. Explain why certain phases disappeared, transformed, or became more crystalline.

Prompt 4

Discuss the phase purity of my sample based on the identified XRD phases. Explain whether the absence of impurity peaks indicates successful synthesis and how this should be described in a scientific paper.

Prompt 5

Explain how the identified phases agree with the proposed synthesis route and reaction mechanism. Discuss whether the observed crystal structure matches the expected material composition.

Prompt 6

Compare the experimental phase identification results with those reported in recent scientific literature. Highlight similarities, differences, and possible reasons for any discrepancies.

Prompt 7

The XRD analysis shows the coexistence of multiple crystalline phases. Explain how each phase may contribute to the material’s mechanical, catalytic, magnetic, optical, or electrochemical performance.

Prompt 8

Prepare a publication-ready Results and Discussion section describing the identified crystalline phases, their relative importance, and the implications for the intended application of the material.

Prompt 9

A reviewer asked whether the identified crystalline phases confirm successful synthesis of the target material. Write a professional reviewer response using the validated XRD phase identification results.

Prompt 10

Integrate the phase identification results with complementary characterization techniques such as SEM, TEM, FTIR, Raman spectroscopy, or XPS to produce a coherent scientific discussion explaining the relationship between crystal structure, morphology, surface chemistry, and material performance.

Search-Match Analysis AI Prompts (11–20)

Prompt 11

Based on the validated search-match results obtained from HighScore Plus, JADE, or another XRD software, explain why the identified reference patterns provide the best match for the experimental diffraction pattern.

Prompt 12

Interpret the search-match analysis results and explain how the matched reference phases confirm the successful synthesis of the target material.

Prompt 13

Several candidate phases were identified during the search-match process. Compare these phases and explain why the final selected phases are the most probable based on the diffraction data.

Prompt 14

Prepare a publication-ready discussion describing the search-match results and explain how they support the crystallographic identification of the sample.

Prompt 15

Compare the search-match results of two different samples and explain how differences in phase composition reflect changes in synthesis conditions or processing parameters.

Prompt 16

The search-match analysis identified a small amount of a secondary phase. Discuss its possible origin, formation mechanism, and potential influence on the material’s properties.

Prompt 17

Explain how the search-match results correlate with the expected crystal structure reported in the literature. Discuss any differences and provide possible scientific explanations.

Prompt 18

A reviewer questioned the reliability of the phase identification obtained from the search-match analysis. Write a professional reviewer response explaining how the matched reference patterns support the phase assignment.

Prompt 19

Integrate the search-match results with SEM, TEM, Raman, FTIR, or XPS data to explain how the identified crystalline phases are consistent with the material’s morphology, composition, and surface chemistry.

Prompt 20

Using the validated search-match results, write a clear, concise, and publication-ready Results and Discussion section suitable for submission to an SCI journal, emphasizing phase identification, phase purity, and the significance of the matched crystalline structures.

Peak Indexing AI Prompts (21–30)

Prompt 21

Using the validated peak indexing results, explain the crystallographic significance of the assigned (hkl) planes and discuss how they confirm the crystal structure of the material.

Prompt 22

Prepare a publication-ready discussion describing the indexed diffraction peaks and explain how they agree with the identified crystalline phase and reference diffraction pattern.

Prompt 23

Explain why the strongest diffraction peaks correspond to specific crystallographic planes and discuss what this indicates about the preferred crystal orientation and growth behavior.

Prompt 24

Compare the indexed diffraction peaks of two samples and explain how differences in peak positions or indexed planes reflect structural evolution after doping, heat treatment, or compositional modification.

Prompt 25

Discuss the relationship between the indexed diffraction peaks and the crystal symmetry of the identified material. Explain how the indexed planes support the proposed crystal structure.

Prompt 26

Explain the scientific importance of indexing the diffraction peaks before performing crystallographic calculations such as lattice parameter refinement or Rietveld analysis.

Prompt 27

A reviewer requested additional justification for the indexed diffraction peaks. Write a professional reviewer response explaining how the indexing supports the phase identification and crystal structure assignment.

Prompt 28

Using the indexed diffraction peaks, explain whether the sample exhibits preferred orientation (texture) and discuss how this may have resulted from the synthesis or deposition process.

Prompt 29

Integrate the indexed XRD peaks with SEM, TEM, or electron diffraction results to explain how the observed crystal planes correlate with the material’s morphology and microstructure.

Prompt 30

Write a publication-ready Results and Discussion section describing the indexed diffraction peaks, their crystallographic meaning, and their significance for understanding the structural properties of the synthesized material.

Crystallite Size AI Prompts (31–40)

Prompt 31

The average crystallite size calculated using the Scherrer equation is [X] nm. Write a publication-ready discussion explaining the significance of this value and its influence on the material’s properties.

Prompt 32

Compare the crystallite sizes of multiple samples synthesized under different conditions. Explain how changes in synthesis parameters influenced crystal growth and crystallinity.

Prompt 33

The crystallite size increased after annealing. Explain the mechanisms responsible for grain growth, improved crystallinity, and the reduction of crystal defects.

Prompt 34

The crystallite size decreased after doping with [dopant]. Discuss the possible reasons for this reduction and explain how dopant incorporation inhibits crystal growth.

Prompt 35

Explain the relationship between crystallite size and diffraction peak broadening. Discuss why smaller crystallites generally produce broader diffraction peaks.

Prompt 36

Discuss how changes in crystallite size are expected to affect the optical, magnetic, catalytic, mechanical, or electrochemical properties of the material.

Prompt 37

Compare the crystallite size obtained from XRD with particle size measured by SEM or TEM. Explain why these values may differ and discuss the distinction between crystallite size and particle size.

Prompt 38

A reviewer questioned the crystallite-size calculation obtained using the Scherrer equation. Write a professional reviewer response explaining the assumptions, limitations, and validity of the calculation.

Prompt 39

Using the reported crystallite-size values, prepare a publication-ready Results and Discussion section that relates crystal growth to the synthesis conditions and overall material performance.

Prompt 40

Integrate the crystallite-size results with complementary characterization techniques such as SEM, TEM, BET, Raman spectroscopy, or XPS to explain the relationship between crystal size, morphology, surface properties, and functional performance.

Lattice Parameter AI Prompts (41–50)

Prompt 41

The refined lattice parameters of the material are a = [ ], b = [ ], c = [ ] Å. Write a publication-ready discussion explaining their crystallographic significance and compare them with reported literature values.

Prompt 42

Compare the lattice parameters of the undoped and doped samples. Explain how dopant incorporation affects the crystal lattice and discuss the possible reasons for lattice expansion or contraction.

Prompt 43

The lattice parameters changed after heat treatment. Discuss the structural mechanisms responsible for these changes, including crystal relaxation, defect reduction, and atomic rearrangement.

Prompt 44

Interpret the refined lattice parameters together with the observed XRD peak shifts. Explain how both results support the proposed structural evolution of the material.

Prompt 45

Compare the experimentally determined lattice parameters with the theoretical crystal structure. Discuss possible reasons for any differences, including strain, defects, impurities, or non-stoichiometry.

Prompt 46

Explain how changes in lattice parameters may influence the optical, magnetic, catalytic, mechanical, or electrochemical properties of the material.

Prompt 47

Discuss the relationship between lattice parameter variation and substitutional or interstitial doping. Explain how differences in ionic radius can affect the crystal structure.

Prompt 48

A reviewer questioned the reported lattice parameter refinement. Write a professional reviewer response explaining the refinement procedure and the reliability of the calculated lattice constants.

Prompt 49

Integrate the lattice parameter results with complementary characterization techniques such as XPS, Raman spectroscopy, SEM, TEM, or FTIR to explain the structural evolution of the material.

Prompt 50

Prepare a publication-ready Results and Discussion section describing the refined lattice parameters, their comparison with standard crystallographic data, and their implications for the material’s crystal structure and performance.

Strain Analysis AI Prompts (51–60)

Prompt 51

The microstrain calculated from Williamson–Hall analysis is [X] × 10⁻³. Write a publication-ready discussion explaining the origin of the lattice strain and its effect on the crystal structure.

Prompt 52

Compare the lattice strain of the undoped and doped samples. Explain how dopant incorporation influences lattice distortion and discuss the possible mechanisms responsible for the observed strain.

Prompt 53

The lattice strain decreased after annealing. Discuss how thermal treatment reduces crystal defects, relieves internal stress, and improves crystallinity.

Prompt 54

Interpret the Williamson–Hall analysis results by discussing the relative contributions of crystallite size and lattice strain to diffraction peak broadening.

Prompt 55

Explain how lattice strain affects the optical, electrical, magnetic, catalytic, or electrochemical properties of the material. Correlate the strain results with the intended application.

Prompt 56

Compare the strain values obtained from Williamson–Hall analysis for multiple samples synthesized under different experimental conditions. Explain how the synthesis parameters influence internal lattice distortion.

Prompt 57

A reviewer questioned whether the observed peak broadening originates from crystallite size or lattice strain. Write a professional reviewer response explaining how Williamson–Hall analysis distinguishes between these two effects.

Prompt 58

Integrate the lattice strain results with complementary characterization techniques such as Raman spectroscopy, TEM, SEM, or XPS to explain the structural evolution and defect formation within the material.

Prompt 59

Prepare a publication-ready Results and Discussion section describing the lattice strain, its origin, and its relationship with crystallite size, crystal defects, and overall material performance.

Prompt 60

Compare the lattice strain values with those reported in recent scientific literature for similar materials. Discuss whether the measured strain is relatively high or low and explain the possible reasons for any differences.

Williamson–Hall Analysis AI Prompts (61–70)

Prompt 61

Interpret the Williamson–Hall plot of my sample. Explain the significance of the calculated crystallite size and lattice strain, and discuss how both parameters contribute to XRD peak broadening.

Prompt 62

Compare the Williamson–Hall analysis results of multiple samples prepared under different synthesis conditions. Explain how the crystallite size and lattice strain evolved with changing processing parameters.

Prompt 63

The Williamson–Hall analysis shows that lattice strain decreases while crystallite size increases after annealing. Prepare a publication-ready discussion explaining the underlying structural mechanisms.

Prompt 64

Discuss the advantages of the Williamson–Hall method over the Scherrer equation for evaluating crystallite size and explain why considering lattice strain provides a more comprehensive microstructural analysis.

Prompt 65

Explain how the Williamson–Hall results support the observed changes in XRD peak broadening. Discuss the relative contributions of crystallite size reduction and lattice strain to the diffraction pattern.

Prompt 66

Correlate the Williamson–Hall analysis with complementary characterization techniques such as TEM, SEM, Raman spectroscopy, or XPS. Explain how these techniques collectively support the observed structural evolution.

Prompt 67

Compare the Williamson–Hall analysis results with values reported in recent literature for similar materials. Discuss possible reasons for any differences in crystallite size or lattice strain.

Prompt 68

A reviewer questioned the use of the Williamson–Hall method instead of the Scherrer equation. Write a professional reviewer response explaining the advantages, assumptions, and limitations of the Williamson–Hall approach.

Prompt 69

Prepare a publication-ready Results and Discussion section describing the Williamson–Hall analysis, emphasizing the relationship between crystallite size, lattice strain, crystal defects, and material performance.

Prompt 70

Discuss how the crystallite size and lattice strain obtained from Williamson–Hall analysis are expected to influence the mechanical, catalytic, optical, magnetic, or electrochemical properties of the synthesized material.

Rietveld Refinement AI Prompts (71–80)

Prompt 71

Interpret the Rietveld refinement results of my XRD data. Discuss the refined crystal structure, lattice parameters, phase composition, and overall quality of the refinement in a publication-ready style.

Prompt 72

The Rietveld refinement produced the following agreement factors: Rwp = [ ], Rp = [ ], χ² = [ ]. Explain the significance of these values and evaluate the quality and reliability of the refinement.

Prompt 73

Compare the Rietveld refinement results of the undoped and doped samples. Discuss how doping affects the crystal structure, lattice parameters, atomic arrangement, and phase composition.

Prompt 74

Prepare a publication-ready Results and Discussion section explaining the structural evolution revealed by Rietveld refinement after annealing, calcination, or heat treatment.

Prompt 75

Discuss how the refined atomic positions, lattice parameters, and crystallographic information support the proposed crystal structure and synthesis mechanism.

Prompt 76

Interpret the quantitative phase analysis obtained from Rietveld refinement. Explain how the calculated phase fractions influence the material’s structural and functional properties.

Prompt 77

Integrate the Rietveld refinement results with complementary characterization techniques such as SEM, TEM, Raman spectroscopy, FTIR, or XPS to provide a comprehensive structural interpretation.

Prompt 78

Compare my Rietveld refinement results with published literature for similar materials. Explain possible reasons for differences in lattice parameters, phase fractions, refinement quality, or structural models.

Prompt 79

A reviewer questioned the reliability of the Rietveld refinement. Write a professional reviewer response explaining the refinement procedure, refinement statistics, structural model, and the validity of the obtained crystallographic parameters.

Prompt 80

Summarize the Rietveld refinement results in a clear, concise, and publication-ready discussion suitable for submission to a high-impact SCI journal. Emphasize the crystal structure, refinement quality, quantitative phase analysis, and their implications for the material’s performance.

Thin Films XRD AI Prompts (81–90)

Prompt 81

Interpret the XRD pattern of my thin film deposited by [RF magnetron sputtering / DC sputtering / PLD / CVD / ALD / evaporation]. Discuss the crystal structure, preferred orientation, crystallinity, and phase purity in a publication-ready style.

Prompt 82

Compare the XRD patterns of thin films deposited under different sputtering powers, deposition temperatures, or deposition times. Explain how these processing parameters influence crystal growth and structural evolution.

Prompt 83

The XRD results show stronger diffraction peaks after annealing. Explain how post-deposition heat treatment improves crystallinity, grain growth, and crystal quality.

Prompt 84

Discuss the preferred orientation (texture) observed in my thin-film XRD pattern. Explain why certain crystallographic planes exhibit enhanced diffraction intensity and how deposition conditions influence texture formation.

Prompt 85

Interpret the XRD peak shifts observed after thin-film deposition. Discuss whether they are related to residual stress, lattice distortion, compositional changes, or substrate effects.

Prompt 86

Compare the XRD results of thin films before and after annealing. Explain the structural evolution, grain growth, strain relaxation, and possible phase transformations.

Prompt 87

Integrate the XRD results with SEM, AFM, TEM, XPS, Raman spectroscopy, or optical measurements to explain the relationship between crystal structure, surface morphology, and functional properties of the thin film.

Prompt 88

Prepare a publication-ready Results and Discussion section explaining the structural properties of the thin film, including crystallinity, preferred orientation, lattice changes, and their influence on optical, electrical, magnetic, or mechanical performance.

Prompt 89

A reviewer questioned the structural quality of the deposited thin film based on the XRD data. Write a professional reviewer response explaining how the diffraction pattern confirms successful film growth and crystallographic quality.

Prompt 90

Compare the structural properties of my thin film with similar films reported in recent literature. Discuss similarities, differences, and possible reasons related to deposition technique, processing parameters, or material composition.

Nanomaterials XRD AI Prompts (91–100)

Prompt 91

Interpret the XRD pattern of my nanomaterial and discuss its crystal structure, phase purity, crystallinity, and average crystallite size in a publication-ready style.

Prompt 92

Compare the XRD patterns of undoped and doped nanoparticles. Explain how doping affects crystallinity, lattice distortion, crystallite size, and phase composition.

Prompt 93

The XRD peaks became broader after reducing the particle size. Explain the relationship between peak broadening, crystallite size, lattice strain, and nanoscale effects.

Prompt 94

Discuss how hydrothermal reaction time, calcination temperature, or synthesis conditions influence the crystal structure and crystallinity of my nanomaterials based on the XRD results.

Prompt 95

Correlate the XRD results with TEM and SEM observations. Explain the relationship between crystallite size, particle size, morphology, and agglomeration.

Prompt 96

Interpret the XRD results together with Raman spectroscopy, FTIR, or XPS to explain the structural evolution and surface chemistry of the synthesized nanomaterial.

Prompt 97

Prepare a publication-ready Results and Discussion section explaining how the observed XRD characteristics contribute to the optical, photocatalytic, magnetic, antibacterial, or electrochemical performance of the nanomaterial.

Prompt 98

Compare the crystallographic properties of my nanomaterial with those reported in recent literature. Discuss similarities, differences, and possible reasons related to synthesis conditions or material composition.

Prompt 99

A reviewer questioned the crystallinity and phase purity of my nanoparticles. Write a professional reviewer response explaining how the XRD data support the successful synthesis and structural quality of the material.

Prompt 100

Integrate the XRD analysis with complementary characterization techniques including SEM, TEM, BET, UV–Vis spectroscopy, XPS, and electrochemical measurements to produce a comprehensive publication-ready discussion of the nanomaterial’s structure–property relationship.

Polymer and Polymer Composite XRD AI Prompts (101–110)

Prompt 101

Interpret the XRD pattern of my polymer sample. Discuss its crystalline and amorphous regions, degree of crystallinity, and the implications for the material’s mechanical and thermal properties.

Prompt 102

Compare the XRD patterns of the pure polymer and the polymer composite. Explain how the addition of fillers or nanoparticles influences crystallinity, crystal structure, and overall material performance.

Prompt 103

The XRD peaks became sharper after thermal treatment. Explain how annealing affects crystal growth, molecular chain ordering, and crystallinity in the polymer.

Prompt 104

Interpret the XRD results of a polymer nanocomposite containing graphene, CNTs, MXenes, MOFs, silica, or metal oxide nanoparticles. Discuss the structural interaction between the polymer matrix and the reinforcement.

Prompt 105

Explain how changes in polymer crystallinity observed by XRD influence tensile strength, flexibility, toughness, thermal stability, barrier properties, or electrical conductivity.

Prompt 106

Compare the XRD patterns of biodegradable polymers before and after chemical modification or crosslinking. Discuss the structural evolution and its influence on material properties.

Prompt 107

Integrate the XRD results with FTIR, DSC, TGA, SEM, AFM, or Raman spectroscopy to explain the structural and thermal behavior of the polymer or polymer composite.

Prompt 108

Prepare a publication-ready Results and Discussion section describing the crystallinity, crystal structure, amorphous content, and structural evolution of the polymer based on XRD analysis.

Prompt 109

A reviewer questioned the reported increase in polymer crystallinity. Write a professional reviewer response explaining how the XRD results support the calculated crystallinity and structural changes.

Prompt 110

Compare the XRD characteristics of my polymer material with recently published studies. Discuss similarities, differences, and possible reasons related to polymer type, processing conditions, filler content, or fabrication method.

Battery Materials XRD AI Prompts (111–120)

Prompt 111

Interpret the XRD pattern of my battery electrode material. Discuss the crystal structure, phase purity, crystallinity, and their significance for electrochemical performance.

Prompt 112

Compare the XRD patterns of the electrode material before and after electrochemical cycling. Explain the structural evolution and discuss how these changes influence battery performance and cycling stability.

Prompt 113

The XRD peaks shifted after repeated charge–discharge cycles. Explain the possible mechanisms responsible for these peak shifts, including lattice expansion, contraction, phase transformation, or ion insertion/extraction.

Prompt 114

Compare the XRD results of pristine and doped cathode materials. Discuss how doping influences crystal structure, lattice parameters, structural stability, and electrochemical properties.

Prompt 115

Interpret the XRD analysis of anode materials before and after cycling. Explain possible structural degradation, amorphization, or volume expansion during electrochemical operation.

Prompt 116

Prepare a publication-ready Results and Discussion section describing the structural stability of the battery material based on XRD analysis and relate it to capacity retention and cycling performance.

Prompt 117

Integrate the XRD results with SEM, TEM, XPS, Raman spectroscopy, EIS, cyclic voltammetry, or charge–discharge measurements to explain the relationship between crystal structure and electrochemical behavior.

Prompt 118

Compare the XRD results of my battery material with recently published studies. Discuss similarities, differences, and possible reasons related to synthesis conditions, composition, or cycling protocol.

Prompt 119

A reviewer questioned whether the XRD data adequately demonstrate structural stability after cycling. Write a professional reviewer response explaining how the diffraction results support the material’s electrochemical durability.

Prompt 120

Explain how the observed crystal structure, phase composition, crystallinity, and lattice evolution influence lithium-ion, sodium-ion, potassium-ion, zinc-ion, or aluminum-ion storage performance in my battery material.

Catalysts and Photocatalysts XRD AI Prompts (121–130)

Prompt 121

Interpret the XRD pattern of my catalyst or photocatalyst. Discuss the identified crystalline phases, crystallinity, phase purity, and their significance for catalytic performance.

Prompt 122

Compare the XRD patterns of the catalyst before and after the catalytic reaction. Explain any structural changes, phase transformations, or loss of crystallinity and discuss their impact on catalyst stability.

Prompt 123

The XRD results indicate that doping modified the catalyst’s crystal structure. Explain how the dopant influences crystallinity, lattice distortion, defect formation, and catalytic activity.

Prompt 124

Compare the XRD patterns of catalysts synthesized under different calcination temperatures or synthesis conditions. Discuss how these parameters affect phase formation, crystallite size, and catalytic efficiency.

Prompt 125

Interpret the XRD results of a supported catalyst (e.g., metal nanoparticles on oxide, carbon, MOF, or zeolite supports). Explain how the support influences the catalyst’s crystal structure and stability.

Prompt 126

Prepare a publication-ready Results and Discussion section describing how the observed XRD characteristics correlate with photocatalytic, electrocatalytic, or heterogeneous catalytic performance.

Prompt 127

Integrate the XRD results with SEM, TEM, BET, XPS, Raman spectroscopy, UV–Vis spectroscopy, or catalytic performance data to explain the structure–activity relationship of the catalyst.

Prompt 128

Compare my catalyst’s XRD results with recently published literature. Discuss similarities, differences, and possible reasons related to synthesis method, composition, particle size, or support material.

Prompt 129

A reviewer questioned the phase purity and structural stability of the catalyst based on the XRD data. Write a professional reviewer response explaining how the diffraction results support the proposed crystal structure and catalytic behavior.

Prompt 130

Explain how crystallinity, phase composition, crystallite size, and lattice modifications observed in the XRD analysis contribute to improved catalytic activity, selectivity, reaction kinetics, and long-term stability.

MOF (Metal–Organic Framework) XRD AI Prompts (131–140)

Prompt 131

Interpret the XRD pattern of my metal–organic framework (MOF). Discuss the crystal structure, phase purity, crystallinity, and whether the synthesized material matches the expected MOF topology.

Prompt 132

Compare the XRD patterns of the synthesized MOF with the simulated or reference diffraction pattern. Explain the similarities, differences, and possible reasons for any deviations.

Prompt 133

The XRD peaks changed after guest molecule adsorption or functionalization. Explain how these structural changes reflect framework stability, pore occupancy, or host–guest interactions.

Prompt 134

Compare the XRD patterns of the pristine MOF and the modified MOF composite. Discuss how the incorporation of nanoparticles, graphene, MXenes, polymers, or metal oxides influences crystallinity and framework integrity.

Prompt 135

Interpret the XRD results of my MOF before and after thermal treatment or chemical activation. Discuss the framework stability, crystallinity changes, and possible structural degradation.

Prompt 136

Prepare a publication-ready Results and Discussion section describing the structural characteristics of my MOF based on XRD analysis and explain how they influence adsorption, catalysis, sensing, or energy-storage performance.

Prompt 137

Integrate the XRD results with BET surface area, SEM, TEM, FTIR, Raman spectroscopy, or XPS data to explain the structure–property relationship of the synthesized MOF.

Prompt 138

Compare the XRD characteristics of my MOF with recently published studies. Discuss similarities, differences, and possible reasons related to synthesis conditions, metal centers, organic linkers, or post-synthetic modification.

Prompt 139

A reviewer questioned whether the synthesized material retained the original MOF crystal structure after modification. Write a professional reviewer response explaining how the XRD results demonstrate structural preservation or controlled structural evolution.

Prompt 140

Explain how the observed crystallinity, phase purity, framework stability, and structural changes identified by XRD contribute to the adsorption capacity, catalytic efficiency, gas storage performance, or electrochemical properties of the MOF.

MXene XRD AI Prompts (141–150)

Prompt 141

Interpret the XRD pattern of my MXene material. Discuss the successful transformation from the MAX phase to the MXene structure, phase purity, and crystallinity.

Prompt 142

Compare the XRD patterns of the MAX phase and the synthesized MXene. Explain the disappearance of characteristic MAX peaks, the shift of the (002) reflection, and the structural changes that confirm successful etching.

Prompt 143

The (002) peak shifted toward lower 2θ values after etching. Explain the crystallographic significance of this peak shift and discuss how increased interlayer spacing confirms MXene formation.

Prompt 144

Interpret the XRD results of functionalized MXenes. Explain how surface terminations (-O, -OH, -F), intercalation, or chemical modification influence the crystal structure and interlayer spacing.

Prompt 145

Compare the XRD patterns of pristine MXene and MXene-based composites containing polymers, MOFs, graphene, metal oxides, or nanoparticles. Discuss the structural interactions between the MXene sheets and the secondary material.

Prompt 146

Prepare a publication-ready Results and Discussion section describing the structural evolution during MXene synthesis, emphasizing etching, delamination, interlayer expansion, and crystallinity.

Prompt 147

Integrate the XRD results with SEM, TEM, AFM, XPS, Raman spectroscopy, FTIR, or BET analysis to explain the relationship between the crystal structure, morphology, surface chemistry, and functional properties of the MXene.

Prompt 148

Compare the XRD characteristics of my MXene with recently published studies. Discuss similarities, differences, and possible reasons related to etching conditions, intercalation agents, synthesis method, or precursor composition.

Prompt 149

A reviewer questioned whether the XRD results sufficiently demonstrate successful MXene synthesis. Write a professional reviewer response explaining how the disappearance of MAX-phase peaks, the (002) peak shift, and other structural features confirm the formation of MXene.

Prompt 150

Explain how the structural characteristics observed in the XRD analysis—including interlayer spacing, crystallinity, phase purity, and surface modification—affect the electrical conductivity, energy-storage performance, electromagnetic shielding, catalytic activity, or corrosion resistance of the MXene.

Comparative XRD Analysis AI Prompts (151–160)

Prompt 151

Compare the XRD patterns of Sample A and Sample B. Discuss the differences in phase composition, crystallinity, peak positions, peak intensities, and crystallite size, and explain how these structural variations influence the material’s properties.

Prompt 152

Prepare a publication-ready comparative discussion of multiple XRD patterns obtained under different synthesis conditions. Explain how variations in temperature, reaction time, precursor concentration, or processing parameters affect the crystal structure.

Prompt 153

Compare the XRD patterns of pristine and modified materials. Explain the structural evolution caused by doping, surface functionalization, composite formation, or chemical treatment, and discuss its significance.

Prompt 154

Interpret the structural differences between the XRD patterns before and after annealing. Discuss changes in crystallinity, grain growth, lattice strain, phase transformation, and defect reduction.

Prompt 155

Compare my XRD results with those reported in recent scientific literature. Discuss similarities, differences, and possible reasons for discrepancies in crystal structure, crystallite size, lattice parameters, or phase composition.

Prompt 156

Integrate comparative XRD analysis with complementary characterization techniques such as SEM, TEM, FTIR, Raman spectroscopy, XPS, BET, or thermal analysis to explain the observed structure–property relationships.

Prompt 157

Compare the XRD patterns of samples synthesized using different preparation methods (e.g., hydrothermal, sol–gel, co-precipitation, solid-state reaction, or sputtering). Explain how the synthesis route influences crystallinity, phase formation, and microstructure.

Prompt 158

Prepare a comparative Results and Discussion section suitable for a high-impact SCI journal. Highlight the key structural differences among multiple samples and explain how these differences correlate with their functional performance.

Prompt 159

A reviewer requested a clearer comparison between the XRD patterns of multiple samples. Write a professional reviewer response emphasizing the major structural differences, supporting crystallographic evidence, and their scientific significance.

Prompt 160

Summarize the structural evolution observed across all XRD patterns in this study. Explain the relationships among crystal structure, phase composition, crystallinity, lattice changes, and material performance, and conclude with the key scientific findings in a concise, publication-ready style.

Scientific Writing & Publication XRD AI Prompts (161–170)

Prompt 161

Write a publication-ready Results and Discussion section based on my XRD analysis. Explain the crystal structure, phase purity, crystallinity, and their relationship to the material’s functional properties in the style of a high-impact SCI journal.

Prompt 162

Rewrite my XRD discussion to improve its scientific quality, logical flow, grammar, and readability while preserving the original scientific meaning. Use the writing style commonly found in journals such as Applied Surface Science, Ceramics International, or Journal of Alloys and Compounds.

Prompt 163

Write a concise but scientifically rigorous XRD discussion suitable for the Results section of a manuscript. Avoid repetition and emphasize the most significant crystallographic findings.

Prompt 164

Prepare a professional figure caption for my XRD pattern. Clearly describe the identified phases, diffraction peaks, experimental conditions, and the key structural observations.

Prompt 165

Write a comparison paragraph discussing the differences between my XRD results and previously published studies. Highlight possible reasons for similarities or discrepancies in crystal structure, crystallinity, or phase composition.

Prompt 166

A reviewer commented that the XRD discussion is too descriptive. Rewrite it to provide deeper scientific interpretation, including structure–property relationships and comparison with the literature.

Prompt 167

Write a professional response to a reviewer who requested additional evidence supporting the phase identification and structural interpretation obtained from XRD analysis.

Prompt 168

Summarize my XRD results in one concise paragraph suitable for the Abstract of a scientific paper, emphasizing the most important structural findings.

Prompt 169

Integrate the XRD discussion with SEM, TEM, FTIR, Raman spectroscopy, XPS, BET, or electrochemical results to produce a coherent, publication-ready characterization section.

Prompt 170

Act as an experienced journal editor and critically evaluate my XRD Results and Discussion section. Identify scientific weaknesses, unclear statements, unsupported conclusions, and suggest specific improvements to make it suitable for publication in a Q1 journal.

Universal XRD AI Prompts (171–180)

These prompts are designed to work with almost any XRD dataset, regardless of the material type or application. Simply replace the placeholder information with your own experimental results.

Prompt 171

Act as an experienced materials scientist and interpret my XRD results. Explain the crystal structure, phase composition, crystallinity, peak positions, and the scientific significance of the observed diffraction pattern.

Prompt 172

Write a publication-ready Results and Discussion section based on my XRD analysis. Use the writing style of a high-impact SCI journal and relate the structural characteristics to the intended application of the material.

Prompt 173

Compare my XRD results with recently published literature on similar materials. Discuss the similarities, differences, and possible reasons for discrepancies in crystal structure, crystallinity, lattice parameters, or phase composition.

Prompt 174

Integrate my XRD results with SEM, TEM, FTIR, Raman spectroscopy, XPS, BET, TGA, UV–Vis spectroscopy, or electrochemical measurements to provide a comprehensive structure–property relationship.

Prompt 175

Act as a journal reviewer and critically evaluate my XRD discussion. Identify scientific weaknesses, unsupported claims, missing interpretations, and suggest specific improvements before manuscript submission.

Prompt 176

A reviewer questioned my XRD interpretation. Write a professional, scientifically rigorous reviewer response that addresses the comment while maintaining a polite and convincing tone.

Prompt 177

Rewrite my XRD discussion to improve scientific accuracy, logical organization, readability, grammar, and publication quality while preserving the original meaning.

Prompt 178

Based on my XRD results, explain how the observed crystal structure influences the optical, electrical, magnetic, catalytic, mechanical, thermal, corrosion-resistant, or electrochemical properties of the material.

Prompt 179

Prepare a complete characterization report based on my XRD analysis. Include structural interpretation, comparison with the literature, scientific discussion, practical implications, and recommendations for additional characterization if needed.

Prompt 180

Act as an expert crystallographer and materials scientist. Analyze my validated XRD results from a publication perspective, identify the strongest scientific findings, highlight potential weaknesses, recommend additional analyses if necessary, and produce a publication-ready discussion suitable for submission to a Q1 journal.

10. 20 Expert Prompt Templates for XRD Analysis

While the previous sections provided 180 specialized AI prompts for different XRD applications, experienced researchers often need more comprehensive prompts that combine multiple characterization techniques, experimental conditions, and publication objectives into a single request.

The following expert prompt templates are designed for advanced users who want AI to generate detailed, publication-ready analyses with minimal editing. Simply replace the placeholder information with your own experimental data.

Template 1 – Complete XRD Interpretation

I synthesized [material] using [synthesis method] under [experimental conditions]. XRD analysis identified [phases] with an average crystallite size of [X] nm. Please write a publication-ready Results and Discussion section explaining the crystal structure, phase purity, crystallinity, and how these structural characteristics influence the material’s performance.

Template 2 – Comparative XRD Analysis

Compare the XRD results of Sample A and Sample B. Discuss differences in phase composition, crystallinity, lattice parameters, peak positions, crystallite size, and explain how these structural changes affect the final properties.

Template 3 – Multi-Technique Characterization

Integrate my XRD, SEM, TEM, FTIR, Raman spectroscopy, XPS, and BET results into a coherent publication-ready discussion that explains the complete structure–property relationship of the synthesized material.

Template 4 – Doping Effects

Explain how [dopant] affects the crystal structure, crystallinity, lattice distortion, crystallite size, phase composition, and the resulting functional properties based on the XRD analysis.

Template 5 – Thin Film Analysis

Interpret the XRD results of thin films deposited under different sputtering powers or deposition temperatures. Discuss preferred orientation, crystallinity, residual stress, lattice changes, and relate these findings to the film’s functional properties.

Template 6 – Nanomaterials

Prepare a publication-ready discussion explaining how particle size reduction, crystallite size, lattice strain, and phase purity observed in XRD influence the optical, catalytic, magnetic, or electrochemical properties of the nanomaterial.

Template 7 – Rietveld Refinement

Interpret the Rietveld refinement results, including lattice parameters, quantitative phase composition, refinement statistics, and explain the structural significance of the refined crystallographic model.

Template 8 – Reviewer Response

A reviewer questioned my XRD interpretation. Write a professional response that justifies the phase identification, structural analysis, crystallite size calculation, and conclusions while maintaining a polite scientific tone.

Template 9 – Literature Comparison

Compare my XRD results with recently published papers on similar materials. Highlight similarities, differences, and provide scientific explanations for any discrepancies.

Template 10 – Journal-Style Discussion

Rewrite my XRD discussion in the writing style of a high-impact SCI journal such as Applied Surface Science, Journal of Alloys and Compounds, Chemical Engineering Journal, or ACS Applied Materials & Interfaces.

Template 11 – Battery Materials

Interpret the XRD patterns of battery electrodes before and after cycling. Explain structural stability, phase evolution, lattice changes, and their influence on electrochemical performance.

Template 12 – Catalysts

Explain how the crystal structure observed in XRD influences catalytic activity, selectivity, reaction kinetics, and long-term stability.

Template 13 – MOFs

Interpret the XRD pattern of my MOF and explain framework formation, crystallinity, structural stability, and their relationship to adsorption or catalytic performance.

Template 14 – MXenes

Analyze the XRD results of my MXene material and explain the structural evolution from the MAX phase, interlayer expansion, surface functionalization, and implications for energy storage or EMI shielding.

Template 15 – Polymer Composites

Discuss how nanoparticle incorporation changes the crystallinity and crystal structure of my polymer composite and relate these changes to mechanical and thermal performance.

Template 16 – Corrosion Studies

Interpret the XRD results of corrosion products formed after exposure to a corrosive environment. Explain the corrosion mechanism and discuss the protective or detrimental role of each identified phase.

Template 17 – Scientific Abstract

Summarize my XRD results in one concise paragraph suitable for the Abstract of a scientific paper while emphasizing the key structural findings.

Template 18 – Figure Caption

Write a professional figure caption describing my XRD patterns, including phase identification, experimental conditions, and the major structural observations.

Template 19 – Complete Characterization Report

Based on my XRD results and complementary characterization techniques, prepare a comprehensive characterization report suitable for publication or technical documentation.

Template 20 – Expert Consultation

Act as a senior crystallographer and journal editor. Critically evaluate my XRD analysis, identify weaknesses, suggest additional analyses if needed, compare the results with the literature, and provide recommendations to improve the manuscript before submission to a Q1 journal.

Pro Tip

For the highest-quality AI responses, always include:

• Material name and composition
• Synthesis or processing method
• Experimental conditions
• Validated XRD results (phase identification, crystallite size, lattice parameters, etc.)
• Complementary characterization (SEM, TEM, FTIR, Raman, XPS, BET, etc.)
• Your desired output (discussion, reviewer response, comparison, figure caption, abstract, etc.)

At AnalyzeTest AI, these expert templates are optimized for materials characterization research. When combined with professional crystallographic analysis, they enable researchers to generate accurate, publication-ready XRD interpretations in a fraction of the time required for manual writing.

11. Frequently Asked Questions (FAQs)

Below are some of the most common questions researchers ask about using artificial intelligence for XRD analysis and scientific writing.

1. Can AI identify crystalline phases directly from a raw XRD pattern?

Not reliably. Accurate phase identification requires comparison with crystallographic reference databases (such as the ICDD PDF database), search-match algorithms, and expert interpretation. AI is far more reliable for interpreting validated XRD results than for performing phase identification from raw diffraction patterns.

2. Can AI replace HighScore Plus, JADE, GSAS-II, TOPAS, or FullProf?

No. These specialized crystallographic software packages perform phase identification, Rietveld refinement, peak indexing, lattice parameter refinement, and quantitative phase analysis. AI complements these tools by helping interpret the results and prepare publication-quality scientific text.

3. Can AI perform Rietveld refinement?

No. Rietveld refinement requires crystallographic models, iterative numerical optimization, and specialized software. AI can explain and interpret refinement results but cannot replace the refinement process itself.

4. Is AI useful for writing XRD discussions?

Yes. This is one of AI’s greatest strengths. AI can rapidly generate publication-ready Results and Discussion sections, compare results with the literature, prepare reviewer responses, improve scientific writing, and summarize structural findings.

5. What information should I provide to obtain the best AI response?

Include as much scientific context as possible, such as:

• Material composition
• Synthesis method
• Experimental conditions
• Identified phases
• Crystallite size
• Lattice parameters
• Rietveld refinement results (if available)
• Complementary characterization (SEM, TEM, FTIR, Raman, XPS, BET, etc.)

The more information you provide, the more accurate and useful the AI-generated interpretation will be.

6. Can AI compare multiple XRD patterns?

Yes. AI is highly effective at comparing diffraction patterns and discussing differences in crystallinity, phase composition, crystallite size, lattice parameters, peak shifts, and structural evolution across multiple samples.

7. Can AI explain why diffraction peaks shift?

Yes. AI can discuss possible reasons for peak shifts—including lattice distortion, doping, residual stress, thermal expansion, or compositional changes—provided that sufficient experimental information is supplied.

8. Can AI calculate crystallite size?

Not directly from a raw diffraction pattern. However, if you provide values such as FWHM, X-ray wavelength, and instrumental broadening correction, AI can explain or verify crystallite-size calculations and interpret their significance.

9. Can AI prepare responses to journal reviewers?

Absolutely. AI can draft professional, scientifically sound reviewer responses, improve manuscript language, strengthen structural interpretations, and address common reviewer concerns regarding XRD analysis.

10. What makes AnalyzeTest AI different from generic AI tools?

AnalyzeTest AI is specifically designed for researchers in materials science. Unlike general-purpose AI systems, it focuses on materials characterization techniques such as XRD, XPS, FTIR, Raman spectroscopy, SEM, TEM, BET, electrochemistry, and related analyses. It also combines expert-assisted crystallographic analysis with AI-powered scientific interpretation, enabling researchers to obtain technically accurate analyses and publication-ready manuscripts from a single platform.

11. Can AnalyzeTest AI perform expert XRD analysis?

Yes. For projects requiring advanced crystallographic analysis—such as phase identification, search-match analysis, Rietveld refinement, lattice parameter determination, Williamson–Hall analysis, or quantitative phase analysis—AnalyzeTest provides expert-supported services. Once the technical analysis is completed, AI helps transform the results into clear, publication-ready scientific discussions.

12. Who can benefit from AnalyzeTest AI?

AnalyzeTest AI is suitable for researchers working in:

• Materials Science
• Chemistry
• Nanotechnology
• Corrosion Engineering
• Thin Films and Coatings
• Battery Materials
• Catalysis
• MOFs and MXenes
• Polymers and Composites
• Biomaterials
• Ceramics
• Environmental Materials

Whether you are preparing a journal article, thesis, technical report, or research proposal, AnalyzeTest AI helps accelerate XRD interpretation while maintaining scientific accuracy.

12. Why AnalyzeTest AI Is Different

Artificial intelligence has transformed scientific research, but not all AI tools are designed for materials characterization. Most general-purpose AI models can generate fluent text, yet they often lack the domain-specific knowledge required for accurate interpretation of X-ray diffraction (XRD) results.

AnalyzeTest AI was developed specifically for researchers in materials science, chemistry, nanotechnology, corrosion engineering, energy storage, thin films, polymers, biomaterials, and related disciplines. Rather than acting as a generic chatbot, it serves as a specialized scientific assistant built around real characterization workflows.

AI That Understands Materials Characterization

Unlike generic AI platforms, AnalyzeTest AI is optimized for interpreting data from multiple characterization techniques, including:

• X-ray Diffraction (XRD)
• X-ray Photoelectron Spectroscopy (XPS)
• Fourier Transform Infrared Spectroscopy (FTIR)
• Raman Spectroscopy
• SEM and FESEM
• TEM and HRTEM
• BET Surface Area Analysis
• Thermal Analysis (TGA, DSC, DTA)
• UV–Vis Spectroscopy
• Electrochemical Characterization (EIS, CV, Charge–Discharge)
• VSM and other materials characterization methods

This multidisciplinary approach enables researchers to generate integrated, publication-quality discussions instead of interpreting each characterization technique separately.

AI Does Not Replace Crystallographic Software

One of the most important principles behind AnalyzeTest AI is scientific transparency.

We do not claim that AI can perform:

• Phase identification from raw XRD patterns
• Search-match analysis
• Peak indexing
• Rietveld refinement
• Quantitative phase analysis
• Lattice parameter refinement
• Williamson–Hall calculations

These tasks require professional crystallographic software and expert interpretation.

Instead, AnalyzeTest AI complements these analyses by transforming validated crystallographic results into clear, technically accurate, publication-ready scientific discussions.

Human Expertise + Artificial Intelligence

This is where AnalyzeTest AI differs most from conventional AI tools.

For advanced XRD projects, researchers can request expert-assisted analysis, where experienced materials scientists perform crystallographic analyses using professional software before AI is used to prepare:

• Results and Discussion sections
• Figure captions
• Reviewer responses
• Literature comparisons
• Scientific summaries
• Journal-ready manuscripts

This hybrid workflow combines the reliability of expert interpretation with the speed and efficiency of artificial intelligence.

Designed for Scientific Publishing

AnalyzeTest AI is optimized for the needs of researchers preparing:

• SCI and SCIE journal articles
• Master’s and PhD theses
• Conference papers
• Research reports
• Technical documentation
• Grant proposals

Instead of generating generic explanations, it focuses on producing scientifically rigorous content consistent with the writing style of leading international journals.

Extensive Prompt Library

AnalyzeTest AI includes one of the largest collections of expert-designed prompts for materials characterization.

Researchers can access specialized prompts covering:

• XRD
• XPS
• FTIR
• Raman
• SEM
• TEM
• Batteries
• Thin films
• Catalysts
• MOFs
• MXenes
• Corrosion
• Polymers
• Nanomaterials
• Scientific writing
• Reviewer responses

These prompts are continually refined based on current scientific literature and real research experience.

Built by Researchers, for Researchers

AnalyzeTest AI has been developed around the real challenges faced by scientists—not only interpreting characterization data but also writing manuscripts, responding to reviewers, comparing results with the literature, and preparing high-quality publications.

Every feature is designed with one goal:

Helping researchers spend less time writing and more time doing science.

Why Researchers Choose AnalyzeTest AI

Researchers choose AnalyzeTest AI because it offers:

• Specialized expertise in materials characterization
• Scientifically accurate AI-assisted interpretation
• Expert-supported XRD analysis when required
• Publication-ready scientific writing
• Professional reviewer response generation
• Integrated multi-technique analysis
• A comprehensive library of optimized AI prompts
• Faster manuscript preparation without compromising scientific quality

Whether you need help interpreting XRD results, improving your manuscript, or preparing a submission for a high-impact journal, AnalyzeTest AI combines domain expertise, advanced AI, and scientific writing support in a single platform designed specifically for the materials science community.

13. Conclusion

Artificial intelligence is rapidly changing the way researchers analyze experimental data and prepare scientific publications. When used correctly, AI can dramatically reduce the time required to interpret XRD results, compare findings with the literature, draft Results and Discussion sections, prepare reviewer responses, and improve the overall quality of scientific writing.

However, it is equally important to recognize the current limitations of AI. Tasks such as phase identification, search-match analysis, peak indexing, Rietveld refinement, quantitative phase analysis, lattice parameter refinement, and Williamson–Hall analysis still require specialized crystallographic software and the expertise of experienced researchers. AI should be viewed as a powerful scientific assistant—not as a replacement for crystallographic analysis.

Throughout this guide, we have presented 180 carefully engineered AI prompts covering virtually every major application of XRD in materials science, including nanomaterials, thin films, batteries, catalysts, MOFs, MXenes, polymers, corrosion studies, comparative analysis, and scientific writing. By adapting these prompts to your own experimental data, you can generate more accurate, detailed, and publication-ready interpretations while significantly accelerating your research workflow.

AnalyzeTest AI was created specifically for this purpose. Unlike generic AI tools, it combines domain-specific knowledge in materials characterization with advanced AI-powered scientific writing. More importantly, when advanced crystallographic analysis is required, AnalyzeTest also provides expert-assisted XRD services, ensuring that critical tasks such as phase identification and Rietveld refinement are performed using professional software before AI is used to interpret and communicate the results.

Whether you are preparing your first journal article or publishing regularly in high-impact SCI journals, combining expert crystallographic analysis with intelligently designed AI prompts offers the most reliable, efficient, and scientifically rigorous workflow.

If you want to save time, improve the quality of your manuscripts, and obtain professional support for XRD interpretation, AnalyzeTest AI provides a complete solution—from expert crystallographic analysis to publication-ready scientific writing—all in one platform.

Smarter XRD Analysis. Better Scientific Writing. Faster Research.

AI Prompts for XPS Analysis are transforming the way researchers interpret X-ray Photoelectron Spectroscopy (XPS) data. From peak assignment and oxidation state analysis to publication-ready scientific discussions, artificial intelligence can significantly accelerate XPS workflows while improving the quality of scientific writing. In this comprehensive guide, you’ll discover 160 expert AI prompts, practical examples, prompt templates, and best practices designed specifically for materials scientists, chemists, corrosion engineers, battery researchers, and nanotechnology professionals.

Today, XPS is routinely employed across a wide range of scientific disciplines, including materials science, nanotechnology, chemistry, chemical engineering, corrosion engineering, energy storage, biomaterials, polymer science, environmental engineering, semiconductor research, and catalysis. Whether researchers are studying graphene oxide, MXenes, metal oxides, thin films, corrosion inhibitors, catalysts, battery electrodes, or biomedical coatings, XPS often serves as the primary technique for understanding surface composition and chemical interactions.

Despite its enormous value, interpreting XPS spectra remains one of the most challenging tasks in materials characterization. Unlike many analytical techniques, XPS requires simultaneous interpretation of several interconnected factors, including elemental identification, oxidation-state determination, peak deconvolution, spin-orbit splitting, satellite peaks, charging effects, quantitative atomic concentrations, and chemical-state assignments. Even experienced researchers frequently consult dozens of journal articles before preparing a publication-quality XPS discussion.

Artificial Intelligence is beginning to transform this workflow. Modern AI systems such as ChatGPT, Claude, Gemini, and other advanced large language models can assist researchers in interpreting XPS spectra, explaining chemical-state changes, generating publication-ready discussions, comparing multiple samples, preparing reviewer responses, and even suggesting additional experiments. However, the quality of AI-generated interpretations depends heavily on how the researcher communicates with the AI. A vague prompt often produces generic responses, whereas a carefully designed prompt can yield detailed, technically accurate, and publication-ready analyses.

This guide was created to help researchers fully exploit the capabilities of AI for XPS spectroscopy. Rather than providing only a few example prompts, we present 160 carefully designed AI prompts covering nearly every aspect of XPS analysis—from basic elemental identification to advanced surface chemistry, quantitative analysis, scientific writing, and manuscript preparation. These prompts are organized into practical categories so researchers can quickly find the most appropriate prompt for their specific application.

In addition to the 160 prompts, this guide includes:

• Expert prompt templates for reusable XPS workflows
• Practical examples of effective and ineffective prompts
• Frequently asked questions about AI-assisted XPS analysis
• Best practices for obtaining accurate AI-generated interpretations
• Guidance on integrating XPS with complementary techniques such as XRD, Raman spectroscopy, FTIR, SEM, TEM, BET, EIS, TGA, DSC, and electrochemical measurements

These resources are intended for researchers at every stage of their careers—from undergraduate students performing their first XPS experiment to experienced scientists preparing manuscripts for high-impact journals.

It is important to recognize that AI should not replace scientific expertise. Instead, it should be viewed as an intelligent research assistant capable of accelerating data interpretation, improving scientific writing, and enhancing research productivity. The most reliable conclusions are always obtained by combining AI-generated insights with experimental evidence, peer-reviewed literature, and expert judgment.

Whether your goal is to identify oxidation states, analyze surface functionalization, study corrosion products, investigate catalytic active sites, interpret thin-film chemistry, or prepare a publication-ready manuscript, the prompts in this guide will help you use AI more effectively and consistently.

Welcome to the next generation of AI-assisted XPS analysis. By learning how to communicate with AI using well-designed prompts, you can significantly reduce interpretation time, improve manuscript quality, and unlock deeper insights from your XPS data.

What Are AI Prompts for XPS Analysis?

Artificial Intelligence can significantly simplify XPS interpretation, but the quality of the results depends heavily on the quality of the prompt you provide. A vague request such as “Analyze this XPS spectrum” often produces generic explanations, while a detailed prompt allows AI to generate a much deeper, publication-ready interpretation.

A well-designed XPS prompt should provide enough scientific context for the AI to understand not only the spectrum itself, but also the material, experimental conditions, and research objective. The more information you provide, the more accurate and useful the interpretation becomes.

At AnalyzeTest AI, we have found that combining experimental details with a structured prompt consistently produces more reliable discussions, better chemical-state assignments, and stronger publication-ready analyses.

1. Clearly Describe Your Material

Always begin by introducing the material being analyzed.

Instead of writing:

Analyze this XPS spectrum.

Write:

Analyze the XPS spectrum of nitrogen-doped graphene oxide synthesized by hydrothermal reduction.

Providing the material immediately narrows the possible chemical environments and allows the AI to generate more meaningful interpretations.

2. Specify Which Core-Level Spectra Are Available

Different XPS regions contain different chemical information.

Mention exactly which spectra you have, for example:

• Survey Spectrum
• C 1s
• O 1s
• N 1s
• Fe 2p
• Co 2p
• Ni 2p
• Ti 2p
• Zn 2p
• Cu 2p

The AI can then focus on the correct chemical states and expected bonding environments.

3. Include Peak Positions

Peak positions are the foundation of every XPS interpretation.

Instead of saying:

Interpret my C 1s spectrum.

Provide something like:

• 284.8 eV
• 286.2 eV
• 287.9 eV
• 289.1 eV

This enables AI to identify the likely chemical bonds, oxidation states, and functional groups with much greater accuracy.

4. Mention Peak Areas or Atomic Percentages

If quantitative analysis is available, include it.

Example:

• Carbon: 68.5 at.%
• Oxygen: 22.3 at.%
• Nitrogen: 5.1 at.%
• Iron: 4.1 at.%

Quantitative information helps the AI explain changes in surface composition and compare different samples more effectively.

5. Describe the Experimental Conditions

Surface chemistry is highly dependent on sample preparation.

Useful information includes:

• Synthesis method
• Heat-treatment temperature
• Annealing atmosphere
• Plasma treatment
• Acid or alkali modification
• Electrochemical cycling
• Corrosion exposure
• Surface functionalization

This context allows AI to explain why the observed chemical states appear.

6. Define Your Objective

Tell the AI exactly what you need.

Examples include:

• Publication-ready discussion
• Peak assignment
• Oxidation-state determination
• Surface chemistry interpretation
• Reviewer response
• Comparison between samples
• Figure caption
• Thesis writing

The more specific the objective, the better the final response.

7. Mention Complementary Characterization

XPS rarely tells the whole story.

Whenever possible, include results from:

• XRD
• FTIR
• Raman
• SEM
• TEM
• BET
• TGA
• DSC
• UV–Vis
• EIS

At AnalyzeTest AI, integrated interpretation of multiple characterization techniques consistently produces more comprehensive and scientifically convincing discussions than analyzing XPS data in isolation.

8. Specify Your Target Journal or Writing Style

Scientific writing varies depending on the publication.

For example:

Write the discussion in the style of Applied Surface Science.

or

Prepare the discussion for ACS Applied Materials & Interfaces.

This helps the AI generate text with an appropriate level of technical depth and academic style.

Example of a Strong XPS Prompt

Act as an internationally recognized XPS spectroscopy expert.

Analyze the XPS results of nitrogen-doped graphene oxide.

Available spectra:
• Survey
• C 1s
• O 1s
• N 1s

C 1s peaks:
284.8, 286.2, 287.8, 289.0 eV

N 1s peaks:
398.6, 400.1, 401.3 eV

The material was synthesized by hydrothermal reduction at 180 °C.

Interpret:

• Chemical states
• Surface functional groups
• Nitrogen configurations
• Oxidation-state changes
• Structure–property relationships

Write a publication-ready Results and Discussion section suitable for a Q1 materials science journal.

Why Prompt Quality Matters

Artificial Intelligence is not simply a search engine—it is a reasoning tool. The more scientific context you provide, the more effectively it can connect peak positions, chemical states, synthesis conditions, and material properties into a coherent interpretation.

This principle is at the core of AnalyzeTest AI, where carefully engineered prompts are used to transform raw XPS spectra into publication-ready scientific discussions. Whether you are analyzing catalysts, thin films, nanomaterials, corrosion products, battery electrodes, or advanced coatings, investing a few extra minutes in writing a detailed prompt can save hours of manual interpretation and significantly improve the quality of your research output.

Can AI Perform XPS Peak Deconvolution? Understanding the Limitations of Artificial Intelligence

Artificial Intelligence has dramatically improved the way researchers interpret XPS data, generate publication-ready discussions, explain chemical states, and compare surface compositions. However, one common misconception is that AI can completely replace the experimental workflow required for XPS analysis.

The reality is different.

While AI can greatly assist in interpreting XPS results, it cannot reliably perform peak deconvolution (peak fitting) directly from raw XPS spectra. Peak fitting remains one of the most critical—and expertise-dependent—steps in XPS analysis.

What is Peak Deconvolution?

Peak deconvolution is the mathematical process of separating overlapping XPS peaks into individual chemical-state components.

For example, a C 1s spectrum may contain contributions from:

• C–C / C=C
• C–O
• C=O
• O–C=O
• π–π* satellite peaks

Similarly, Fe 2p, Co 2p, Ni 2p, Mn 2p and many transition-metal spectra often contain:

• Multiple oxidation states
• Multiplet splitting
• Shake-up satellites
• Asymmetric peak shapes
• Background contributions

Accurate separation of these components requires careful optimization of several parameters, including:

• Peak positions
• Peak widths (FWHM)
• Gaussian/Lorentzian mixing
• Background selection (Shirley or Tougaard)
• Spin-orbit splitting
• Area ratios
• Chemical constraints
• Instrument calibration

These operations are mathematical curve-fitting procedures rather than language-based reasoning tasks.

Why Can’t AI Perform Peak Fitting Reliably?

Current AI language models—including ChatGPT, Claude, Gemini, and similar systems—do not directly analyze raw spectral intensity data in the same way as dedicated XPS software.

They cannot automatically:

• Fit overlapping peaks
• Optimize fitting residuals
• Calculate goodness-of-fit
• Apply instrumental constraints
• Verify physically meaningful fitting parameters

Attempting to fit raw XPS spectra without specialized software often leads to inaccurate chemical-state assignments and unreliable scientific conclusions.

Therefore, peak fitting should always be performed before asking AI to interpret the results.

Where AI Becomes Extremely Powerful

Once high-quality peak fitting has been completed, AI becomes an outstanding scientific assistant.

It can rapidly:

• Assign chemical states
• Explain oxidation-state changes
• Compare treated and untreated samples
• Interpret surface functionalization
• Relate XPS results to synthesis conditions
• Correlate XPS with FTIR, Raman, XRD and SEM
• Generate publication-ready Results & Discussion sections
• Prepare reviewer responses
• Improve manuscript quality
• Suggest additional characterization techniques

In other words, AI is exceptionally effective for scientific interpretation, while dedicated XPS software remains essential for quantitative spectral fitting.

The AnalyzeTest AI Workflow

At AnalyzeTest AI, we combine the strengths of experienced XPS researchers with advanced AI-assisted scientific writing.

Our typical workflow includes:

1. Inspection of the raw XPS spectra
2. Professional baseline correction
3. Expert peak deconvolution using specialized XPS software
4. Verification of fitting quality
5. Chemical-state assignment
6. Atomic concentration analysis
7. Surface chemistry interpretation
8. Publication-ready scientific discussion generated with AI assistance
9. Reviewer-ready explanations
10. Integration with complementary characterization techniques (FTIR, Raman, XRD, SEM, TEM, BET, EIS, etc.)

This hybrid approach combines human expertise, professional XPS software, and Artificial Intelligence, producing interpretations that are significantly more reliable than relying on AI alone.

Our XPS Analysis Service

If you already have fitted spectra, AnalyzeTest AI can help you transform them into publication-ready scientific discussions.

If your spectra have not yet been deconvoluted, our team can also perform professional XPS peak fitting before the AI-assisted interpretation begins.

This combination ensures that your final report is both scientifically accurate and ready for publication in high-impact journals, making AnalyzeTest AI much more than a simple AI chatbot—it is a complete AI-assisted materials characterization platform supported by experienced researchers.

Common Mistakes Researchers Make When Using AI for XPS Analysis

Artificial Intelligence has become an invaluable assistant for interpreting XPS data, preparing manuscripts, and explaining surface chemistry. However, the quality of AI-generated results depends entirely on the quality of the information provided by the researcher.

Many disappointing AI responses are not caused by limitations of the AI itself—they result from incomplete or poorly structured prompts. Understanding the most common mistakes can dramatically improve the accuracy of AI-assisted XPS interpretation.

At AnalyzeTest AI, we have analyzed hundreds of XPS interpretation requests and found that the same mistakes occur repeatedly. Avoiding these pitfalls will help you obtain more reliable, publication-ready results.

1. Asking AI to Interpret Raw XPS Spectra Without Peak Deconvolution

This is by far the most common mistake.

Many researchers upload a raw XPS spectrum and ask:

“Please interpret my XPS spectrum.”

Unfortunately, this is rarely sufficient.

Most XPS peaks consist of multiple overlapping chemical states. Without proper peak fitting (deconvolution), neither AI nor a human expert can accurately determine the contribution of each chemical species.

Professional peak deconvolution should always be performed before attempting detailed chemical-state interpretation.

AnalyzeTest AI provides professional XPS peak fitting services using dedicated spectroscopy software before beginning AI-assisted interpretation whenever necessary.

2. Uploading Only an Image Instead of Peak Positions

A screenshot of an XPS spectrum contains very limited quantitative information.

Instead of uploading only an image, include:

• Binding energies
• Peak areas
• FWHM values (if available)
• Atomic concentrations
• Fitted peak components

Providing numerical data allows AI to generate significantly more accurate interpretations.

3. Forgetting to Specify Which Spectrum Is Being Analyzed

Many researchers simply upload a spectrum without identifying it.

For example:

“Analyze this spectrum.”

Instead, specify:

• Survey Spectrum
• C 1s
• O 1s
• N 1s
• Fe 2p
• Ti 2p
• Zn 2p

Each core level contains different chemical information, and identifying the spectrum helps AI apply the appropriate interpretation strategy.

4. Ignoring Experimental Conditions

Surface chemistry depends strongly on how the material was prepared.

Important details include:

• Synthesis method
• Annealing temperature
• Atmosphere
• Plasma treatment
• Acid or alkali modification
• Electrochemical cycling
• Corrosion exposure
• Surface functionalization

Without this information, AI cannot explain why chemical states change.

5. Requesting Chemical-State Assignments Without Peak Fitting

Researchers often ask AI:

“Determine the oxidation states.”

However, oxidation-state determination usually requires:

• Peak fitting
• Satellite identification
• Spin-orbit splitting analysis
• Chemical-state constraints

AI can explain fitted components, but it should not invent peak components that have not been experimentally resolved.

6. Not Providing the Research Objective

Different goals require different types of analysis.

For example, are you looking for:

• Publication-ready discussion?
• Peak assignments?
• Reviewer response?
• Surface chemistry interpretation?
• Thesis writing?
• Figure captions?
• Comparative analysis?

Clearly defining your objective enables AI to tailor its response to your needs.

7. Ignoring Complementary Characterization

XPS alone rarely tells the complete story.

The strongest scientific discussions combine XPS with:

• XRD
• FTIR
• Raman spectroscopy
• SEM
• TEM
• BET
• TGA
• DSC
• EIS

At AnalyzeTest AI, integrated interpretation across multiple characterization techniques produces more convincing and scientifically rigorous conclusions than interpreting XPS in isolation.

8. Expecting AI to Replace Scientific Judgment

Artificial Intelligence is an exceptionally powerful research assistant, but it is not a substitute for scientific expertise.

Researchers should always:

• Review AI-generated interpretations.
• Verify peak assignments.
• Compare conclusions with experimental evidence.
• Consult relevant literature.
• Apply their own scientific reasoning.

AI should accelerate scientific work—not replace critical thinking.

9. Requesting References Without Verification

Although AI can suggest relevant concepts and commonly cited mechanisms, researchers should always verify references before including them in a manuscript.

Using fabricated or incorrect citations can seriously compromise the credibility of your work.

At AnalyzeTest AI, we encourage researchers to validate all references and support important conclusions with peer-reviewed literature.

10. Assuming All AI Tools Are Designed for XPS

Most general-purpose AI assistants have not been specifically developed for materials characterization.

As a result, they may:

• Use incorrect terminology.
• Misinterpret transition-metal spectra.
• Ignore satellite peaks.
• Overlook multiplet splitting.
• Produce generic explanations unrelated to the material.

AnalyzeTest AI is different. It is specifically designed to support researchers working with advanced characterization techniques, including XPS, FTIR, Raman spectroscopy, XRD, TGA, SEM, TEM, BET, EIS, and many others. By combining expert knowledge with AI-assisted scientific writing, it delivers interpretations that are tailored to the needs of materials scientists and engineers.

Final Advice

The quality of AI-assisted XPS analysis depends less on the sophistication of the AI model and more on the quality of the information you provide.

A carefully prepared dataset—including professionally fitted spectra, experimental details, quantitative results, and a clear research objective—allows AI to generate interpretations that are more accurate, more insightful, and far closer to publication-ready quality.

By avoiding these common mistakes and combining expert XPS analysis with AI-assisted interpretation, researchers can dramatically reduce analysis time while improving the scientific quality of their manuscripts. AnalyzeTest AI follows exactly this philosophy, integrating professional peak fitting, expert validation, and advanced AI to help researchers produce reliable, publication-ready XPS analyses.

AI vs Human Expert: Which One Should You Trust for XPS Analysis?

With the rapid advancement of Artificial Intelligence, many researchers now use AI tools to assist with XPS interpretation, manuscript preparation, and data analysis. AI has undoubtedly become a valuable research assistant, but an important question remains:

Can AI replace an experienced XPS researcher?

The short answer is no.

Artificial Intelligence and human expertise excel at different tasks. Understanding their respective strengths and limitations allows researchers to obtain more accurate interpretations and avoid costly mistakes.

What AI Does Extremely Well

Modern AI systems can process large amounts of scientific information within seconds. When provided with properly prepared XPS data, AI can generate detailed explanations that would otherwise require hours of literature review.

AI is particularly effective at:

• Explaining chemical-state assignments
• Interpreting oxidation-state changes
• Identifying probable chemical bonds
• Comparing multiple XPS spectra
• Generating publication-ready Results & Discussion sections
• Improving scientific writing
• Drafting reviewer responses
• Summarizing complex surface chemistry
• Correlating XPS with FTIR, Raman, XRD, SEM, TEM, BET, TGA, and electrochemical measurements
• Suggesting additional experiments to strengthen a manuscript

For researchers preparing journal articles or theses, AI can dramatically reduce the time required to transform raw analytical results into professional scientific text.

Where Human Expertise Remains Essential

Despite its impressive capabilities, AI does not directly analyze raw XPS signals in the same way as specialized spectroscopy software.

Several critical aspects of XPS analysis still require an experienced researcher, including:

• Instrument calibration
• Energy referencing
• Background selection (Shirley or Tougaard)
• Peak deconvolution
• Peak-shape optimization
• Spin-orbit constraints
• Satellite peak identification
• Multiplet splitting analysis
• Validation of chemical-state assignments
• Assessment of fitting quality

These tasks involve mathematical optimization, experimental knowledge, and practical experience that cannot currently be replaced by language-based AI models.

Why Peak Deconvolution Is Different

One of the most common misconceptions is that AI can automatically fit raw XPS spectra.

In reality, peak deconvolution is not a text-generation task—it is a quantitative mathematical procedure.

Reliable peak fitting requires specialized XPS software, careful adjustment of fitting parameters, and validation against known physical and chemical constraints.

Without accurate peak fitting, even the most advanced AI system may produce misleading interpretations because the underlying spectral components have not been correctly identified.

For this reason, professional peak fitting should always precede AI-assisted interpretation.

The Ideal Workflow: AI + Human Expertise

Rather than viewing AI and human experts as competitors, researchers should consider them complementary tools.

An efficient XPS workflow typically follows these steps:

1. Acquire high-quality XPS spectra.
2. Perform energy calibration and background correction.
3. Carry out professional peak deconvolution using dedicated XPS software.
4. Verify the quality of the fitting.
5. Use AI to interpret the fitted spectra.
6. Correlate the XPS results with other characterization techniques.
7. Generate publication-ready discussions and reviewer responses.

This hybrid approach combines the precision of expert data processing with the speed and productivity of Artificial Intelligence.

Comparison: AI vs. Human Expert

Why AnalyzeTest AI Combines Both Approaches

At AnalyzeTest AI, we believe that the highest-quality XPS analysis comes from combining professional scientific expertise with advanced Artificial Intelligence.

Unlike generic AI chatbots, our workflow is designed specifically for materials characterization. Depending on your requirements, our experts can:

• Perform professional XPS peak deconvolution using specialized software.
• Verify the quality and reliability of the fitted spectra.
• Assign chemical states and oxidation states accurately.
• Interpret surface chemistry in the context of your material and synthesis method.
• Correlate XPS results with complementary techniques such as FTIR, XRD, Raman spectroscopy, SEM, TEM, BET, and electrochemical analysis.
• Produce publication-ready Results and Discussion sections tailored to high-impact journals.
• Assist with reviewer responses, thesis writing, and scientific reporting.

This combination of expert analysis and AI-assisted scientific writing provides a level of accuracy and depth that cannot be achieved by AI or manual interpretation alone.

The Future of XPS Analysis

Artificial Intelligence is rapidly changing the way researchers analyze and communicate scientific data. However, AI should be viewed as an intelligent collaborator, not a replacement for scientific expertise.

Researchers who combine high-quality experimental work, professional XPS analysis, and AI-assisted interpretation will produce more reliable results, prepare stronger manuscripts, and accelerate their research workflow.

At AnalyzeTest AI, our mission is to bring these strengths together—delivering scientifically rigorous, publication-ready XPS analyses while preserving the accuracy and critical thinking that only experienced researchers can provide.

Before vs. After: Poor and Excellent XPS Prompts

One of the biggest advantages of Artificial Intelligence is its ability to generate detailed scientific interpretations in seconds. However, the quality of the output depends almost entirely on the quality of the prompt you provide.

Many researchers believe that AI produces inconsistent or inaccurate XPS interpretations. In reality, the problem is often the prompt itself. A vague request gives the AI almost no scientific context, while a carefully designed prompt allows it to produce responses that are much closer to publication-ready quality.

The following examples demonstrate how a small improvement in prompt design can dramatically improve the usefulness of AI-generated XPS analyses.

Example 1 – Generic XPS Interpretation

❌ Poor Prompt

Analyze my XPS spectrum.

Why It Doesn’t Work

This prompt provides almost no information.

The AI does not know:

• What material is being analyzed.
• Which XPS spectrum is shown.
• Whether peak fitting has been completed.
• The synthesis method.
• The research objective.
• The experimental conditions.

As a result, the response will usually consist of generic information about XPS rather than a meaningful scientific interpretation.

✅ Excellent Prompt

Act as an internationally recognized XPS expert.

Analyze the C 1s XPS spectrum of nitrogen-doped graphene oxide synthesized by hydrothermal reduction at 180 °C.

Peak fitting has already been completed.

Fitted components:

284.8 eV
286.2 eV
287.8 eV
289.1 eV

Interpret:

• Chemical states
• Surface functional groups
• Structural evolution
• Influence of nitrogen doping

Write a publication-ready Results and Discussion section.

Example 2 – Oxidation State Analysis

❌ Poor Prompt

Determine the oxidation state of iron.

Why It Doesn’t Work

Iron may exist as:

• Fe⁰
• Fe²⁺
• Fe³⁺

Without the Fe 2p peak positions, fitted components, or satellite information, the AI cannot reliably distinguish between these oxidation states.

✅ Excellent Prompt

Interpret the Fe 2p XPS spectrum.

Peak fitting has been completed.

Fe 2p3/2:

709.8 eV
711.2 eV
713.6 eV

Fe 2p1/2:

723.5 eV
724.8 eV

Satellite peaks are observed.

Determine:

• Oxidation states
• Relative chemical species
• Surface chemistry

Explain the results in the style of Applied Surface Science.

Example 3 – Comparative Analysis

❌ Poor Prompt

Compare these two XPS spectra.

Why It Doesn’t Work

The AI has no idea:

• What the samples are.
• What treatment was performed.
• What differences should be expected.
• Which core level is being compared.

✅ Excellent Prompt

Compare the C 1s XPS spectra of untreated and plasma-treated carbon fibers.

Discuss:

• Peak shifts
• Relative peak intensities
• Oxygen-containing functional groups
• Surface activation
• Chemical modifications

Explain how these changes influence interfacial bonding with epoxy resin.

Example 4 – Survey Spectrum

❌ Poor Prompt

Explain my survey spectrum.

Why It Doesn’t Work

A survey spectrum contains only elemental information.

Without atomic percentages or material information, AI can provide only superficial comments.

✅ Excellent Prompt

Interpret the survey XPS spectrum of TiO₂-coated stainless steel.

Atomic composition:

Ti: 21.4 at.%

O: 52.7 at.%

C: 24.5 at.%

N: 1.4 at.%

Discuss:

• Surface composition
• Surface contamination
• Coating quality
• Implications for corrosion resistance

Write in academic English suitable for a Q1 journal.

Example 5 – Reviewer Response

❌ Poor Prompt

Answer the reviewer's comment.

Why It Doesn’t Work

The AI does not know:

• What the reviewer asked.
• What the manuscript contains.
• What data are available.

✅ Excellent Prompt

Act as an experienced journal reviewer and scientific editor.

Reviewer comment:

"The XPS discussion lacks evidence supporting the proposed oxidation-state assignments."

Using the following fitted peak positions:

[Insert Peak Table]

Write a professional reviewer response that justifies the assignments and strengthens the manuscript.

Example 6 – Integrated Characterization

❌ Poor Prompt

Explain my XPS results.

Why It Doesn’t Work

Scientific conclusions rarely rely on XPS alone.

✅ Excellent Prompt

Interpret the XPS results together with:

• XRD
• FTIR
• Raman spectroscopy
• SEM
• BET

Material:

Nitrogen-doped porous biochar.

Explain how the surface chemistry observed by XPS supports the structural evolution identified by the complementary characterization techniques.

Prepare a publication-ready discussion.

Example 7 – Surface Functionalization

❌ Poor Prompt

Analyze my O 1s spectrum.

Why It Doesn’t Work

Different materials produce very different O 1s components.

Without experimental context, the AI can only guess.

✅ Excellent Prompt

Interpret the O 1s XPS spectrum of plasma-treated polyethylene.

Peak fitting has been completed.

Components:

530.9 eV

532.2 eV

533.6 eV

Discuss:

• Hydroxyl groups
• Carbonyl groups
• Adsorbed oxygen
• Surface activation
• Wettability improvement

Prepare the discussion for ACS Applied Materials & Interfaces.

Why Better Prompts Produce Better Science

The difference between a poor prompt and an excellent one is not simply the length—it is the amount of scientific context provided.

A high-quality XPS prompt should include:

• Material name
• Sample preparation method
• Core-level spectra
• Peak positions
• Peak fitting information
• Atomic concentrations
• Experimental conditions
• Research objective
• Target journal (optional)

The more complete your prompt, the more accurate, detailed, and publication-ready the AI-generated interpretation becomes.

At AnalyzeTest AI, carefully engineered prompts form the foundation of every AI-assisted XPS analysis. Combined with professional peak deconvolution and expert scientific review, this structured approach enables researchers to obtain interpretations that are not only technically accurate but also suitable for publication in high-impact scientific journals.

How to Customize These AI Prompts for Your Own XPS Research

The 160 AI prompts presented in this guide are designed as powerful starting points for XPS interpretation. However, no two research projects are identical. A prompt that works perfectly for analyzing graphene oxide may not be appropriate for battery electrodes, corrosion products, catalysts, or polymer coatings.

To obtain the most accurate and publication-ready AI responses, you should customize each prompt according to your specific material, experimental conditions, and research objectives.

At AnalyzeTest AI, we encourage researchers to think of prompts as flexible scientific templates rather than fixed commands. The more relevant information you provide, the more valuable the AI-generated interpretation becomes.

1. Replace the Material Name

Always begin by specifying the exact material under investigation.

Instead of writing:

Analyze my XPS spectrum.

Write:

• Analyze the XPS spectrum of TiO₂ nanoparticles.
• Interpret the XPS results of nitrogen-doped biochar.
• Analyze the surface chemistry of MXene-coated stainless steel.
• Interpret the XPS spectra of CoFeNi thin films after annealing.

This immediately provides the AI with the chemical context required for a more accurate interpretation.

2. Include the Sample Preparation Method

Surface chemistry depends strongly on how the material was produced.

Useful information includes:

• Hydrothermal synthesis
• Sol–gel process
• RF magnetron sputtering
• Chemical vapor deposition (CVD)
• Electrodeposition
• Plasma treatment
• Electrochemical oxidation
• Acid activation
• Thermal annealing

For example:

The sample was synthesized by hydrothermal treatment at 180 °C for 12 hours.

or

Thin films were deposited by RF magnetron sputtering and annealed at 500 °C under nitrogen.

These details allow AI to explain why specific chemical states appear on the surface.

3. Specify Which Core-Level Spectra Are Available

Instead of saying:

Interpret the XPS results.

Tell the AI exactly which spectra you have:

• Survey Spectrum
• C 1s
• O 1s
• N 1s
• Fe 2p
• Co 2p
• Ni 2p
• Ti 2p
• Zn 2p
• Cu 2p
• Si 2p
• Al 2p

Different elements require completely different interpretation strategies.

4. Always Include Peak Fitting Results

One of the most effective ways to improve AI accuracy is to provide fitted peak positions rather than raw spectra.

For example:

C 1s

• 284.8 eV
• 286.2 eV
• 287.9 eV
• 289.0 eV

O 1s

• 530.4 eV
• 531.7 eV
• 533.1 eV

Peak fitting allows AI to focus on chemical interpretation instead of attempting to infer unresolved spectral components.

If your spectra have not yet been deconvoluted, AnalyzeTest AI can perform professional peak fitting before generating the AI-assisted interpretation.

5. Add Quantitative Results

Whenever available, include atomic concentrations.

Example:

• Carbon: 68.2 at.%
• Oxygen: 21.7 at.%
• Nitrogen: 7.1 at.%
• Iron: 3.0 at.%

This enables AI to discuss changes in surface composition rather than simply assigning peaks.

6. Describe What Changed Between Samples

If your study compares multiple samples, explain the treatment applied to each one.

Examples include:

• Before and after annealing
• Untreated vs plasma-treated
• Coated vs uncoated
• Before and after corrosion
• Fresh catalyst vs used catalyst
• Different doping concentrations
• Different sputtering powers

The AI can then relate changes in peak position, peak intensity, and atomic concentration to the processing conditions.

7. Tell the AI What You Want

The same XPS data can be interpreted in many different ways depending on your objective.

Examples include:

• Publication-ready Results & Discussion
• Peak assignment
• Oxidation-state analysis
• Surface chemistry interpretation
• Reviewer response
• Thesis chapter
• Figure caption
• Comparative discussion
• Journal-style scientific writing

Being specific helps the AI produce exactly the type of output you need.

8. Mention Complementary Characterization

The strongest scientific discussions integrate XPS with other characterization techniques.

Whenever possible, mention:

• XRD
• FTIR
• Raman spectroscopy
• SEM
• TEM
• BET
• AFM
• TGA
• DSC
• EIS
• Contact angle measurements

At AnalyzeTest AI, multi-technique interpretation is one of the core strengths of our platform. Rather than analyzing XPS data in isolation, we help researchers connect surface chemistry with structural, morphological, thermal, optical, and electrochemical properties to produce more comprehensive scientific discussions.

9. Specify Your Target Journal

Different journals have different expectations regarding writing style and technical depth.

For example:

Write the discussion in the style of Applied Surface Science.

or

Prepare a Results & Discussion section suitable for ACS Applied Materials & Interfaces.

or

Write in the style typically accepted by Surface and Coatings Technology.

This helps AI generate text that more closely matches your intended publication.

10. Build Your Own Prompt Library

As your research progresses, you will likely analyze many similar materials and experiments. Instead of writing new prompts from scratch each time, save and refine your best-performing prompts.

Creating a personal prompt library offers several advantages:

• Consistent interpretation across projects.
• Faster analysis of new datasets.
• Improved reproducibility in scientific writing.
• Reduced time spent editing AI-generated content.

Researchers who maintain a well-organized collection of prompts often achieve better results with less effort.

A Complete Customized Prompt Example

Act as an internationally recognized XPS spectroscopy expert.

Analyze the XPS results of nitrogen-doped MXene synthesized by hydrothermal treatment at 180 °C.

Available spectra:

• Survey
• C 1s
• O 1s
• N 1s
• Ti 2p

Peak fitting has already been completed.

Discuss:

• Chemical-state assignments
• Surface functional groups
• Oxidation-state changes
• Influence of nitrogen doping
• Correlation with XRD, FTIR, and Raman results
• Structure–property relationships

Write a publication-ready Results & Discussion section suitable for Applied Surface Science.

Final Recommendation

The prompts in this guide are designed to be adaptable, not rigid. By replacing the material name, experimental details, peak fitting results, and research objectives with your own data, you can transform a generic AI response into a technically accurate and publication-ready interpretation.

At AnalyzeTest AI, we combine expertly crafted prompts with professional XPS peak deconvolution, scientific validation, and AI-assisted writing to help researchers produce high-quality analyses that are ready for theses, reports, and publication in leading scientific journals.

How AnalyzeTest AI Improves XPS Interpretation

Artificial Intelligence has transformed the way researchers interpret XPS data, but obtaining reliable, publication-quality results requires far more than simply uploading a spectrum to a chatbot.

At AnalyzeTest AI, we have developed a specialized workflow that combines expert XPS knowledge, professional peak fitting, scientific literature, and advanced AI-assisted writing. The result is an interpretation that is not only technically accurate but also suitable for publication in high-impact scientific journals.

Unlike general-purpose AI tools, AnalyzeTest AI is specifically designed for researchers working in materials science, nanotechnology, chemistry, corrosion engineering, energy storage, catalysis, polymers, and surface science.

More Than a General AI Assistant

Most AI chatbots can explain basic XPS concepts, but they are not designed to perform complete scientific analyses.

AnalyzeTest AI is built around the real workflow followed by experienced materials scientists.

Instead of generating generic explanations, our platform focuses on producing interpretations that are:

• Scientifically accurate
• Technically detailed
• Publication-ready
• Consistent with current literature
• Tailored to your specific material and research objectives

Step 1 – Professional Evaluation of Your Data

Every XPS project begins with an evaluation of the submitted data.

Our experts first determine whether the provided information is sufficient for a reliable interpretation.

Typical checks include:

• Spectrum quality
• Energy calibration
• Signal-to-noise ratio
• Availability of survey spectra
• Availability of fitted peak components
• Presence of complementary characterization techniques

If important information is missing, we recommend the additional data needed before proceeding with the interpretation.

Step 2 – Expert Peak Deconvolution (When Required)

One of the biggest misconceptions in AI-assisted XPS analysis is that Artificial Intelligence can perform peak fitting automatically.

In reality, peak deconvolution remains a specialist task that requires dedicated XPS software and scientific expertise.

When raw spectra are provided, our team can perform professional peak fitting using industry-standard software before the AI interpretation begins.

This service includes:

• Background correction
• Peak deconvolution
• Peak-shape optimization
• Spin-orbit constraints
• Satellite peak analysis
• Chemical-state validation

This ensures that the interpretation is based on physically meaningful spectral components rather than assumptions.

Step 3 – AI-Assisted Scientific Interpretation

Once the spectra have been properly prepared, AnalyzeTest AI uses advanced prompt engineering together with scientific reasoning to generate detailed interpretations.

The system can explain:

• Chemical-state assignments
• Oxidation-state evolution
• Surface functional groups
• Surface contamination
• Effects of synthesis conditions
• Surface modification mechanisms
• Structure–property relationships
• Corrosion mechanisms
• Catalytic behavior
• Battery surface reactions

Each discussion is tailored to the specific material rather than relying on generic textbook descriptions.

Step 4 – Integration with Other Characterization Techniques

Scientific conclusions should never rely on XPS alone.

One of the unique strengths of AnalyzeTest AI is its ability to integrate XPS results with complementary characterization techniques, including:

• XRD
• FTIR
• Raman spectroscopy
• SEM
• FESEM
• TEM
• SAED
• EDS
• BET
• TGA/DTG
• DSC
• AFM
• UV–Vis spectroscopy
• Contact angle measurements
• Electrochemical techniques (EIS, Polarization, CV, GCD)

This integrated approach produces a much more complete scientific interpretation than analyzing XPS data in isolation.

Step 5 – Publication-Ready Scientific Writing

Many researchers spend days converting experimental observations into a well-written Results and Discussion section.

AnalyzeTest AI dramatically accelerates this process.

Our platform can generate:

• Results & Discussion sections
• Journal-style scientific writing
• Figure captions
• Supporting Information text
• Reviewer responses
• Thesis chapters
• Technical reports
• Conference papers

All content is written in professional academic English and can be adapted to the style of leading journals.

Step 6 – Literature-Based Scientific Reasoning

Strong scientific discussions should be supported by established knowledge rather than simple peak assignments.

AnalyzeTest AI uses literature-informed reasoning to explain:

• Why peak shifts occur
• Why oxidation states change
• How synthesis parameters influence surface chemistry
• Relationships between XPS and material performance
• Mechanisms behind corrosion resistance, catalysis, adsorption, sensing, or electrochemical behavior

The goal is not merely to identify peaks, but to explain the underlying scientific mechanisms.

Designed for Many Research Fields

AnalyzeTest AI supports researchers working on a wide variety of materials, including:

• Nanoparticles
• Thin films
• MXenes
• MOFs
• Catalysts
• Biochar
• Biomaterials
• Polymers
• Composite materials
• Corrosion-resistant coatings
• Energy storage materials
• Supercapacitors
• Battery electrodes
• Photocatalysts
• Sensors
• Semiconductor materials
• Magnetic materials

Why Researchers Choose AnalyzeTest AI

Researchers choose AnalyzeTest AI because it combines capabilities that are rarely available within a single platform.

Our service offers:

• AI-assisted scientific interpretation
• Expert XPS consultation
• Professional peak deconvolution
• Publication-ready scientific writing
• Integration of multiple characterization techniques
• Reviewer response preparation
• Assistance with thesis and manuscript development
• Support for high-impact journal submissions

Rather than replacing scientific expertise, AnalyzeTest AI enhances it by combining experienced researchers with modern Artificial Intelligence.

Our Mission

Our mission is simple:

To help researchers transform complex characterization data into accurate, insightful, and publication-ready scientific knowledge.

Whether you are working on advanced coatings, nanomaterials, catalysts, battery materials, polymers, or corrosion science, AnalyzeTest AI provides a complete workflow—from expert spectral evaluation and professional peak fitting to AI-assisted interpretation and manuscript preparation.

By combining human expertise, specialized XPS software, and Artificial Intelligence, AnalyzeTest AI enables researchers to work faster, publish with greater confidence, and extract the maximum scientific value from every XPS experiment.

Survey Spectrum Prompts (1–10)

The survey spectrum is the starting point of every XPS investigation. It provides an overview of the elements present on the sample surface, their relative abundance, and potential contaminants. Although it does not provide detailed chemical-state information, a properly interpreted survey spectrum helps researchers assess sample purity, coating coverage, oxidation, and elemental distribution before proceeding to high-resolution scans.

The following AI prompts are designed to help researchers extract the maximum scientific value from XPS survey spectra.

Prompt 1 – Complete Survey Spectrum Interpretation

Act as an internationally recognized XPS expert.

Interpret the following XPS survey spectrum.

Material:
[Insert Material]

Elements detected:
[Insert Elements]

Atomic concentrations:
[Insert Atomic Percentages]

Discuss:

• Surface elemental composition
• Possible contaminants
• Surface cleanliness
• Implications for the material's properties

Write a publication-ready Results and Discussion section.

Prompt 2 – Surface Composition Analysis

Analyze the XPS survey spectrum and explain what the elemental composition reveals about the surface chemistry of this material.

Discuss whether the detected elements are expected based on the synthesis process.

Prompt 3 – Atomic Percentage Interpretation

Interpret the following atomic percentages obtained from an XPS survey spectrum.

Discuss:

• Relative abundance of each element
• Surface enrichment
• Possible segregation effects
• Scientific significance

Prompt 4 – Detecting Surface Contamination

Analyze this XPS survey spectrum.

Identify possible surface contaminants such as carbon, oxygen, silicon, sodium, chlorine, sulfur, or other unexpected elements.

Explain their possible origin and whether they may influence subsequent high-resolution analysis.

Prompt 5 – Comparing Two Survey Spectra

Compare the XPS survey spectra of Sample A and Sample B.

Discuss differences in:

• Elemental composition
• Atomic percentages
• Surface contamination
• Possible effects of the treatment process

Prepare the discussion for publication.

Prompt 6 – Coating Quality Evaluation

Interpret the XPS survey spectrum of a coated material.

Determine whether the coating appears continuous based on the detected elemental composition.

Discuss possible substrate exposure, coating uniformity, and surface coverage.

Prompt 7 – Surface Modification Analysis

Compare the XPS survey spectra before and after surface modification.

Explain:

• Which new elements appear
• Which elements decrease
• Whether the modification was successful
• Evidence supporting surface functionalization

Prompt 8 – Correlating Survey Spectrum with Synthesis

Interpret the XPS survey spectrum in relation to the synthesis method.

Material:
[Insert Material]

Synthesis:
[Insert Method]

Explain whether the observed elemental composition agrees with the expected reaction mechanism.

Prompt 9 – Multi-Technique Interpretation

Interpret the XPS survey spectrum together with XRD, FTIR, Raman spectroscopy, and SEM results.

Explain how the elemental composition supports the structural and morphological characterization.

Write in the style of a high-impact journal.

Prompt 10 – Journal-Ready Survey Discussion

Act as a reviewer and XPS specialist.

Write a complete publication-ready discussion for the XPS survey spectrum.

Include:

• Element identification
• Surface composition
• Contamination assessment
• Scientific interpretation
• Connection to material performance

Use professional academic English suitable for Applied Surface Science or ACS Applied Materials & Interfaces.

These prompts are designed to help researchers move beyond simply listing detected elements and instead generate meaningful, publication-quality interpretations of XPS survey spectra.

C 1s Prompts (11–20)

The C 1s high-resolution spectrum is one of the most frequently analyzed regions in XPS because carbon is present in a wide variety of materials, including polymers, carbon nanomaterials, biomaterials, catalysts, coatings, batteries, and even surface contamination. Proper interpretation of the C 1s spectrum provides valuable insights into chemical bonding, surface functionalization, oxidation, and material modification.

The following prompts are designed to help researchers obtain accurate, publication-ready interpretations of C 1s spectra using AI.

Prompt 11 – Complete C 1s Interpretation

Act as an internationally recognized XPS expert.

Interpret the following C 1s spectrum.

Peak fitting has already been completed.

Components:

[Insert Binding Energies]

Discuss:

• Chemical bond assignments
• Relative peak intensities
• Surface chemistry
• Functional groups
• Structural implications

Write a publication-ready Results and Discussion section.

Prompt 12 – Functional Group Assignment

Interpret the C 1s XPS spectrum and assign each fitted peak to the corresponding functional group.

Discuss possible contributions from:

• C–C/C=C
• C–H
• C–O
• C–N
• C=O
• O–C=O
• Carbonates

Explain the scientific significance of each component.

Prompt 13 – Surface Oxidation Analysis

Analyze the C 1s spectrum before and after oxidation treatment.

Discuss:

• Changes in oxygen-containing functional groups
• Surface oxidation mechanism
• Evidence for successful oxidation
• Influence on material properties

Prompt 14 – Plasma Surface Treatment

Interpret the C 1s XPS spectra of a polymer before and after plasma treatment.

Explain:

• Peak shifts
• Formation of oxygen-containing groups
• Surface activation
• Wettability improvement
• Adhesion enhancement

Prompt 15 – Carbon Contamination Assessment

Evaluate the C 1s spectrum for evidence of adventitious carbon contamination.

Discuss:

• Typical contamination peaks
• Their origin
• Whether they interfere with interpretation
• Recommendations for data analysis

Prompt 16 – Graphene and Carbon Materials

Interpret the C 1s spectrum of graphene, graphene oxide, reduced graphene oxide, or carbon nanotubes.

Discuss:

• sp² carbon
• sp³ carbon
• Oxygen functional groups
• Degree of reduction
• Structural defects

Prepare the discussion for publication.

Prompt 17 – Comparative C 1s Analysis

Compare the C 1s spectra of Sample A and Sample B.

Discuss:

• Peak intensity changes
• Binding-energy shifts
• Surface functionalization
• Chemical modifications
• Structure–property relationships

Prompt 18 – Correlation with FTIR

Interpret the C 1s spectrum together with FTIR results.

Explain how both techniques support the identification of surface functional groups.

Write a coherent scientific discussion suitable for a Q1 journal.

Prompt 19 – Reviewer Response

Act as an experienced XPS reviewer.

A reviewer questioned the assignment of the C 1s peaks.

Using the following fitted peak positions:

[Insert Peak Positions]

Prepare a professional reviewer response that justifies each assignment using accepted XPS principles.

Prompt 20 – Advanced Publication-Ready Discussion

Act as an internationally recognized XPS scientist.

Interpret the following C 1s spectrum.

Material:
[Insert Material]

Synthesis Method:
[Insert Method]

Peak Positions:
[Insert Peaks]

Discuss:

• Peak assignments
• Surface chemistry
• Chemical-state evolution
• Influence of synthesis conditions
• Correlation with XRD, FTIR, Raman, and SEM
• Expected effects on material performance

Write a publication-ready Results and Discussion section in the style of Applied Surface Science.

These prompts help researchers move beyond simple peak assignments by generating comprehensive discussions that connect C 1s chemistry with material synthesis, surface modification, and functional performance.

O 1s Prompts (21–30)

The O 1s high-resolution XPS spectrum is one of the most informative regions for studying oxides, hydroxides, catalysts, corrosion products, biomaterials, polymers, ceramics, and nanomaterials. Proper interpretation of the O 1s spectrum provides valuable information about lattice oxygen, hydroxyl groups, adsorbed water, oxygen vacancies, surface oxidation, and chemical functionalization.

The following AI prompts are designed to help researchers generate scientifically accurate and publication-ready interpretations of O 1s spectra.

Prompt 21 – Complete O 1s Interpretation

Act as an internationally recognized XPS expert.

Interpret the following O 1s XPS spectrum.

Peak fitting has already been completed.

Components:

[Insert Binding Energies]

Discuss:

• Peak assignments
• Oxygen species
• Surface chemistry
• Chemical-state evolution
• Scientific significance

Write a publication-ready Results and Discussion section.

Prompt 22 – Assigning O 1s Components

Interpret the fitted O 1s spectrum.

Assign each component to the appropriate oxygen species, including:

• Lattice oxygen (O²⁻)
• Hydroxyl groups (–OH)
• Adsorbed oxygen
• Adsorbed water
• Carbonyl oxygen
• Carboxyl oxygen
• Oxygen vacancies (if applicable)

Explain the evidence supporting each assignment.

Prompt 23 – Oxygen Vacancy Analysis

Analyze the O 1s spectrum for evidence of oxygen vacancies.

Discuss:

• Peak positions
• Defect-related oxygen
• Surface defects
• Influence on catalytic or electrochemical performance
• Relationship with synthesis conditions

Prompt 24 – Metal Oxide Interpretation

Interpret the O 1s spectrum of a metal oxide.

Material:

[Insert Material]

Discuss:

• Lattice oxygen
• Surface hydroxylation
• Surface adsorbed oxygen
• Oxide stability
• Effects on material properties

Prepare a publication-ready discussion.

Prompt 25 – Before and After Surface Treatment

Compare the O 1s spectra before and after surface treatment.

Discuss:

• Peak shifts
• Relative peak intensity changes
• Formation of hydroxyl groups
• Surface oxidation
• Chemical modification mechanism

Prompt 26 – Corrosion Product Analysis

Interpret the O 1s spectrum of a corroded metal surface.

Explain:

• Oxide formation
• Hydroxide formation
• Adsorbed oxygen species
• Corrosion products
• Corrosion mechanism

Write the discussion in the style of Corrosion Science.

Prompt 27 – Battery Materials

Analyze the O 1s spectrum of a battery electrode.

Discuss:

• Surface oxide formation
• Oxygen-containing species
• Electrochemical reactions
• SEI formation
• Effects on battery performance

Prepare a publication-ready interpretation.

Prompt 28 – Correlation with FTIR and Raman

Interpret the O 1s spectrum together with FTIR and Raman spectroscopy.

Explain how all three techniques support the identification of oxygen-containing functional groups and structural evolution.

Write in academic English suitable for a Q1 journal.

Prompt 29 – Reviewer Response

Act as an experienced XPS reviewer.

A reviewer questioned the assignment of the O 1s peaks.

Using the fitted peak positions:

[Insert Peak Positions]

Prepare a professional reviewer response explaining the assignments and supporting the interpretation.

Prompt 30 – Advanced O 1s Discussion

Act as an internationally recognized XPS scientist.

Interpret the O 1s spectrum of:

[Insert Material]

Synthesis Method:

[Insert Method]

Peak Positions:

[Insert Components]

Discuss:

• Oxygen species
• Surface chemistry
• Oxidation mechanism
• Defect formation
• Surface functionalization
• Correlation with XRD, FTIR, Raman, and SEM
• Influence on the material's physical and chemical properties

Write a publication-ready Results and Discussion section suitable for Applied Surface Science or ACS Applied Materials & Interfaces.

These prompts help researchers move beyond simple O 1s peak assignments by generating comprehensive discussions that connect oxygen chemistry with synthesis methods, surface modification, defect engineering, and the functional performance of advanced materials.

N 1s Prompts (31–40)

The N 1s high-resolution XPS spectrum is essential for investigating nitrogen-containing materials, including nitrogen-doped carbons, MXenes, MOFs, polymers, catalysts, biomaterials, corrosion inhibitors, and battery electrodes. Proper interpretation of N 1s spectra provides insights into nitrogen configurations, doping mechanisms, coordination environments, catalytic active sites, and surface functionalization.

The following AI prompts are designed to help researchers produce comprehensive and publication-ready interpretations of N 1s XPS spectra.

Prompt 31 – Complete N 1s Interpretation

Act as an internationally recognized XPS spectroscopy expert.

Interpret the following N 1s XPS spectrum.

Peak fitting has already been completed.

Components:

[Insert Binding Energies]

Discuss:

• Chemical-state assignments
• Nitrogen configurations
• Surface chemistry
• Functional significance

Write a publication-ready Results and Discussion section.

Prompt 32 – Nitrogen Configuration Assignment

Interpret the fitted N 1s spectrum.

Assign each peak to the appropriate nitrogen species, including:

• Pyridinic nitrogen
• Pyrrolic nitrogen
• Graphitic (quaternary) nitrogen
• Oxidized nitrogen
• Amino groups
• Amide groups

Explain the evidence supporting each assignment.

Prompt 33 – Nitrogen-Doped Carbon Materials

Analyze the N 1s spectrum of nitrogen-doped carbon.

Discuss:

• Nitrogen doping mechanism
• Relative abundance of nitrogen species
• Structural evolution
• Influence on electrical conductivity
• Catalytic activity

Prepare a publication-ready discussion.

Prompt 34 – MXene Surface Chemistry

Interpret the N 1s XPS spectrum of nitrogen-functionalized MXene.

Discuss:

• Surface nitrogen species
• Chemical bonding
• Nitrogen incorporation mechanism
• Influence on electrochemical performance

Correlate the results with the synthesis method.

Prompt 35 – Catalyst Active Sites

Analyze the N 1s spectrum of a nitrogen-containing catalyst.

Explain:

• Active nitrogen species
• Metal–nitrogen coordination (if applicable)
• Catalytic active sites
• Expected influence on catalytic performance

Write in the style of Applied Catalysis B: Environmental.

Prompt 36 – Polymer Surface Modification

Interpret the N 1s spectrum before and after surface functionalization of a polymer.

Discuss:

• New nitrogen-containing functional groups
• Surface activation
• Chemical modification
• Expected effects on adhesion and wettability

Prompt 37 – Comparative N 1s Analysis

Compare the N 1s spectra of Sample A and Sample B.

Discuss:

• Peak shifts
• Relative peak area changes
• Nitrogen configuration evolution
• Surface chemistry modifications

Prepare a publication-ready comparison.

Prompt 38 – Correlation with FTIR and Raman

Interpret the N 1s spectrum together with FTIR and Raman spectroscopy.

Explain how all three techniques support the identification of nitrogen-containing functional groups and structural evolution.

Write in professional academic English.

Prompt 39 – Reviewer Response

Act as an experienced XPS reviewer.

A reviewer questioned the assignment of the N 1s peaks.

Using the following fitted peak positions:

[Insert Peak Positions]

Prepare a professional reviewer response that justifies each nitrogen assignment according to accepted XPS principles.

Prompt 40 – Advanced Publication-Ready Discussion

Act as an internationally recognized XPS scientist.

Interpret the following N 1s spectrum.

Material:

[Insert Material]

Synthesis Method:

[Insert Method]

Peak Positions:

[Insert Components]

Discuss:

• Nitrogen configurations
• Surface chemistry
• Doping mechanism
• Electronic structure modification
• Correlation with XRD, FTIR, Raman, SEM, and electrochemical measurements
• Expected influence on material performance

Write a publication-ready Results and Discussion section suitable for ACS Applied Materials & Interfaces or Applied Surface Science.

These prompts help researchers generate high-quality interpretations of N 1s spectra by linking nitrogen chemistry with synthesis conditions, electronic structure, catalytic behavior, and overall material performance, producing discussions suitable for publication in leading materials science journals.

Transition Metal XPS Prompts (41–50)

Transition metals such as Fe, Co, Ni, Cu, Mn, Cr, Ti, V, Mo, W, Zn, and Ce are among the most challenging elements to interpret by XPS because their spectra often contain multiple oxidation states, spin–orbit splitting, multiplet splitting, shake-up satellites, and overlapping peaks. Correct interpretation requires both careful peak fitting and a solid understanding of transition-metal chemistry.

The following AI prompts are designed to help researchers generate publication-ready discussions for transition-metal XPS spectra.

Prompt 41 – Complete Transition Metal Interpretation

Act as an internationally recognized XPS spectroscopy expert.

Interpret the high-resolution XPS spectrum of the following transition metal:

Element:
[Insert Element]

Peak fitting has already been completed.

Peak Positions:

[Insert Binding Energies]

Discuss:

• Oxidation states
• Chemical-state assignments
• Surface chemistry
• Scientific significance

Write a publication-ready Results and Discussion section.

Prompt 42 – Oxidation State Determination

Analyze the XPS spectrum and determine the oxidation states of the transition metal.

Explain the evidence supporting each oxidation state using:

• Binding energies
• Spin–orbit splitting
• Satellite peaks
• Literature comparison

Prepare the discussion for publication.

Prompt 43 – Before and After Treatment

Compare the transition-metal XPS spectra before and after treatment.

Discuss:

• Peak shifts
• Oxidation-state evolution
• Relative peak-area changes
• Surface chemical reactions
• Influence of the treatment process

Write in academic English suitable for a Q1 journal.

Prompt 44 – Spin–Orbit Splitting Analysis

Interpret the spin–orbit splitting observed in the XPS spectrum.

Explain:

• 2p3/2 and 2p1/2 peaks
• Peak separation
• Area ratios
• Chemical-state assignments
• Scientific significance

Prompt 45 – Satellite Peak Interpretation

Interpret the satellite peaks observed in the transition-metal XPS spectrum.

Discuss:

• Shake-up satellites
• Multiplet splitting
• Oxidation-state confirmation
• Electronic structure
• Surface chemistry

Explain how these satellites support the peak assignments.

Prompt 46 – Transition Metal Oxides

Interpret the XPS spectrum of a transition-metal oxide.

Discuss:

• Metal oxidation states
• Surface hydroxylation
• Oxygen vacancies
• Defect chemistry
• Expected influence on catalytic or electrochemical performance

Prepare a publication-ready discussion.

Prompt 47 – Correlation with XRD and Raman

Interpret the transition-metal XPS spectrum together with XRD and Raman spectroscopy.

Explain how all three techniques support:

• Phase identification
• Oxidation states
• Surface chemistry
• Structural evolution

Write in professional scientific English.

Prompt 48 – Thin Film Analysis

Analyze the transition-metal XPS spectrum of a thin film.

Discuss:

• Surface oxidation
• Chemical-state evolution
• Film quality
• Interface chemistry
• Effects of deposition parameters

Prepare a Results and Discussion section suitable for Surface and Coatings Technology.

Prompt 49 – Reviewer Response

Act as an experienced XPS reviewer.

The reviewer questioned the oxidation-state assignments of the transition metal.

Using the fitted peak positions and satellite peaks,

prepare a professional reviewer response that justifies the assignments according to accepted XPS principles.

Prompt 50 – Advanced Publication-Ready Interpretation

Act as an internationally recognized XPS scientist.

Interpret the following transition-metal XPS spectrum.

Material:
[Insert Material]

Transition Metal:
[Insert Element]

Synthesis Method:
[Insert Method]

Peak Positions:
[Insert Peaks]

Discuss:

• Oxidation states
• Chemical-state evolution
• Surface chemistry
• Defect formation
• Electronic structure
• Correlation with XRD, FTIR, Raman, SEM, TEM, and electrochemical measurements
• Influence on material performance

Write a publication-ready Results and Discussion section suitable for Applied Surface Science or ACS Applied Materials & Interfaces.

These prompts are suitable for virtually all transition-metal systems—including Fe, Co, Ni, Cu, Mn, Cr, Ti, V, Mo, W, Zn, Ce, Zr, Nb, Ta, Ag, Au, Pt, and Pd—and help researchers generate scientifically rigorous interpretations that go beyond simple oxidation-state assignments by connecting XPS results with structure, synthesis, and material performance.

Catalyst XPS Prompts (51–60)

XPS is one of the most powerful characterization techniques for heterogeneous catalysts because it provides direct information about surface elemental composition, oxidation states, active sites, electronic structure, oxygen vacancies, metal–support interactions, and catalyst deactivation. Since catalytic reactions occur primarily on the surface, XPS plays a crucial role in understanding catalytic mechanisms and optimizing catalyst performance.

The following AI prompts are designed specifically for researchers working on catalysts, photocatalysts, electrocatalysts, and supported metal catalysts.

Prompt 51 – Complete Catalyst XPS Interpretation

Act as an internationally recognized catalyst characterization expert.

Interpret the XPS spectra of the following catalyst.

Material:
[Insert Catalyst]

Available spectra:

• Survey
• [Insert Core Levels]

Peak fitting has already been completed.

Discuss:

• Surface composition
• Oxidation states
• Active catalytic species
• Surface chemistry
• Scientific significance

Write a publication-ready Results and Discussion section.

Prompt 52 – Active Site Identification

Analyze the XPS spectra and identify the possible catalytic active sites.

Discuss:

• Surface oxidation states
• Defect sites
• Surface functional groups
• Electronic structure
• Their expected role in catalytic performance.

Prompt 53 – Metal–Support Interaction

Interpret the XPS results to evaluate the interaction between the active metal and the catalyst support.

Discuss:

• Binding-energy shifts
• Charge transfer
• Electronic interaction
• Surface stabilization
• Influence on catalytic activity.

Prompt 54 – Oxygen Vacancy Analysis

Interpret the O 1s and metal core-level spectra.

Determine whether oxygen vacancies are present.

Explain:

• Evidence from XPS
• Defect formation mechanism
• Influence on catalytic activity
• Relationship with synthesis conditions.

Prompt 55 – Fresh vs. Used Catalyst

Compare the XPS spectra of fresh and spent catalysts.

Discuss:

• Oxidation-state evolution
• Surface contamination
• Catalyst deactivation
• Coke deposition
• Surface reconstruction
• Performance degradation.

Prompt 56 – Photocatalyst Interpretation

Interpret the XPS spectra of a photocatalyst.

Discuss:

• Surface oxidation states
• Oxygen vacancies
• Defect engineering
• Charge separation
• Surface electronic structure
• Expected influence on photocatalytic efficiency.

Prepare the discussion for publication.

Prompt 57 – Electrocatalyst Analysis

Interpret the XPS spectra of an electrocatalyst.

Discuss:

• Surface chemical states
• Active sites
• Electronic structure
• Charge-transfer characteristics
• Expected ORR/OER/HER performance

Correlate the results with electrochemical measurements.

Prompt 58 – Correlation with Catalytic Performance

Interpret the XPS spectra together with catalytic performance data.

Explain how the observed oxidation states and surface composition influence:

• Conversion
• Selectivity
• Stability
• Reaction mechanism

Write in the style of Applied Catalysis B or ACS Catalysis.

Prompt 59 – Reviewer Response

Act as an experienced catalyst researcher and journal reviewer.

The reviewer questioned the XPS interpretation of the catalyst.

Using the fitted peak positions,

prepare a professional reviewer response that justifies the oxidation-state assignments and explains their relationship to catalytic performance.

Prompt 60 – Advanced Catalyst Discussion

Act as an internationally recognized XPS and catalysis expert.

Interpret the XPS spectra of:

[Insert Catalyst]

Synthesis Method:

[Insert Method]

Available Characterization:

• XPS
• XRD
• FTIR
• Raman
• SEM
• TEM
• BET
• Catalytic Performance Data

Discuss:

• Surface composition
• Active catalytic species
• Oxidation states
• Oxygen vacancies
• Metal–support interaction
• Electronic structure
• Reaction mechanism
• Correlation with catalytic activity
• Structure–performance relationship

Write a publication-ready Results and Discussion section suitable for ACS Catalysis, Applied Catalysis B: Environmental, or Journal of Catalysis.

These prompts are applicable to a wide range of catalytic materials, including metal nanoparticles, transition-metal oxides, MOFs, MXenes, zeolites, perovskites, single-atom catalysts, supported noble metals, photocatalysts, electrocatalysts, and biomass-derived catalysts. They help researchers move beyond simple peak assignments by linking XPS results to catalytic mechanisms, active-site chemistry, and overall catalyst performance.

MOF & MOF-Based Materials XPS Prompts (61–70)

Metal–Organic Frameworks (MOFs) and MOF-derived materials are among the fastest-growing classes of advanced functional materials. XPS plays a crucial role in investigating metal coordination environments, ligand chemistry, oxidation states, heteroatom doping, defect formation, post-synthetic modification, and MOF-derived carbon materials.

The following prompts are specifically designed for researchers working with MOFs, MOF composites, MOF-derived catalysts, and hybrid nanostructures.

Prompt 61 – Complete MOF XPS Interpretation

Act as an internationally recognized XPS and MOF characterization expert.

Interpret the XPS spectra of the following MOF.

Material:
[Insert MOF Name]

Available spectra:

• Survey
• [Insert Core Levels]

Peak fitting has already been completed.

Discuss:

• Surface elemental composition
• Metal oxidation states
• Ligand chemistry
• Coordination environment
• Surface functional groups

Write a publication-ready Results and Discussion section.

Prompt 62 – Metal Coordination Analysis

Interpret the XPS spectra to investigate the coordination environment of the metal centers in this MOF.

Discuss:

• Metal oxidation states
• Metal–ligand coordination
• Electronic structure
• Stability of the framework
• Scientific significance

Prompt 63 – Organic Ligand Interpretation

Interpret the C 1s, O 1s and N 1s spectra of the MOF.

Discuss:

• Organic linker chemistry
• Functional groups
• Coordination with metal ions
• Surface functionalization
• Structural integrity of the framework

Prompt 64 – MOF Composite Analysis

Interpret the XPS spectra of a MOF-based composite.

Explain:

• Interaction between MOF and secondary material
• Chemical bonding
• Charge transfer
• Surface chemistry
• Evidence of successful composite formation

Prompt 65 – MOF-Derived Carbon Materials

Analyze the XPS spectra of a MOF-derived carbon material.

Discuss:

• Carbon structure
• Nitrogen doping
• Residual metal species
• Oxygen functional groups
• Surface chemistry
• Expected catalytic or electrochemical properties

Prompt 66 – Post-Synthetic Modification

Compare the XPS spectra before and after post-synthetic modification of the MOF.

Discuss:

• Peak shifts
• Surface functionalization
• Coordination changes
• New chemical bonds
• Surface composition evolution

Prepare a publication-ready discussion.

Prompt 67 – Adsorption Mechanism

Interpret the XPS spectra before and after adsorption.

Explain:

• Surface interactions
• Binding mechanism
• Chemical-state changes
• Adsorption sites
• Evidence supporting the adsorption mechanism

Prompt 68 – Catalytic MOFs

Interpret the XPS spectra of a catalytic MOF.

Discuss:

• Active metal species
• Oxidation states
• Surface electronic structure
• Active catalytic sites
• Correlation with catalytic performance

Write in the style of ACS Catalysis.

Prompt 69 – Correlation with Other Characterization Techniques

Interpret the XPS spectra together with:

• XRD
• FTIR
• Raman spectroscopy
• BET
• SEM
• TEM

Explain how all characterization techniques collectively confirm:

• Framework formation
• Surface chemistry
• Structural stability
• Material performance

Write a coherent scientific discussion suitable for publication.

Prompt 70 – Advanced MOF Discussion

Act as an internationally recognized MOF and XPS expert.

Interpret the XPS spectra of:

[Insert Material]

Synthesis Method:

[Insert Method]

Discuss:

• Metal oxidation states
• Ligand coordination
• Surface chemistry
• Electronic structure
• Defect formation
• Framework stability
• Surface functionalization
• Correlation with XRD, FTIR, Raman, BET, SEM, TEM, and electrochemical measurements
• Structure–property relationship

Write a publication-ready Results and Discussion section suitable for Chemical Engineering Journal, ACS Applied Materials & Interfaces, Advanced Functional Materials, or Journal of Materials Chemistry A.

These prompts are suitable for virtually all MOF families, including ZIFs, UiO-series, MIL-series, HKUST-1, MOF-5, PCNs, Prussian Blue Analogues (PBAs), MOF-derived carbons, MOF-based composites, and hybrid MOF nanostructures. They help researchers connect XPS-derived surface chemistry with framework structure, coordination environment, adsorption behavior, catalysis, and electrochemical performance, producing comprehensive discussions suitable for publication in leading materials science and chemistry journals.

MXene XPS Prompts (71–80)

MXenes are a rapidly expanding family of two-dimensional transition metal carbides, nitrides, and carbonitrides with exceptional applications in energy storage, electromagnetic shielding, catalysis, corrosion protection, sensors, water purification, and biomedical engineering. Because MXenes possess abundant surface terminations (–O, –OH, –F), XPS is one of the most important techniques for understanding their chemistry.

The following prompts are specifically designed for researchers working on pristine MXenes, modified MXenes, MXene composites, and functionalized MXene-based materials.

Prompt 71 – Complete MXene XPS Interpretation

Act as an internationally recognized MXene and XPS expert.

Interpret the XPS spectra of the following MXene.

Material:
[Insert MXene]

Available spectra:

• Survey
• Ti 2p (or other transition metal)
• C 1s
• O 1s
• F 1s

Peak fitting has already been completed.

Discuss:

• Surface composition
• Surface terminations
• Oxidation states
• Surface chemistry
• Scientific significance

Write a publication-ready Results and Discussion section.

Prompt 72 – Surface Termination Analysis

Interpret the XPS spectra to identify the surface terminations of the MXene.

Discuss the evidence for:

• –O termination
• –OH termination
• –F termination
• Surface oxidation
• Surface functionalization

Explain how these terminations influence material properties.

Prompt 73 – Etching Efficiency

Evaluate the XPS spectra to determine whether MAX phase etching was successful.

Discuss:

• Removal of the A-layer element
• Formation of MXene
• Remaining impurities
• Surface chemistry
• Evidence supporting successful synthesis.

Prompt 74 – Oxidation Stability

Compare the XPS spectra of fresh and aged MXene.

Discuss:

• Surface oxidation
• Formation of TiO₂ (or other oxides)
• Changes in surface terminations
• Stability of the MXene
• Implications for long-term applications.

Prompt 75 – Functionalized MXenes

Interpret the XPS spectra before and after surface functionalization of the MXene.

Discuss:

• New functional groups
• Chemical bonding
• Surface modification
• Evidence supporting successful functionalization
• Expected influence on material performance.

Prompt 76 – MXene Composite Analysis

Interpret the XPS spectra of a MXene-based composite.

Discuss:

• Interaction between MXene and the secondary material
• Charge transfer
• Chemical bonding
• Surface chemistry
• Electronic structure

Write a publication-ready discussion.

Prompt 77 – Electrochemical Applications

Interpret the XPS spectra of a MXene electrode used in batteries or supercapacitors.

Discuss:

• Surface oxidation states
• Surface terminations
• Electronic structure
• Ion storage mechanism
• Correlation with electrochemical performance.

Prompt 78 – Correlation with Other Characterization Techniques

Interpret the XPS spectra together with:

• XRD
• Raman spectroscopy
• FTIR
• SEM
• TEM
• AFM

Explain how all techniques collectively confirm:

• MXene formation
• Surface chemistry
• Structural evolution
• Material performance

Prepare a publication-ready discussion.

Prompt 79 – Reviewer Response

Act as an experienced MXene researcher and XPS reviewer.

A reviewer questioned the XPS interpretation of the MXene.

Using the fitted peak positions,

prepare a professional reviewer response explaining:

• Surface terminations
• Oxidation states
• Chemical-state assignments
• Evidence supporting the conclusions.

Prompt 80 – Advanced MXene Discussion

Act as an internationally recognized MXene and XPS expert.

Interpret the XPS spectra of:

[Insert MXene]

Synthesis Method:

[Insert Method]

Available Characterization:

• XPS
• XRD
• Raman
• FTIR
• SEM
• TEM
• AFM
• Electrochemical Measurements

Discuss:

• Surface terminations
• Oxidation states
• Electronic structure
• Surface oxidation
• Functionalization mechanism
• Structure–property relationship
• Correlation with electrochemical performance
• Scientific significance

Write a publication-ready Results and Discussion section suitable for ACS Nano, Advanced Functional Materials, Small, Nano Energy, or Chemical Engineering Journal.

These prompts are applicable to virtually all MXene families, including Ti₃C₂Tₓ, Ti₂CTₓ, Nb₂CTₓ, Nb₄C₃Tₓ, V₂CTₓ, Mo₂CTₓ, Mo₂TiC₂Tₓ, Ta₄C₃Tₓ, and their composites with MOFs, graphene, CNTs, metal oxides, polymers, hydrogels, and biomaterials. They are designed to help researchers move beyond simple peak assignments by connecting XPS-derived surface chemistry with synthesis, functionalization, electronic structure, and application-specific performance.

Polymer & Polymer Composite XPS Prompts (81–90)

XPS is one of the most valuable surface characterization techniques for polymers because it provides detailed information about surface functional groups, oxidation, plasma treatment, grafting reactions, coating adhesion, aging, degradation, and interfacial chemistry. Since many polymer applications depend on surface properties rather than bulk composition, XPS is widely used in coatings, biomedical materials, adhesives, packaging, membranes, and polymer nanocomposites.

The following AI prompts are specifically designed for polymer scientists and engineers.

Prompt 81 – Complete Polymer XPS Interpretation

Act as an internationally recognized XPS expert specializing in polymer materials.

Interpret the XPS spectra of the following polymer.

Material:
[Insert Polymer]

Available spectra:

• Survey
• C 1s
• O 1s
• N 1s (if available)

Peak fitting has already been completed.

Discuss:

• Surface composition
• Functional groups
• Surface chemistry
• Chemical modifications
• Scientific significance

Write a publication-ready Results and Discussion section.

Prompt 82 – Plasma Surface Modification

Interpret the XPS spectra of a polymer before and after plasma treatment.

Discuss:

• New oxygen-containing groups
• Nitrogen incorporation (if applicable)
• Surface activation
• Surface oxidation
• Chemical bonding
• Expected improvement in wettability and adhesion

Prepare a publication-ready discussion.

Prompt 83 – Polymer Functionalization

Analyze the XPS spectra before and after chemical functionalization of the polymer.

Discuss:

• New functional groups
• Surface grafting
• Chemical-state changes
• Surface modification mechanism
• Evidence supporting successful functionalization.

Prompt 84 – Polymer Nanocomposites

Interpret the XPS spectra of a polymer nanocomposite.

Discuss:

• Polymer–nanoparticle interaction
• Chemical bonding
• Surface chemistry
• Charge transfer
• Interfacial compatibility
• Expected influence on mechanical and thermal properties.

Prompt 85 – Surface Aging and Degradation

Compare the XPS spectra before and after environmental aging of the polymer.

Discuss:

• Surface oxidation
• Chain degradation
• Formation of oxygen-containing functional groups
• Chemical-state evolution
• Aging mechanism.

Prompt 86 – Coating Adhesion Analysis

Interpret the XPS spectra of a polymer coating deposited on a metallic substrate.

Discuss:

• Surface chemistry
• Interfacial bonding
• Adhesion mechanism
• Surface contamination
• Evidence supporting coating quality.

Prompt 87 – Biomedical Polymer Analysis

Interpret the XPS spectra of a biomedical polymer.

Discuss:

• Surface functional groups
• Biocompatibility
• Protein adsorption behavior
• Surface modification
• Expected biological performance.

Prompt 88 – Correlation with FTIR

Interpret the XPS spectra together with FTIR results.

Explain how both techniques confirm:

• Functional groups
• Surface chemistry
• Chemical modification
• Polymer structure

Write a publication-ready scientific discussion.

Prompt 89 – Reviewer Response

Act as an experienced polymer scientist and XPS reviewer.

A reviewer questioned the interpretation of the polymer XPS spectra.

Using the fitted peak positions,

prepare a professional reviewer response explaining:

• Functional-group assignments
• Surface chemistry
• Evidence supporting the conclusions.

Prompt 90 – Advanced Polymer Discussion

Act as an internationally recognized polymer characterization expert.

Interpret the XPS spectra of:

[Insert Polymer]

Synthesis Method:

[Insert Method]

Available Characterization:

• XPS
• FTIR
• Raman
• SEM
• AFM
• Contact Angle
• Mechanical Testing
• Thermal Analysis

Discuss:

• Surface functional groups
• Chemical-state evolution
• Surface modification mechanism
• Polymer–filler interaction
• Surface energy
• Adhesion mechanism
• Structure–property relationship
• Correlation with complementary characterization techniques

Write a publication-ready Results and Discussion section suitable for Polymer, Composites Part B, ACS Applied Polymer Materials, or Progress in Organic Coatings.

These prompts are applicable to a broad range of polymer systems, including epoxy resins, polyethylene (PE), polypropylene (PP), polystyrene (PS), PVC, PET, PTFE, PMMA, PEEK, polyurethane (PU), PDMS, chitosan, alginate, cellulose, hydrogels, biodegradable polymers, conductive polymers, and polymer nanocomposites. They help researchers connect XPS-derived surface chemistry with functionalization, aging, interfacial interactions, adhesion, and overall material performance, resulting in publication-quality scientific discussions.

Biomaterials & Biomedical XPS Prompts (91–100)

XPS is one of the most important surface characterization techniques in biomaterials research because biological interactions occur primarily at the material surface. Whether developing implants, tissue-engineering scaffolds, wound dressings, drug-delivery systems, hydrogels, or antibacterial coatings, XPS helps researchers understand surface chemistry, biofunctionalization, protein adsorption, cell attachment, degradation mechanisms, and biocompatibility.

The following AI prompts are designed specifically for biomaterials and biomedical applications.

Prompt 91 – Complete Biomaterial XPS Interpretation

Act as an internationally recognized biomaterials and XPS expert.

Interpret the XPS spectra of the following biomaterial.

Material:
[Insert Material]

Available spectra:

• Survey
• C 1s
• O 1s
• N 1s
• Ca 2p (if available)
• P 2p (if available)

Peak fitting has already been completed.

Discuss:

• Surface composition
• Functional groups
• Surface chemistry
• Bioactive components
• Scientific significance

Write a publication-ready Results and Discussion section.

Prompt 92 – Surface Functionalization

Interpret the XPS spectra before and after biomolecule immobilization.

Discuss:

• Formation of new chemical bonds
• Surface functional groups
• Successful grafting
• Evidence of biofunctionalization
• Expected biological performance.

Prompt 93 – Protein Adsorption Analysis

Analyze the XPS spectra before and after protein adsorption.

Discuss:

• Nitrogen enrichment
• Carbon chemistry
• Surface functional groups
• Evidence supporting protein adsorption
• Surface interaction mechanism.

Prompt 94 – Hydrogel Surface Chemistry

Interpret the XPS spectra of a hydrogel.

Discuss:

• Surface functional groups
• Crosslinking chemistry
• Hydrophilic groups
• Surface modification
• Correlation with swelling behavior and biocompatibility.

Prompt 95 – Bioactive Coating Analysis

Interpret the XPS spectra of a bioactive coating deposited on a metallic implant.

Discuss:

• Surface composition
• Calcium and phosphorus chemistry
• Bioactivity
• Surface functionalization
• Expected osseointegration performance.

Prompt 96 – Antibacterial Biomaterials

Interpret the XPS spectra of an antibacterial biomaterial.

Discuss:

• Surface chemistry
• Antibacterial functional groups
• Metal ion incorporation
• Surface oxidation states
• Correlation with antibacterial activity.

Prompt 97 – Biodegradation Study

Compare the XPS spectra before and after biodegradation.

Discuss:

• Surface oxidation
• Chemical degradation
• Functional-group evolution
• Surface composition changes
• Degradation mechanism.

Prompt 98 – Correlation with Biological Performance

Interpret the XPS spectra together with biological characterization results.

Available data:

• Cell viability
• Cell proliferation
• Antibacterial activity
• Protein adsorption
• Contact angle

Explain how the observed surface chemistry influences biological performance.

Prepare a publication-ready discussion.

Prompt 99 – Reviewer Response

Act as an experienced biomaterials researcher and journal reviewer.

A reviewer questioned the interpretation of the XPS spectra.

Using the fitted peak positions,

prepare a professional reviewer response explaining:

• Functional-group assignments
• Surface chemistry
• Evidence supporting biofunctionalization
• Biological significance.

Prompt 100 – Advanced Biomaterials Discussion

Act as an internationally recognized biomaterials and XPS expert.

Interpret the XPS spectra of:

[Insert Material]

Application:

[Insert Biomedical Application]

Available Characterization:

• XPS
• FTIR
• Raman
• SEM
• AFM
• Contact Angle
• Mechanical Testing
• Cell Viability
• Antibacterial Tests

Discuss:

• Surface chemistry
• Functional groups
• Biofunctionalization
• Surface modification mechanism
• Chemical-state evolution
• Correlation with biological performance
• Structure–property relationship
• Scientific significance

Write a publication-ready Results and Discussion section suitable for Biomaterials, Bioactive Materials, Acta Biomaterialia, Materials Science & Engineering C, or Journal of Biomedical Materials Research.

These prompts are suitable for a wide range of biomaterials, including hydrogels, chitosan, alginate, gelatin, collagen, silk fibroin, cellulose, bioactive glasses, hydroxyapatite, titanium implants, magnesium alloys, biodegradable polymers, tissue-engineering scaffolds, wound dressings, drug-delivery systems, antibacterial coatings, and nanobiomaterials. They help researchers transform XPS surface chemistry into meaningful biological insights by connecting chemical composition with protein adsorption, cell behavior, antibacterial performance, degradation mechanisms, and clinical functionality, resulting in high-quality, publication-ready scientific discussions.

Corrosion & Protective Coatings XPS Prompts (101–110)

XPS is one of the most powerful techniques for investigating corrosion mechanisms, passive films, protective coatings, inhibitor adsorption, oxide formation, and surface degradation. Since corrosion begins at the material surface, XPS provides direct evidence of oxidation states, corrosion products, passive-layer composition, inhibitor bonding, and coating chemistry.

The following prompts are specifically designed for researchers working in corrosion science, electrochemistry, and protective coatings.

Prompt 101 – Complete Corrosion XPS Interpretation

Act as an internationally recognized corrosion scientist and XPS expert.

Interpret the XPS spectra of the following corroded material.

Material:
[Insert Material]

Environment:
[Insert Corrosion Medium]

Available spectra:

• Survey
• Fe 2p (or other metal)
• O 1s
• C 1s
• Cl 2p (if available)

Peak fitting has already been completed.

Discuss:

• Corrosion products
• Oxidation states
• Surface chemistry
• Corrosion mechanism
• Scientific significance

Write a publication-ready Results and Discussion section.

Prompt 102 – Passive Film Characterization

Interpret the XPS spectra of the passive film formed on the metal surface.

Discuss:

• Passive-layer composition
• Oxide species
• Hydroxide species
• Film stability
• Corrosion resistance

Explain how the passive layer contributes to corrosion protection.

Prompt 103 – Corrosion Inhibitor Adsorption

Analyze the XPS spectra before and after corrosion inhibitor treatment.

Discuss:

• Adsorption mechanism
• Chemical bonding
• Surface coverage
• Functional groups
• Evidence supporting inhibitor adsorption

Prepare a publication-ready discussion.

Prompt 104 – Before and After Corrosion

Compare the XPS spectra of the metal before and after corrosion testing.

Discuss:

• Oxidation-state evolution
• Corrosion products
• Surface composition changes
• Surface contamination
• Corrosion mechanism

Write in the style of Corrosion Science.

Prompt 105 – Protective Coating Analysis

Interpret the XPS spectra of a protective coating deposited on a metallic substrate.

Discuss:

• Surface chemistry
• Coating composition
• Interfacial bonding
• Oxide formation
• Expected corrosion protection mechanism.

Prompt 106 – Marine Corrosion

Interpret the XPS spectra of a sample exposed to a chloride-containing environment.

Discuss:

• Chloride adsorption
• Corrosion products
• Passive film degradation
• Localized corrosion
• Pitting initiation

Prepare the discussion for publication.

Prompt 107 – Electrochemical Correlation

Interpret the XPS spectra together with electrochemical measurements.

Available data:

• EIS
• Potentiodynamic polarization
• OCP

Explain how the observed surface chemistry supports the electrochemical behavior and corrosion resistance.

Prompt 108 – High-Temperature Oxidation

Interpret the XPS spectra of a material after high-temperature oxidation.

Discuss:

• Oxide formation
• Oxidation states
• Surface stability
• Protective oxide layers
• Oxidation mechanism

Write a publication-ready discussion.

Prompt 109 – Reviewer Response

Act as an experienced corrosion researcher and XPS reviewer.

A reviewer questioned the interpretation of the XPS corrosion results.

Using the fitted peak positions,

prepare a professional reviewer response explaining:

• Oxidation-state assignments
• Corrosion products
• Surface chemistry
• Evidence supporting the corrosion mechanism.

Prompt 110 – Advanced Corrosion Discussion

Act as an internationally recognized corrosion scientist.

Interpret the XPS spectra of:

[Insert Material]

Corrosion Environment:

[Insert Environment]

Available Characterization:

• XPS
• XRD
• Raman
• FTIR
• SEM
• EDS
• EIS
• Polarization Curves

Discuss:

• Corrosion products
• Passive-film composition
• Oxidation states
• Surface chemistry
• Corrosion inhibition mechanism
• Coating performance
• Correlation with electrochemical measurements
• Structure–property relationship

Write a publication-ready Results and Discussion section suitable for Corrosion Science, Electrochimica Acta, Surface and Coatings Technology, or Progress in Organic Coatings.

These prompts are suitable for virtually all corrosion-related materials, including carbon steels, stainless steels, magnesium alloys, aluminum alloys, titanium alloys, nickel-based alloys, zinc coatings, conversion coatings, polymer coatings, ceramic coatings, nanocomposite coatings, corrosion inhibitors, and marine engineering materials. They help researchers connect XPS-derived surface chemistry with passive film formation, corrosion mechanisms, inhibitor adsorption, coating performance, and electrochemical behavior, producing comprehensive discussions suitable for publication in leading corrosion and surface engineering journals.

Battery & Energy Storage XPS Prompts (111–120)

XPS is one of the most important characterization techniques for lithium-ion batteries, sodium-ion batteries, potassium-ion batteries, zinc-ion batteries, aluminum-ion batteries, solid-state batteries, lithium–sulfur batteries, supercapacitors, and fuel cells. It provides valuable information about surface oxidation states, electrode chemistry, solid electrolyte interphase (SEI), electrolyte decomposition, ion storage mechanisms, and charge-transfer processes.

The following AI prompts are designed specifically for battery and energy-storage researchers.

Prompt 111 – Complete Battery XPS Interpretation

Act as an internationally recognized battery materials and XPS expert.

Interpret the XPS spectra of the following electrode material.

Material:
[Insert Material]

Battery Type:
[Insert Battery System]

Available spectra:

• Survey
• [Insert Core Levels]

Peak fitting has already been completed.

Discuss:

• Surface composition
• Oxidation states
• Surface chemistry
• Electrochemical significance

Write a publication-ready Results and Discussion section.

Prompt 112 – Charge–Discharge Mechanism

Interpret the XPS spectra collected before and after electrochemical cycling.

Discuss:

• Oxidation-state evolution
• Redox reactions
• Surface chemistry changes
• Ion storage mechanism
• Electrochemical reactions occurring during cycling

Prepare a publication-ready discussion.

Prompt 113 – SEI Layer Analysis

Analyze the XPS spectra of the electrode surface.

Determine the composition of the solid electrolyte interphase (SEI).

Discuss:

• Organic SEI species
• Inorganic SEI species
• Stability of the SEI
• Influence on battery performance

Prompt 114 – Cathode Material Interpretation

Interpret the XPS spectra of a cathode material.

Discuss:

• Transition-metal oxidation states
• Oxygen chemistry
• Surface degradation
• Electronic structure
• Influence on electrochemical performance

Write in the style of Journal of Power Sources.

Prompt 115 – Anode Material Interpretation

Interpret the XPS spectra of an anode material.

Discuss:

• Surface chemistry
• Carbon functional groups
• Surface oxidation
• Electrolyte decomposition
• Correlation with lithium or sodium storage mechanism

Prompt 116 – Before and After Cycling

Compare the XPS spectra of the electrode before and after 200 charge–discharge cycles.

Discuss:

• Oxidation-state changes
• SEI evolution
• Surface degradation
• Capacity fading mechanism
• Structural stability

Prompt 117 – Correlation with Electrochemical Measurements

Interpret the XPS spectra together with:

• Cyclic Voltammetry (CV)
• Galvanostatic Charge–Discharge (GCD)
• Electrochemical Impedance Spectroscopy (EIS)

Explain how the observed surface chemistry supports the electrochemical behavior.

Prepare a publication-ready discussion.

Prompt 118 – Heteroatom-Doped Carbon Electrodes

Interpret the XPS spectra of a heteroatom-doped carbon electrode.

Discuss:

• Nitrogen species
• Sulfur species
• Phosphorus species
• Oxygen-containing groups
• Their influence on ion storage and electrical conductivity.

Prompt 119 – Reviewer Response

Act as an experienced battery researcher and journal reviewer.

The reviewer questioned the interpretation of the XPS spectra.

Using the fitted peak positions,

prepare a professional reviewer response explaining:

• Oxidation-state assignments
• SEI composition
• Surface chemistry
• Electrochemical significance.

Prompt 120 – Advanced Battery Discussion

Act as an internationally recognized battery materials expert.

Interpret the XPS spectra of:

[Insert Electrode Material]

Battery System:

[Insert Battery Type]

Available Characterization:

• XPS
• XRD
• Raman
• FTIR
• SEM
• TEM
• EIS
• CV
• GCD

Discuss:

• Surface chemistry
• Oxidation states
• SEI formation
• Charge-storage mechanism
• Electronic structure
• Surface degradation
• Correlation with electrochemical performance
• Structure–property relationship

Write a publication-ready Results and Discussion section suitable for Journal of Power Sources, Nano Energy, Advanced Energy Materials, Energy Storage Materials, or ACS Energy Letters.

These prompts are suitable for virtually all energy-storage systems, including Li-ion, Na-ion, K-ion, Zn-ion, Al-ion, Mg-ion, Li–S, Li–O₂, solid-state batteries, supercapacitors, and hybrid capacitors, as well as electrode materials such as MXenes, MOFs, transition-metal oxides, phosphides, sulfides, carbides, nitrides, silicon, graphite, hard carbon, graphene, and biomass-derived carbons. They help researchers connect XPS-derived surface chemistry with electrochemical reactions, SEI evolution, charge-storage mechanisms, and long-term cycling performance, enabling publication-quality scientific discussions.

Thin Films & Coatings XPS Prompts (121–130)

XPS is one of the most important techniques for characterizing thin films, multilayer coatings, PVD/CVD coatings, oxide films, semiconductor films, magnetic coatings, optical coatings, and protective surface layers. Because XPS probes only the top few nanometers of a material, it provides critical information about surface composition, oxidation states, interface chemistry, contamination, coating quality, diffusion, and deposition mechanisms.

The following AI prompts are specifically designed for researchers working on thin films and advanced coatings.

Prompt 121 – Complete Thin Film Interpretation

Act as an internationally recognized XPS and thin-film characterization expert.

Interpret the XPS spectra of the following thin film.

Material:
[Insert Material]

Deposition Method:
[Insert Method]

Available spectra:

• Survey
• [Insert Core Levels]

Peak fitting has already been completed.

Discuss:

• Surface composition
• Oxidation states
• Surface chemistry
• Film quality
• Scientific significance

Write a publication-ready Results and Discussion section.

Prompt 122 – Effect of Deposition Parameters

Interpret the XPS spectra of thin films deposited under different processing conditions.

Discuss how deposition parameters influence:

• Surface composition
• Oxidation states
• Chemical bonding
• Film quality
• Surface chemistry

Prepare a publication-ready discussion.

Prompt 123 – Annealing Effects

Compare the XPS spectra of thin films before and after thermal annealing.

Discuss:

• Peak shifts
• Oxidation-state evolution
• Surface diffusion
• Chemical reactions
• Structural stability
• Expected influence on material properties.

Prompt 124 – Interface Chemistry

Interpret the XPS spectra to investigate the interface between the thin film and substrate.

Discuss:

• Chemical bonding
• Interfacial oxide formation
• Diffusion
• Surface contamination
• Adhesion mechanism

Write the discussion for publication.

Prompt 125 – Oxide Thin Films

Interpret the XPS spectra of an oxide thin film.

Discuss:

• Metal oxidation states
• Oxygen species
• Oxygen vacancies
• Surface defects
• Electronic structure

Explain how these characteristics influence the film performance.

Prompt 126 – Multilayer Coatings

Interpret the XPS spectra of a multilayer thin-film coating.

Discuss:

• Surface composition
• Layer interaction
• Diffusion between layers
• Interface chemistry
• Expected influence on coating performance.

Prompt 127 – Semiconductor Thin Films

Interpret the XPS spectra of a semiconductor thin film.

Discuss:

• Chemical states
• Surface defects
• Electronic structure
• Surface oxidation
• Influence on optical and electrical properties.

Prompt 128 – Correlation with Other Characterization Techniques

Interpret the XPS spectra together with:

• XRD
• Raman spectroscopy
• AFM
• SEM
• TEM
• UV–Vis spectroscopy

Explain how all characterization techniques collectively confirm:

• Film composition
• Crystal structure
• Surface chemistry
• Film quality

Prepare a publication-ready discussion.

Prompt 129 – Reviewer Response

Act as an experienced thin-film researcher and journal reviewer.

The reviewer questioned the XPS interpretation of the thin-film coating.

Using the fitted peak positions,

prepare a professional reviewer response explaining:

• Oxidation-state assignments
• Surface chemistry
• Interface reactions
• Evidence supporting the conclusions.

Prompt 130 – Advanced Thin Film Discussion

Act as an internationally recognized thin-film and XPS expert.

Interpret the XPS spectra of:

[Insert Thin Film]

Deposition Method:

[Insert Method]

Available Characterization:

• XPS
• XRD
• Raman
• SEM
• TEM
• AFM
• UV–Vis
• Contact Angle
• Electrical Measurements
• Magnetic Measurements (if available)

Discuss:

• Surface composition
• Oxidation states
• Chemical bonding
• Interface chemistry
• Surface oxidation
• Defect formation
• Structure–property relationship
• Correlation with complementary characterization techniques
• Influence on film performance

Write a publication-ready Results and Discussion section suitable for Surface and Coatings Technology, Thin Solid Films, Applied Surface Science, ACS Applied Materials & Interfaces, or Journal of Alloys and Compounds.

These prompts are suitable for virtually all thin-film systems, including PVD coatings, magnetron-sputtered films, CVD films, ALD coatings, sol–gel coatings, oxide thin films, nitride coatings, carbide coatings, semiconductor films, magnetic multilayers, optical coatings, DLC films, polymer coatings, and nanocomposite thin films. They help researchers connect XPS-derived surface chemistry with deposition conditions, interface reactions, microstructure, and functional properties, resulting in publication-quality scientific discussions suitable for leading materials science and surface engineering journals.

Comparative XPS Analysis Prompts (131–140)

Comparative XPS analysis is essential for understanding how composition, synthesis conditions, processing parameters, aging, functionalization, corrosion, cycling, or environmental exposure affect surface chemistry. Rather than interpreting a single spectrum, comparative analysis reveals chemical evolution, structure–property relationships, and performance mechanisms, making it one of the most valuable approaches for publication-quality discussions.

The following prompts are designed for systematic comparison of multiple XPS datasets.

Prompt 131 – Compare Two XPS Spectra

Act as an internationally recognized XPS expert.

Compare the XPS spectra of Sample A and Sample B.

Material:

[Insert Material]

Peak fitting has already been completed.

Discuss:

• Surface elemental composition
• Binding energy shifts
• Oxidation-state differences
• Surface chemistry evolution
• Scientific significance

Write a publication-ready comparative discussion.

Prompt 132 – Compare Multiple Samples

Interpret and compare the XPS spectra of the following samples:

• Sample 1
• Sample 2
• Sample 3
• Sample 4

Discuss:

• Surface composition changes
• Oxidation-state evolution
• Chemical-state differences
• Surface functional groups
• Structure–property relationship

Present the discussion in a publication-ready format.

Prompt 133 – Effect of Synthesis Parameters

Compare the XPS spectra of materials synthesized under different experimental conditions.

Explain how changing:

• Temperature
• Time
• pH
• Precursor concentration
• Calcination conditions

affects:

• Surface chemistry
• Oxidation states
• Surface composition
• Material performance.

Prompt 134 – Before vs. After Treatment

Compare the XPS spectra before and after surface treatment.

Possible treatments include:

• Annealing
• Plasma treatment
• Chemical modification
• Functionalization
• Acid/base treatment

Discuss:

• Chemical-state evolution
• Peak shifts
• Surface composition changes
• Functional-group formation

Prepare a publication-ready discussion.

Prompt 135 – Fresh vs. Aged Material

Compare the XPS spectra of fresh and aged samples.

Discuss:

• Surface oxidation
• Contamination
• Chemical degradation
• Oxidation-state evolution
• Stability

Explain how aging influences material performance.

Prompt 136 – Before and After Electrochemical Cycling

Compare the XPS spectra before and after electrochemical cycling.

Discuss:

• Surface reconstruction
• Oxidation-state changes
• SEI evolution (if applicable)
• Chemical degradation
• Correlation with electrochemical performance.

Prompt 137 – Before and After Corrosion

Compare the XPS spectra before and after corrosion exposure.

Discuss:

• Corrosion products
• Passive-film evolution
• Surface chemistry
• Oxidation-state changes
• Corrosion mechanism

Write in the style of Corrosion Science.

Prompt 138 – Correlation with Other Characterization Techniques

Compare the XPS results with:

• XRD
• FTIR
• Raman
• SEM
• TEM
• EDS
• BET

Discuss how all characterization techniques collectively explain the observed material behavior and verify the proposed mechanism.

Prompt 139 – Comparative Reviewer Response

Act as an experienced journal reviewer.

The reviewer requested a more detailed comparison between multiple XPS spectra.

Using the fitted peak positions,

prepare a professional reviewer response explaining:

• Chemical-state differences
• Binding-energy shifts
• Surface chemistry evolution
• Scientific interpretation

in a concise and convincing manner.

Prompt 140 – Advanced Comparative Discussion

Act as an internationally recognized XPS expert.

Compare the XPS spectra of multiple samples.

Available characterization:

• XPS
• XRD
• FTIR
• Raman
• SEM
• TEM
• AFM
• Electrochemical measurements (if available)

Discuss:

• Surface composition evolution
• Oxidation-state changes
• Chemical-state differences
• Surface functional groups
• Charge transfer
• Defect formation
• Structure–property relationship
• Correlation with complementary characterization techniques
• Mechanism responsible for the observed performance

Write a publication-ready Results and Discussion section suitable for high-impact journals such as ACS Applied Materials & Interfaces, Applied Surface Science, Chemical Engineering Journal, Advanced Functional Materials, or Journal of Materials Chemistry A.

These comparative prompts are applicable across virtually all classes of materials—including nanomaterials, catalysts, MOFs, MXenes, polymers, biomaterials, thin films, corrosion-resistant coatings, semiconductors, and battery electrodes. They are designed to help researchers move beyond isolated spectrum interpretation by identifying trends, explaining chemical evolution, correlating XPS with complementary characterization techniques, and constructing compelling, publication-quality scientific discussions.

Scientific Writing & Publication XPS Prompts (141–150)

Interpreting XPS data is only the first step. The real challenge for many researchers is transforming spectral analysis into clear, logical, publication-ready scientific writing. High-impact journals expect authors to explain surface chemistry, oxidation states, chemical bonding, and structure–property relationships rather than simply listing peak assignments.

The following prompts are designed to help researchers prepare manuscripts, reviewer responses, graphical abstracts, and publication-quality discussions.

Prompt 141 – Publication-Ready XPS Discussion

Act as an internationally recognized XPS expert and scientific writer.

Using the following XPS fitting results,

write a publication-ready Results and Discussion section suitable for a Q1 journal.

Requirements:

• Scientific writing style
• Logical flow
• Proper interpretation
• Structure–property relationship
• No repetition
• Avoid unsupported claims

Target journal:

[Insert Journal]

Prompt 142 – Reviewer Response

Act as an experienced journal reviewer.

The reviewer questioned our XPS interpretation.

Using the provided peak fitting,

prepare a professional reviewer response that:

• Justifies peak assignments
• Explains oxidation states
• Supports conclusions with scientific reasoning
• Uses a polite academic tone.

Prompt 143 – Improve Existing Discussion

Improve the following XPS discussion for publication in a high-impact journal.

Requirements:

• Improve scientific language
• Remove repetition
• Increase logical flow
• Add scientific interpretation
• Maintain technical accuracy

Text:

[Paste your discussion]

Prompt 144 – Figure Caption

Write a professional figure caption for the following XPS spectra.

Include:

• Material name
• Measured spectra
• Peak assignments
• Scientific significance

Target style:

ACS Applied Materials & Interfaces.

Prompt 145 – Results vs. Discussion Separation

Rewrite the following XPS interpretation by separating:

1. Results
2. Discussion

Ensure that the Results section only describes observations while the Discussion explains their scientific significance.

Prompt 146 – Journal Style Conversion

Rewrite this XPS discussion in the writing style of:

• Nature
• Advanced Functional Materials
• ACS Nano
• Chemical Engineering Journal
• Applied Surface Science

Maintain scientific accuracy while matching the journal style.

Prompt 147 – Abstract Integration

Using the XPS interpretation,

write two to three sentences suitable for inclusion in the manuscript abstract.

Focus on:

• Surface chemistry
• Key findings
• Scientific importance

Prompt 148 – Graphical Abstract Summary

Summarize the XPS findings in five concise bullet points suitable for preparing a graphical abstract or visual summary.

Highlight:

• Surface composition
• Oxidation states
• Chemical bonding
• Functional groups
• Performance relationship

Prompt 149 – Conclusion Based on XPS

Write a concise conclusion paragraph based on the XPS results.

Summarize:

• Major findings
• Surface chemistry
• Structure–property relationship
• Scientific significance

Limit to approximately 150 words.

Prompt 150 – Complete Publication Package

Act as an internationally recognized XPS expert, journal editor, and scientific writer.

Using the provided XPS results,

prepare a complete publication package including:

• Publication-ready Results section
• Scientific Discussion
• Figure caption
• Abstract summary
• Conclusion
• Reviewer response
• Suggested references to support the interpretation
• Recommendations for improving the manuscript

Target journal:

[Insert Journal]

These prompts are intended for researchers preparing manuscripts for leading journals such as ACS Applied Materials & Interfaces, Applied Surface Science, Chemical Engineering Journal, Advanced Functional Materials, Nano Energy, Corrosion Science, Journal of Power Sources, Surface and Coatings Technology, Biomaterials, and Journal of Materials Chemistry A. Rather than focusing only on spectral interpretation, they help convert XPS data into polished scientific writing, strengthen responses to reviewers, and improve the overall quality and publication readiness of a manuscript.

Universal & Advanced XPS AI Prompts (151–160)

Not every XPS project fits into a predefined category. Researchers often work on novel materials, hybrid nanostructures, multifunctional composites, interdisciplinary systems, or completely new applications where a flexible and comprehensive prompt is required.

The following universal prompts are designed to work with virtually any XPS dataset, regardless of the material or application. These prompts help transform raw XPS data into publication-quality scientific interpretation.

Prompt 151 – Universal XPS Interpretation

Act as an internationally recognized XPS expert with over 25 years of experience in materials characterization.

Interpret the XPS spectra of the following material.

Material:

[Insert Material]

Application:

[Insert Application]

Available spectra:

[Insert Core Levels]

Peak fitting has already been completed.

Discuss:

• Surface elemental composition
• Oxidation states
• Chemical bonding
• Surface functional groups
• Electronic structure
• Scientific significance

Write a publication-ready Results and Discussion section suitable for a Q1 journal.

Prompt 152 – AI Research Assistant

Act as my personal research assistant specializing in XPS analysis.

Analyze the following XPS results as if you are preparing them for publication.

Your discussion should:

• Explain every peak
• Justify oxidation-state assignments
• Identify possible errors
• Recommend additional characterization techniques
• Suggest references that should be cited
• Recommend improvements before journal submission.

Prompt 153 – Multi-Technique Interpretation

Interpret the XPS spectra together with all available characterization techniques.

Available techniques:

• XRD
• FTIR
• Raman
• SEM
• TEM
• AFM
• BET
• UV–Vis
• Electrochemical tests
• Mechanical tests

Explain how all results support each other.

Write a coherent publication-ready discussion.

Prompt 154 – Structure–Property Relationship

Interpret the XPS spectra by focusing on the relationship between:

• Surface chemistry
• Electronic structure
• Material properties
• Experimental performance

Rather than describing the peaks individually, explain how the observed chemistry determines the material's behavior.

Prompt 155 – Mechanism Development

Based on the XPS spectra,

develop a scientifically reasonable mechanism explaining:

• Surface reactions
• Chemical transformations
• Charge transfer
• Defect formation
• Material performance

Support every conclusion using XPS evidence.

Prompt 156 – Critical Evaluation

Critically evaluate my XPS interpretation.

Identify:

• Weak arguments
• Unsupported claims
• Missing explanations
• Incorrect peak assignments
• Alternative interpretations

Suggest specific improvements before manuscript submission.

Prompt 157 – Journal Reviewer Simulation

Act as a reviewer for a top-tier journal.

Review my XPS interpretation.

Identify every weakness that a reviewer might criticize regarding:

• Peak assignments
• Oxidation states
• References
• Scientific logic
• Discussion quality

Then suggest how to address each concern.

Prompt 158 – Literature Comparison

Compare my XPS results with published studies on similar materials.

Discuss:

• Similarities
• Differences
• Possible reasons for discrepancies
• Scientific novelty
• Positioning of the work within the existing literature

Suggest keywords and landmark papers to search for.

Prompt 159 – AI-Assisted Publication Enhancement

Improve my entire XPS Results and Discussion section.

Your tasks are to:

• Rewrite the text in fluent academic English
• Improve scientific logic
• Increase readability
• Remove redundancy
• Strengthen the discussion
• Add meaningful scientific insights
• Preserve all original scientific information

Target a high-impact SCI journal.

Prompt 160 – Ultimate XPS Master Prompt

Act as one of the world's leading experts in X-ray Photoelectron Spectroscopy (XPS), materials science, surface chemistry, and scientific writing.

Analyze the following XPS dataset comprehensively.

Material:

[Insert Material]

Application:

[Insert Application]

Available Characterization:

• XPS
• XRD
• FTIR
• Raman
• SEM
• TEM
• AFM
• BET
• UV–Vis
• Thermal analysis
• Mechanical testing
• Electrochemical measurements
• Any additional characterization

Peak fitting has already been completed.

Prepare a complete publication-quality interpretation including:

• Surface elemental composition
• Oxidation states
• Chemical bonding
• Surface functional groups
• Electronic structure
• Defect analysis
• Charge-transfer mechanism
• Structure–property relationship
• Correlation with all complementary characterization techniques
• Mechanism explaining the observed performance
• Publication-ready Results and Discussion
• Figure caption
• Reviewer-response suggestions
• Suggested references and keywords for literature review
• Potential limitations of the interpretation
• Recommendations for strengthening the manuscript before submission

Write in the style of leading journals such as Nature Materials, Advanced Materials, ACS Nano, Advanced Functional Materials, Chemical Engineering Journal, or ACS Applied Materials & Interfaces.

These universal prompts are designed to be applicable to any XPS study, regardless of the material class or application. Whether the research involves nanomaterials, catalysts, MOFs, MXenes, polymers, biomaterials, thin films, corrosion-resistant coatings, semiconductors, batteries, or emerging hybrid systems, these prompts help researchers produce rigorous, publication-ready analyses. They also encourage critical evaluation, integration with complementary characterization techniques, and stronger scientific reasoning, making them valuable tools for manuscript preparation, peer-review responses, and AI-assisted research workflows.

9. 20 Expert XPS Prompt Templates

Although the previous section introduced 160 specialized AI prompts, many researchers prefer ready-to-use prompt templates that can be quickly customized for different projects. The following expert templates are designed for common XPS workflows encountered in academic research, industrial characterization, and journal publication.

Simply replace the placeholders with your own information before submitting the prompt to ChatGPT or AnalyzeTest AI.

Template 1 — Complete XPS Interpretation

Interpret the XPS spectra of my material.

Material:
[Material Name]

Available spectra:
[Survey, C 1s, O 1s, Metal Peaks...]

Peak fitting has already been completed.

Write a publication-ready discussion explaining:

• Surface composition
• Oxidation states
• Chemical bonding
• Functional groups
• Scientific significance

Template 2 — Compare Two Samples

Compare the XPS spectra of Sample A and Sample B.

Discuss:

• Binding energy shifts
• Oxidation-state changes
• Surface chemistry
• Possible reasons for the observed differences
• Relationship with material performance

Write in journal style.

Template 3 — Reviewer Response

A reviewer questioned my XPS interpretation.

Using the fitted peaks,

prepare a professional reviewer response that justifies every peak assignment using scientific reasoning.

Template 4 — Figure Caption

Write a professional figure caption for my XPS spectra suitable for publication in a Q1 journal.

Template 5 — Journal Discussion

Rewrite my XPS discussion in the writing style of ACS Applied Materials & Interfaces.

Improve logic, readability and scientific interpretation.

Template 6 — Peak Assignment

Assign every XPS peak.

Explain why each peak corresponds to a particular oxidation state and discuss possible overlapping peaks.

Template 7 — Structure–Property Relationship

Instead of only assigning peaks,

explain how the observed surface chemistry affects the physical, chemical or electrochemical properties of the material.

Template 8 — Multi-Technique Discussion

Interpret the XPS results together with XRD, FTIR, Raman, SEM and TEM.

Write one coherent scientific discussion suitable for publication.

Template 9 — Mechanism Development

Develop a reaction mechanism supported by the XPS results.

Explain every step based on the observed oxidation states and surface chemistry.

Template 10 — Critical Review

Critically review my XPS interpretation.

Identify weak arguments, unsupported claims and possible mistakes.

Suggest improvements before submission.

Template 11 — AI Journal Editor

Act as an editor for a high-impact journal.

Rewrite my XPS discussion to improve clarity, scientific accuracy and publication quality.

Template 12 — Literature Comparison

Compare my XPS results with published studies.

Identify similarities, differences and possible reasons.

Suggest references that should be cited.

Template 13 — Surface Chemistry Summary

Summarize the surface chemistry revealed by XPS in less than 250 words for inclusion in my Results section.

Template 14 — Abstract Writing

Write two concise sentences describing my XPS findings for the manuscript abstract.

Template 15 — Conclusion Writing

Write a publication-ready conclusion paragraph based solely on my XPS analysis.

Template 16 — AI Supervisor

Pretend you are my PhD supervisor.

Review my XPS interpretation and tell me everything that needs improvement before journal submission.

Template 17 — Conference Presentation

Summarize my XPS results into five presentation slides suitable for an international conference.

Template 18 — Graphical Abstract

Summarize my XPS findings into five concise bullet points suitable for a graphical abstract.

Template 19 — AI Discussion Generator

Generate a complete publication-ready XPS Results and Discussion section from my fitted peak positions.

Avoid repeating peak assignments.

Focus on scientific interpretation.

Template 20 — Ultimate XPS Prompt

Analyze my XPS spectra as if you are one of the world's leading XPS experts.

Provide:

• Peak assignments
• Oxidation states
• Surface chemistry
• Chemical bonding
• Structure–property relationship
• Mechanism
• Publication-ready discussion
• Reviewer response
• Figure caption
• Suggested references
• Suggestions for improving the manuscript

Write at the level expected by Nature Materials or Advanced Materials.

10. 20 Frequently Asked Questions (FAQs) About AI for XPS Analysis

Artificial intelligence is rapidly transforming the way researchers analyze XPS spectra. However, many scientists still have important questions regarding its capabilities, limitations, and best practices. Below are answers to some of the most common questions we receive from researchers using AnalyzeTest AI for XPS interpretation.

1. Can AI accurately interpret XPS spectra?

Yes—but only when used correctly. AI can identify chemical states, explain surface chemistry, compare spectra, and generate publication-quality discussions. However, it should work with properly processed and peak-fitted spectra, not raw experimental data.

2. Can AI perform XPS peak fitting or deconvolution?

No.

Peak fitting (deconvolution) requires scientific judgment regarding:

• Background selection
• Peak shape
• Peak width
• Peak constraints
• Chemical consistency

These decisions cannot currently be made reliably by AI alone.

At AnalyzeTest AI, peak fitting is performed manually by experienced XPS researchers before AI-assisted interpretation is generated.

3. Can ChatGPT replace an XPS expert?

No.

ChatGPT is an excellent scientific writing assistant and can explain XPS chemistry, but it cannot replace the expertise required for:

• Peak fitting
• Selecting appropriate fitting models
• Validating oxidation states
• Identifying fitting artifacts
• Instrument-specific data processing

4. Why do different AI tools sometimes provide different XPS interpretations?

AI models generate responses based on their training and the information provided in the prompt.

If the prompt lacks:

• Material information
• Experimental conditions
• Peak fitting results
• Complementary characterization data

the interpretation may be incomplete or even incorrect.

5. What information should I provide before asking AI to interpret XPS spectra?

The best results are obtained when you provide:

• Material name
• Synthesis method
• Application
• Peak fitting results
• Binding energies
• Peak assignments
• Experimental conditions
• Complementary characterization (XRD, FTIR, Raman, SEM, TEM, etc.)

6. Can AI determine oxidation states automatically?

AI can suggest likely oxidation states based on peak positions and published literature.

However, final confirmation should always consider:

• Chemical environment
• Satellite peaks
• Multiplet splitting
• Complementary characterization techniques
• Previous literature

7. Can AI identify surface functional groups from XPS?

Yes.

AI can interpret functional groups from high-resolution spectra such as:

• C 1s
• O 1s
• N 1s
• S 2p
• P 2p
• F 1s

provided that accurate peak fitting has already been completed.

8. Can AI compare multiple XPS spectra?

Absolutely.

AI performs particularly well when comparing:

• Before vs. after treatment
• Fresh vs. aged materials
• Different synthesis conditions
• Various dopant concentrations
• Electrochemical cycling
• Corrosion exposure

9. Can AI write publication-ready XPS discussions?

Yes.

One of the strongest applications of AI is transforming processed XPS data into:

• Results sections
• Scientific discussions
• Figure captions
• Reviewer responses
• Abstract summaries
• Conclusions

10. Can AI explain the relationship between XPS and material performance?

Yes.

Modern AI models can connect surface chemistry with:

• Catalytic activity
• Battery performance
• Corrosion resistance
• Wettability
• Mechanical properties
• Optical behavior
• Electrical conductivity

provided that sufficient experimental information is supplied.

11. Does AI know the latest XPS literature?

AI has broad scientific knowledge, but it may not always include the newest publications. For cutting-edge research, compare AI-generated interpretations with recent peer-reviewed articles and current databases.

12. Can AI help answer reviewers’ comments about XPS?

Yes.

AI can draft professional reviewer responses by explaining peak assignments, oxidation states, chemical-state changes, and the scientific reasoning behind your interpretation. Researchers should always verify the final response before submission.

13. Which XPS spectra are most suitable for AI interpretation?

AI works best with:

• Survey spectra
• High-resolution core-level spectra
• Peak-fitted spectra
• Comparative datasets (before/after treatment or multiple samples)

Raw spectra without proper processing provide much less reliable results.

14. Is AI useful for beginners learning XPS?

Absolutely.

AI can explain:

• Basic XPS principles
• Peak assignments
• Binding energy shifts
• Oxidation states
• Surface chemistry

making it an excellent educational tool for students and early-career researchers.

15. Can AI detect errors in my XPS interpretation?

Yes.

AI can often identify:

• Inconsistent oxidation-state assignments
• Unsupported conclusions
• Missing scientific explanations
• Weak logical arguments
• Areas requiring additional characterization

However, it should not replace expert review.

16. Can AI interpret XPS together with other characterization techniques?

Yes.

One of AI’s greatest strengths is integrating XPS with complementary techniques such as:

• XRD
• FTIR
• Raman
• SEM
• TEM
• AFM
• BET
• Electrochemical measurements
• Thermal analysis

to build a coherent scientific explanation.

17. What are the biggest mistakes researchers make when using AI for XPS?

Common mistakes include:

• Uploading raw spectra without peak fitting
• Providing incomplete experimental details
• Accepting AI output without verification
• Ignoring complementary characterization
• Assuming AI can perform deconvolution automatically

18. How is AnalyzeTest AI different from generic AI tools?

Unlike general-purpose AI chatbots, AnalyzeTest AI is designed specifically for materials characterization. It combines optimized prompts with domain expertise in XPS interpretation and, when needed, expert-assisted services such as manual peak fitting, publication-ready discussions, and reviewer-response preparation.

19. Can AnalyzeTest AI help with SCI journal publications?

Yes.

Many researchers use AnalyzeTest AI to prepare:

• Publication-ready Results and Discussion sections
• Reviewer responses
• Figure captions
• Abstract summaries
• Conclusions
• Scientific interpretations aligned with the expectations of high-impact journals.

20. When should I use AnalyzeTest AI instead of a generic AI chatbot?

If your goal is to produce accurate, publication-quality XPS interpretation rather than a generic explanation, AnalyzeTest AI offers a more specialized workflow. It is particularly valuable for researchers who need assistance connecting XPS results with complementary characterization, strengthening scientific discussions, and preparing manuscripts for peer-reviewed journals. For projects requiring reliable peak fitting and deconvolution, expert support from the AnalyzeTest team is also available, ensuring that AI-assisted interpretation is built on scientifically validated XPS data.

11. Why AnalyzeTest AI Is Different from Generic AI Tools

Artificial intelligence has made XPS interpretation faster and more accessible than ever before. General AI assistants such as ChatGPT, Gemini, Claude, and Copilot can generate explanations of XPS spectra, summarize scientific literature, and help improve academic writing. However, surface analysis is a highly specialized field, and obtaining a scientifically reliable interpretation requires much more than simply asking an AI model to explain a spectrum.

AnalyzeTest AI was developed specifically for researchers working in materials science, chemistry, nanotechnology, corrosion engineering, catalysis, biomaterials, batteries, polymers, and thin films. Rather than acting as a general chatbot, it focuses on solving real-world challenges encountered during XPS data interpretation and scientific publication.

Built Specifically for XPS Researchers

Unlike generic AI platforms that answer questions from almost every field, AnalyzeTest AI has been designed around the workflow of XPS analysis.

Researchers can request assistance with:

• Surface chemical-state interpretation
• Oxidation-state identification
• Functional group analysis
• Publication-ready Results & Discussion writing
• Comparative XPS interpretation
• Reviewer response preparation
• Structure–property relationship analysis
• Multi-technique scientific discussions

The responses are optimized for the language and expectations of scientific journals rather than general educational explanations.

AI Does Not Perform Peak Fitting—and Neither Does AnalyzeTest AI Automatically

One of the biggest misconceptions surrounding AI is that it can automatically perform XPS deconvolution.

It cannot.

Reliable XPS peak fitting requires expert decisions regarding:

• Background subtraction
• Peak shape selection
• Peak constraints
• Full width at half maximum (FWHM)
• Spin–orbit splitting
• Satellite peak treatment
• Chemical consistency

These decisions require scientific expertise and cannot be replaced by current AI models.

Instead of pretending otherwise, AnalyzeTest AI follows a scientifically rigorous approach:

• AI is used for interpretation, explanation, and scientific writing.
• Peak fitting is performed by experienced XPS specialists when expert assistance is requested.

This ensures that the interpretation is based on reliable chemical-state assignments rather than potentially incorrect automated fitting.

Designed for Scientific Publications

Most researchers are not simply looking for peak assignments—they need text suitable for publication.

AnalyzeTest AI helps generate:

• Publication-ready Results sections
• High-quality Discussion sections
• Figure captions
• Abstract summaries
• Conclusions
• Reviewer responses
• Journal-style scientific writing

The generated content follows the writing style expected by leading SCI journals.

Integration with Other Characterization Techniques

Scientific conclusions rarely rely on XPS alone.

AnalyzeTest AI can combine XPS interpretation with:

• XRD
• FTIR
• Raman spectroscopy
• SEM
• TEM
• AFM
• BET
• UV–Vis spectroscopy
• Electrochemical measurements
• Thermal analysis
• Mechanical testing

This integrated interpretation produces stronger scientific arguments and improves manuscript quality.

Optimized AI Prompts Developed by Researchers

The quality of AI output depends heavily on the quality of the prompt.

Instead of forcing researchers to spend hours learning prompt engineering, AnalyzeTest AI provides professionally designed prompts created specifically for XPS applications.

These prompts have been refined for:

• Nanomaterials
• Catalysts
• MOFs
• MXenes
• Polymers
• Biomaterials
• Thin films
• Corrosion science
• Batteries
• Surface coatings

This significantly improves both the accuracy and consistency of AI-generated interpretations.

Human Expertise When Needed

Artificial intelligence is an excellent assistant—but it is not a replacement for scientific expertise.

For challenging datasets, AnalyzeTest AI offers access to experienced researchers who can assist with:

• Manual XPS peak fitting
• Peak assignment verification
• Interpretation validation
• Reviewer-response preparation
• Manuscript improvement
• Complete publication-ready reports

This hybrid workflow combines the speed of AI with the reliability of expert scientific judgment.

Who Should Use AnalyzeTest AI?

AnalyzeTest AI is suitable for:

• Undergraduate students
• Master’s students
• PhD researchers
• Postdoctoral fellows
• University faculty
• Industrial R&D scientists
• Quality-control laboratories
• Materials characterization facilities

Whether you need a quick interpretation or a publication-ready discussion, the platform is designed to support every stage of the research process.

From Spectra to Scientific Publication

The ultimate goal of XPS analysis is not simply identifying peaks—it is understanding the material and communicating those findings clearly.

AnalyzeTest AI helps researchers move efficiently from processed XPS spectra to scientifically sound interpretations, well-written manuscripts, and high-quality journal submissions. By combining specialized AI workflows with expert knowledge when required, it provides a practical solution for researchers seeking accurate, publication-ready XPS analysis beyond the capabilities of generic AI chatbots.

12. Conclusion

Artificial intelligence is changing the way researchers analyze X-ray Photoelectron Spectroscopy (XPS) data. When combined with properly processed spectra and expert scientific judgment, AI can significantly accelerate interpretation, improve scientific writing, and reduce the time required to prepare publication-ready manuscripts.

Throughout this guide, you explored 160 specialized AI prompts, expert prompt templates, best practices for prompt engineering, common mistakes to avoid, and practical strategies for using AI in XPS research. Whether your work focuses on nanomaterials, catalysts, MXenes, polymers, biomaterials, corrosion, batteries, thin films, or advanced surface engineering, these prompts provide a solid foundation for generating more accurate, consistent, and insightful XPS interpretations.

However, it is important to remember that AI is an assistant—not a replacement for scientific expertise. Critical tasks such as peak fitting (deconvolution), background selection, constraint optimization, and validation of chemical-state assignments still require experienced XPS researchers. Reliable interpretation begins with high-quality data processing, and no AI model can currently replace the expert knowledge needed for rigorous peak fitting.

This is where AnalyzeTest AI provides a unique advantage. Rather than relying solely on generic AI responses, it combines specialized prompt engineering, materials characterization expertise, and optional expert-assisted XPS services to help researchers transform processed spectra into publication-quality scientific discussions. For projects requiring manual peak fitting, reviewer-response preparation, or complete interpretation reports, expert support is also available.

Whether you are preparing your first XPS manuscript or submitting to leading journals such as Applied Surface Science, ACS Applied Materials & Interfaces, Advanced Functional Materials, or Chemical Engineering Journal, using AI intelligently can improve both productivity and scientific communication.

If you want to go beyond generic AI answers and obtain research-focused XPS interpretation, explore AnalyzeTest AI to generate publication-ready discussions, compare spectra, strengthen reviewer responses, and accelerate your research workflow with AI designed specifically for materials characterization.

Ready to improve your XPS analysis? Upload your processed XPS spectra to AnalyzeTest AI and discover how specialized AI can help you move from raw surface chemistry data to high-quality scientific publications faster and more confidently.

Artificial Intelligence (AI) is rapidly transforming the way scientists analyze Fourier Transform Infrared (FTIR) spectra. Instead of spending hours manually assigning absorption bands, comparing literature, and writing publication-ready discussions, researchers can now use AI to accelerate the entire interpretation process. However, obtaining accurate and reliable results depends heavily on one critical factor: the quality of the prompt given to the AI model.

A well-designed prompt enables AI systems such as ChatGPT and other large language models to generate detailed functional group assignments, identify molecular structures, compare spectra, explain spectral changes after chemical modification, prepare publication-ready discussions, assist in reviewer responses, and even suggest possible reaction mechanisms. In contrast, vague or incomplete prompts often lead to generic, inaccurate, or scientifically weak interpretations.

As AI becomes an increasingly common research assistant in chemistry, materials science, nanotechnology, environmental engineering, pharmaceuticals, polymers, biomass conversion, corrosion science, and biomedical engineering, learning how to communicate effectively with AI has become an essential scientific skill.

This guide presents 100 carefully designed AI prompts for FTIR analysis, created specifically for researchers, graduate students, industrial laboratories, and scientific reviewers. These prompts are not generic AI questions—they are practical, research-oriented templates developed from real scientific workflows and inspired by thousands of published FTIR discussions across a wide range of disciplines.

Whether your objective is to identify functional groups, compare untreated and modified materials, analyze polymer composites, investigate adsorption mechanisms, characterize nanoparticles, interpret biomass-derived materials, or prepare a high-quality journal manuscript, these prompts will help you obtain more accurate, structured, and publication-ready responses from AI.

Why AI is Changing FTIR Interpretation

Traditional FTIR interpretation requires extensive knowledge of vibrational spectroscopy, functional group chemistry, molecular structure, and the existing scientific literature. Researchers often spend significant time searching reference papers, comparing characteristic absorption bands, and carefully writing scientific discussions that satisfy journal reviewers.

Artificial intelligence dramatically reduces this workload by combining literature knowledge, chemical reasoning, and natural language generation into a single workflow. When provided with sufficient experimental information—including the sample composition, synthesis method, experimental conditions, and observed FTIR peaks—AI can rapidly generate comprehensive scientific interpretations that would otherwise require hours of manual work.

Nevertheless, AI is only as good as the instructions it receives. The same FTIR spectrum can produce either an excellent scientific discussion or a poor-quality interpretation depending entirely on how the prompt is written.

That is exactly why this guide exists.

What You Will Learn in This Guide

In this comprehensive guide, you will discover how to use AI effectively for:

• FTIR peak assignment and functional group identification
• Publication-ready FTIR discussions
• Comparison of multiple FTIR spectra
• Polymer and composite characterization
• Nanomaterial analysis
• Biomass and biochar characterization
• Catalyst characterization
• Surface modification analysis
• Adsorption mechanism interpretation
• Reviewer response preparation
• Error detection in FTIR discussions
• Literature-style scientific writing
• AI-assisted hypothesis generation
• Automated report preparation

Each prompt has been designed to maximize the quality of AI-generated interpretations while minimizing vague or misleading responses.

Unlike generic prompt collections found online, the prompts presented here are specifically optimized for scientific spectroscopy, making them suitable for academic research, industrial laboratories, graduate theses, and high-impact journal publications.

Pro Tip: For the best results, always provide AI with detailed experimental information, including the material or sample name, synthesis method, instrument settings, spectral range, major absorption bands, and your research objective. The more context you provide, the more accurate and publication-ready the AI-generated interpretation will be.

What Makes a Good AI Prompt?

Artificial intelligence has become an invaluable assistant for scientific research, but the quality of the output depends directly on the quality of the prompt. Even the most advanced AI models cannot produce accurate FTIR interpretations if they receive vague, incomplete, or ambiguous instructions.

Think of AI as a highly knowledgeable research assistant. If you simply ask:

“Analyze this FTIR spectrum.”

the response will usually be broad and generic because the AI has very little context. However, if you provide detailed experimental information, define your objective, and specify the expected output format, AI can generate interpretations that closely resemble those written by experienced researchers.

A high-quality AI prompt should answer five essential questions:

• What is being analyzed?
• What experimental information is available?
• What is the scientific objective?
• What type of output is expected?
• Who is the intended audience?

The more precisely these questions are answered, the better the AI can understand your research context and produce meaningful results.

1. Clearly Describe the Material

Always begin by describing the sample as accurately as possible.

Instead of writing:

❌ Analyze the FTIR spectrum.

Write:

✅ Analyze the FTIR spectrum of a chitosan/PVA hydrogel reinforced with 2 wt.% ZnO nanoparticles.

Providing the complete material composition helps the AI associate the observed absorption bands with the correct functional groups and chemical structures.

2. Explain How the Sample Was Prepared

The synthesis or preparation method often determines which functional groups are expected to appear.

For example:

• Sol-gel synthesis
• Hydrothermal synthesis
• Chemical vapor deposition
• Electrospinning
• Ball milling
• Calcination
• Pyrolysis
• Surface modification
• Acid treatment
• Plasma treatment

Instead of simply saying:

❌ This is an FTIR spectrum of biochar.

Try:

✅ The biochar was prepared by pyrolysis of rice husk at 700°C under nitrogen for 2 hours.

This additional information allows AI to generate interpretations that are chemically consistent with the preparation process.

3. Include Important Experimental Conditions

Whenever possible, provide the experimental parameters used during FTIR acquisition, such as:

• Spectral range
• Resolution
• Number of scans
• ATR or KBr method
• Instrument model
• Background correction
• Sample state (powder, film, liquid, hydrogel, coating)

Although these parameters may not always change peak assignments, they improve the scientific quality of the generated discussion.

4. State Your Research Objective

One of the biggest mistakes users make is asking AI to “interpret the spectrum” without explaining why.

Different research goals require different types of analysis.

Examples include:

• Functional group identification
• Comparing untreated and treated samples
• Confirming successful surface modification
• Evaluating chemical interactions
• Investigating adsorption mechanisms
• Characterizing degradation products
• Supporting a journal publication
• Preparing a thesis chapter
• Writing an industrial quality control report

Clearly stating your objective enables AI to focus on the most relevant scientific aspects.

5. Specify the Desired Output

Different users require different styles of responses.

For example, you can ask AI to generate:

• A publication-ready discussion
• A reviewer-style critical evaluation
• Peak assignment table
• Scientific conclusion
• Industrial quality control report
• Comparative discussion
• Thesis-style explanation
• Figure caption
• Abstract
• Reviewer response

The more specific your request, the more useful the output becomes.

6. Mention the Expected Scientific Level

AI can adapt its writing style to different audiences.

Examples:

• Undergraduate laboratory report
• Master’s thesis
• PhD dissertation
• SCI journal manuscript
• Nature-style scientific writing
• Industrial technical report

This prevents responses that are either too simple or unnecessarily complicated.

7. Ask AI to Support Its Conclusions

Instead of accepting unsupported statements, encourage AI to explain its reasoning.

For example:

Assign all major absorption bands, explain the corresponding functional groups, discuss possible intermolecular interactions, and justify every interpretation based on accepted FTIR principles.

This usually produces more rigorous and scientifically coherent analyses.

8. Provide Comparison Data Whenever Possible

AI performs significantly better when multiple spectra are available.

For example:

• Before and after modification
• Raw material versus final product
• Commercial sample versus synthesized sample
• Different synthesis temperatures
• Different nanoparticle concentrations
• Different aging times

Comparative analysis allows AI to identify chemical changes rather than merely listing absorption bands.

9. Avoid Overly Generic Prompts

The following prompt:

Interpret this FTIR spectrum.

may produce only a general explanation.

A much stronger prompt would be:

Interpret the FTIR spectrum of hydrothermally synthesized TiO₂ nanoparticles coated with chitosan. Assign all significant absorption bands, discuss surface interactions, compare the spectrum with pure TiO₂, identify evidence of successful coating, and prepare a publication-ready discussion suitable for submission to an SCI journal.

Notice how this version provides the AI with the material, synthesis method, comparison target, scientific objective, and expected writing style.

10. Think Like a Scientific Reviewer

The best prompts resemble the questions that journal reviewers ask:

• Are the peak assignments justified?
• Are all major peaks explained?
• Are new peaks discussed?
• Are disappearing peaks interpreted?
• Are peak shifts explained?
• Are the conclusions supported by the spectral evidence?
• Are the interpretations chemically reasonable?

Designing prompts with these questions in mind often leads to higher-quality AI-generated discussions.

Key Elements of an Excellent FTIR AI Prompt

Pro Tip

The difference between an average AI response and an excellent one is rarely the AI model itself—it is almost always the quality of the prompt. By providing detailed scientific context, clearly defining your objectives, and specifying the desired output, researchers can transform AI from a generic chatbot into a powerful assistant for FTIR interpretation, scientific writing, and publication-ready data analysis.

Common Prompt Mistakes in FTIR Analysis

Artificial intelligence has become a powerful tool for interpreting FTIR spectra, but many researchers are disappointed with the results simply because they provide insufficient or poorly structured prompts. In most cases, the problem is not the AI model itself—it is the lack of scientific context supplied by the user.

A common misconception is that AI can accurately interpret any spectrum from a single sentence. While modern language models possess extensive scientific knowledge, they still rely on the information provided in the prompt. If important details are missing, the response is likely to be generic, incomplete, or even misleading.

Below are the most common mistakes researchers make when asking AI to analyze FTIR data, along with practical recommendations for avoiding them.

Mistake 1: Asking a Question That Is Too General

One of the most frequent mistakes is using an extremely short prompt.

Poor Prompt

Analyze this FTIR spectrum.

This instruction gives the AI almost no information. The response will usually consist of a generic explanation of common FTIR bands rather than a meaningful interpretation of your specific sample.

Better Prompt

Analyze the FTIR spectrum of hydrothermally synthesized ZnO nanoparticles coated with chitosan. Assign all significant peaks, discuss chemical interactions between ZnO and chitosan, and prepare a publication-ready discussion.

The second prompt immediately provides scientific context and defines the expected output.

Mistake 2: Not Describing the Sample

Different materials may exhibit absorption bands in similar spectral regions for completely different chemical reasons.

Simply writing:

FTIR spectrum of polymer.

is far less useful than:

FTIR spectrum of crosslinked PVA/chitosan hydrogel containing 3 wt.% ZnO nanoparticles.

Always describe the material as accurately as possible.

Mistake 3: Ignoring the Synthesis Method

The synthesis route often determines which functional groups should appear in the spectrum.

For example:

• Hydrothermal synthesis
• Sol-gel process
• Calcination
• Electrospinning
• Chemical modification
• Acid treatment

Providing this information allows AI to connect the observed bands with the underlying chemistry.

Mistake 4: Not Explaining the Purpose of the Analysis

AI cannot know what you are trying to prove unless you tell it.

Are you trying to:

• Confirm successful functionalization?
• Identify new functional groups?
• Compare two materials?
• Support an adsorption mechanism?
• Demonstrate oxidation?
• Write a manuscript discussion?

Without a defined objective, the response is often too broad.

Mistake 5: Omitting Important Experimental Details

Whenever possible, include:

• ATR or KBr method
• Spectral range
• Resolution
• Number of scans
• Instrument model
• Sample form (powder, film, coating, hydrogel, etc.)

Although AI may still provide useful answers without these details, including them generally leads to more scientifically consistent interpretations.

Mistake 6: Expecting AI to Identify Unknown Materials with Certainty

FTIR is an excellent technique for identifying functional groups, but it is rarely sufficient to determine the exact chemical identity of an unknown sample.

Avoid asking:

Tell me exactly what material this is.

Instead, ask:

Based on the observed absorption bands, identify the most probable functional groups and suggest possible material classes.

This reflects the actual capabilities of FTIR spectroscopy.

Mistake 7: Requesting Conclusions Without Evidence

Scientific conclusions should always be supported by spectral observations.

Instead of asking:

Tell me whether my synthesis was successful.

Try:

Evaluate whether the FTIR results provide evidence for successful surface modification. Explain your reasoning using the observed absorption bands.

This encourages evidence-based analysis rather than unsupported conclusions.

Mistake 8: Forgetting to Upload the Peak Positions

One of the biggest limitations is asking AI to interpret a spectrum without providing either:

• the spectrum image,
• the raw data,
• or the major peak positions.

For example:

❌ Analyze my FTIR spectrum.

✅ The major absorption bands are observed at 3425, 2920, 1635, 1418, 1084, and 560 cm⁻¹. Interpret these peaks and discuss their significance.

The more spectral information you provide, the more reliable the interpretation becomes.

Mistake 9: Ignoring Comparative Analysis

FTIR interpretation becomes much stronger when multiple spectra are compared.

Examples include:

• Before vs. after modification
• Pure polymer vs. nanocomposite
• Raw biomass vs. hydrochar
• Commercial product vs. synthesized material

Comparative prompts often produce deeper scientific insights than single-spectrum analyses.

Mistake 10: Asking for Everything in One Sentence

Many users combine multiple objectives into one vague request.

For example:

Analyze my FTIR, compare it with the literature, assign peaks, explain the mechanism, write the discussion, and prepare reviewer responses.

Instead, structure the request clearly:

1. Assign the major peaks.
2. Identify functional groups.
3. Explain chemical interactions.
4. Compare with reported literature.
5. Write a publication-ready discussion.
6. Suggest possible reviewer comments.

Structured prompts usually generate better-organized responses.

Mistake 11: Blindly Accepting Every AI Response

Although AI can significantly accelerate FTIR interpretation, it is not a replacement for scientific judgment.

Researchers should always:

• Verify important peak assignments.
• Compare interpretations with reputable literature.
• Check whether conclusions are chemically reasonable.
• Confirm unexpected findings using complementary techniques such as XRD, XPS, Raman spectroscopy, SEM, TGA, or elemental analysis.

AI should be viewed as an intelligent assistant—not as the final authority.

Best Practices Checklist

Before submitting your prompt, ask yourself:

• Have I described my material clearly?
• Have I explained how the sample was prepared?
• Did I include the important FTIR peaks?
• Have I stated the purpose of the analysis?
• Did I specify the type of output I need?
• Am I asking for evidence-based conclusions?
• Have I provided comparison data if available?
• Will another researcher understand my prompt without additional explanation?

If the answer to most of these questions is yes, your prompt is likely to produce a much more accurate and useful AI-generated interpretation.

Final Advice

The quality of AI-assisted FTIR analysis depends far more on the quality of the prompt than on the AI model itself. A carefully designed prompt provides the scientific context needed for accurate peak assignment, meaningful interpretation, and publication-ready discussion. By avoiding the common mistakes described above, researchers can obtain responses that are more reliable, more detailed, and far better suited for academic and industrial applications.

Before vs. After: Examples of Poor and Excellent FTIR Prompts

One of the fastest ways to improve AI-generated FTIR interpretations is to compare poor prompts with well-designed prompts. Small changes in the wording of a prompt can dramatically improve the scientific accuracy, depth, and usefulness of the response.

The following examples demonstrate how researchers can transform vague questions into detailed scientific instructions that produce publication-quality results.

Example 1 – General Spectrum Interpretation

❌ Poor Prompt

Analyze this FTIR spectrum.

Problems

• No sample information
• No research objective
• No expected output
• No scientific context

✅ Excellent Prompt

Analyze the FTIR spectrum of hydrothermally synthesized ZnO nanoparticles coated with chitosan. Assign all major absorption bands, identify the corresponding functional groups, explain chemical interactions between ZnO and chitosan, and prepare a publication-ready discussion suitable for an SCI journal.

Why it is better

This prompt provides the material, synthesis method, scientific objective, expected output, and publication level.

Example 2 – Peak Assignment

❌ Poor Prompt

Assign the FTIR peaks.

✅ Excellent Prompt

Assign all significant FTIR peaks observed at 3432, 2925, 1641, 1417, 1085, and 567 cm⁻¹. Identify the functional groups responsible for each absorption band, discuss their chemical significance, and explain how they support the proposed molecular structure.

Why it is better

Instead of asking for generic assignments, it gives the AI the actual peak positions and requests scientific interpretation.

Example 3 – Comparing Two Spectra

❌ Poor Prompt

Compare these spectra.

✅ Excellent Prompt

Compare the FTIR spectra of untreated cellulose and silane-treated cellulose. Explain peak shifts, new absorption bands, disappearing peaks, and discuss the evidence supporting successful surface modification.

Why it is better

The AI understands exactly what comparison should be performed and what conclusions are expected.

Example 4 – Polymer Characterization

❌ Poor Prompt

Interpret my polymer FTIR.

✅ Excellent Prompt

Interpret the FTIR spectrum of a PVA/chitosan hydrogel reinforced with ZnO nanoparticles. Discuss hydrogen bonding, intermolecular interactions, crosslinking effects, and any evidence of successful nanoparticle incorporation.

Example 5 – Biomass Analysis

❌ Poor Prompt

Analyze my biomass spectrum.

✅ Excellent Prompt

Interpret the FTIR spectrum of wheat straw before and after pyrolysis at 700°C under nitrogen. Explain the disappearance of cellulose and hemicellulose bands, the evolution of aromatic structures, and the formation of biochar.

Example 6 – Adsorption Study

❌ Poor Prompt

Explain the adsorption mechanism.

✅ Excellent Prompt

Compare the FTIR spectra of the adsorbent before and after methylene blue adsorption. Identify shifted or newly formed peaks and explain whether hydrogen bonding, electrostatic attraction, or π–π interactions contributed to the adsorption mechanism.

Example 7 – Reviewer Response

❌ Poor Prompt

Help me answer the reviewer.

✅ Excellent Prompt

Reviewer Comment:
"The FTIR discussion is superficial and lacks evidence."

Rewrite the FTIR discussion with stronger scientific justification, improved peak assignments, and explanations supported by accepted FTIR principles.

Example 8 – Publication Writing

❌ Poor Prompt

Write an FTIR discussion.

✅ Excellent Prompt

Write a publication-ready FTIR discussion for graphene oxide modified with polyethyleneimine. Use formal scientific language suitable for submission to a Q1 materials science journal. Explain all important peaks and discuss the chemical modification mechanism.

Example 9 – Unknown Peak

❌ Poor Prompt

What is this peak?

✅ Excellent Prompt

An unexpected absorption band appeared at approximately 1725 cm⁻¹ after thermal oxidation. Suggest possible chemical species responsible for this peak and explain how oxidation may have generated new carbonyl-containing functional groups.

Example 10 – Industrial Quality Control

❌ Poor Prompt

Is this material OK?

✅ Excellent Prompt

Compare the FTIR spectrum of the production sample with the approved commercial reference. Identify any missing, shifted, or additional absorption bands that may indicate impurities, formulation changes, degradation, or batch-to-batch variation.

What Makes the Excellent Prompts Better?

Across all examples above, the stronger prompts share several common characteristics:

• They clearly identify the material or sample.
• They provide relevant synthesis or preparation details.
• They include important spectral information when available.
• They define a specific scientific objective.
• They request a well-defined type of output.
• They encourage evidence-based reasoning rather than unsupported conclusions.
• They use terminology familiar to researchers, reviewers, and journal editors.

By contrast, poor prompts leave too much room for interpretation. The AI must guess the user’s intent, which often leads to generic or incomplete responses.

A Simple Formula for Writing Better FTIR Prompts

A reliable FTIR prompt can often be built using the following structure:

Material + Preparation Method + Experimental Context + Research Objective + Desired Output + Scientific Writing Style

For example:

Analyze the FTIR spectrum of hydrothermally synthesized ZnO-coated cellulose. Assign all major peaks, explain the chemical interactions responsible for the observed spectral changes, compare the results with untreated cellulose, and prepare a publication-ready discussion suitable for a Q1 journal.

This formula works for nearly every type of FTIR study, from polymers and nanomaterials to biomass, catalysts, coatings, pharmaceuticals, and environmental applications.

Pro Tip

The goal of prompt engineering is not to ask more questions—it is to ask better questions. The more scientific context you provide, the more likely the AI is to generate accurate, reproducible, and publication-ready FTIR interpretations.

How to Customize These AI Prompts for Your Own FTIR Research

The AI prompts presented in this guide are designed as flexible templates, not fixed commands. Every research project is unique, and the quality of AI-generated interpretations improves significantly when the prompt reflects the specific details of your experiment.

Instead of copying a prompt exactly as it appears, you should customize it by replacing the placeholder information with details from your own study. This simple step helps AI understand the scientific context of your work and produce responses that are more accurate, relevant, and publication-ready.

In general, every FTIR prompt should include the following information whenever possible.

1. Replace the Material Name

Always specify the exact material or sample being analyzed.

Instead of:

Analyze the FTIR spectrum of this material.

Write:

Analyze the FTIR spectrum of electrospun PCL/gelatin nanofibers containing 2 wt.% TiO₂ nanoparticles.

The more specific the material description, the more accurate the interpretation.

2. Describe the Preparation or Synthesis Method

The synthesis route often determines which functional groups are expected.

Examples include:

• Hydrothermal synthesis
• Sol-gel synthesis
• Chemical precipitation
• Electrospinning
• Pyrolysis
• Surface functionalization
• Plasma treatment
• Ball milling
• Calcination
• Acid activation

For example:

The hydrochar was prepared by hydrothermal carbonization of wheat straw at 220°C for 5 hours.

This information provides valuable chemical context for the AI.

3. Include Important FTIR Peaks

Rather than asking AI to interpret a spectrum without data, include the major absorption bands.

Example:

Major absorption bands were observed at 3415, 2923, 1638, 1412, 1084, and 565 cm⁻¹.

This enables AI to provide peak-specific interpretations instead of generic explanations.

4. Explain Your Research Objective

Tell the AI what you want to achieve.

For example:

• Identify functional groups
• Confirm successful modification
• Compare untreated and treated samples
• Explain adsorption mechanisms
• Investigate degradation
• Prepare a journal discussion
• Support reviewer responses
• Perform quality control analysis

Different objectives require different analytical approaches.

5. Mention Comparison Samples

Comparative analysis usually produces much stronger scientific discussions.

Examples include:

• Before vs. after modification
• Pure polymer vs. composite
• Commercial vs. synthesized material
• Different synthesis temperatures
• Different nanoparticle concentrations
• Fresh vs. aged samples

Comparisons help AI identify meaningful chemical changes rather than simply listing absorption bands.

6. Define the Type of Output

Clearly tell AI what kind of response you expect.

Examples:

• Publication-ready discussion
• Peak assignment table
• Scientific interpretation
• Reviewer response
• Thesis chapter
• Industrial quality control report
• Figure caption
• Abstract
• Conclusions

This allows AI to adapt both the structure and writing style of the response.

7. Specify the Writing Style

AI can generate content for different audiences.

Examples include:

• Undergraduate laboratory report
• Master’s thesis
• PhD dissertation
• SCI journal manuscript
• Q1 journal publication
• Industrial technical report

Specifying the target audience results in more appropriate language and terminology.

8. Ask AI to Explain Its Reasoning

Avoid requesting only conclusions.

Instead of asking:

Identify the functional groups.

Ask:

Assign all major FTIR peaks, explain the corresponding functional groups, discuss the chemical interactions responsible for each band, and justify the interpretation using accepted FTIR principles.

Evidence-based prompts almost always produce higher-quality scientific responses.

A Customizable FTIR Prompt Template

You can use the following template for almost any FTIR project.

Analyze the FTIR spectrum of [Material Name].

Sample preparation:
[Synthesis or preparation method]

Experimental conditions:
[ATR/KBr, spectral range, resolution, instrument, or other relevant details]

Major absorption bands:
[List the main peak positions]

Research objective:
[Explain what you want to investigate]

Please:
• Assign all major peaks.
• Identify the corresponding functional groups.
• Explain any peak shifts or new absorption bands.
• Discuss possible intermolecular interactions.
• Compare the results with similar materials reported in the literature.
• Prepare a publication-ready discussion suitable for submission to an SCI journal.

Example of a Fully Customized Prompt

Analyze the FTIR spectrum of hydrothermally synthesized biochar derived from wheat straw.

The biomass was treated at 220°C for 5 hours under nitrogen.

Major absorption bands were observed at 3412, 2921, 1718, 1604, 1425, 1096, and 787 cm⁻¹.

Compare the spectrum with raw wheat straw, explain the disappearance of cellulose and hemicellulose bands, discuss the formation of aromatic carbon structures during hydrothermal carbonization, and prepare a publication-ready discussion suitable for a Q1 journal.

Final Tip

AI performs best when it understands the complete scientific story behind your experiment—not just the spectrum itself. By providing detailed information about your material, preparation method, experimental conditions, and research objectives, you transform a generic AI response into a scientifically meaningful interpretation that is far more useful for research, publication, and industrial applications.

Peak Assignment AI Prompts (1–10)

Peak assignment is the foundation of every FTIR analysis. Before discussing reaction mechanisms, confirming successful functionalization, or comparing materials, researchers must first identify the absorption bands and assign them to the correct functional groups.

The following prompts are designed to help researchers obtain accurate, detailed, and publication-ready peak assignments using AI.

Prompt 1 – Complete Peak Assignment

Purpose

Assign all major absorption bands observed in an FTIR spectrum.

AI Prompt

You are an FTIR spectroscopy expert.

Analyze the FTIR spectrum of [Material Name].

The major absorption bands are located at:

[List the peak positions]

Assign every significant absorption band to its corresponding functional group. Explain the molecular vibration responsible for each peak and discuss its chemical significance. Present the results in a scientific table followed by a publication-ready discussion.

Best For

• Journal articles
• MSc and PhD theses
• Scientific reports

Expected Output

• Peak assignment table
• Functional group identification
• Scientific discussion

Prompt 2 – High-Confidence Functional Group Assignment

Purpose

Increase confidence in functional group identification.

AI Prompt

Assign the FTIR peaks of the following sample using accepted FTIR spectroscopy principles.

For every peak:

• Report the most probable functional group.
• Mention alternative assignments if applicable.
• State the confidence level (High, Medium, Low).
• Explain why this assignment is appropriate.

Peak positions:

[List peaks]

Best For

• Unknown materials
• Complex spectra
• Reviewer responses

Expected Output

• Multiple possible assignments
• Confidence ranking
• Scientific justification

Prompt 3 – Scientific Peak Assignment Table

Purpose

Generate a publication-ready table.

AI Prompt

Create a publication-quality FTIR peak assignment table for the following spectrum.

Include the columns:

• Peak Position (cm⁻¹)
• Assigned Functional Group
• Vibrational Mode
• Chemical Interpretation

Peak positions:

[List peaks]

Best For

• SCI manuscripts
• Thesis writing

Expected Output

A professionally formatted table ready for publication.

Prompt 4 – Explain Every Peak

Purpose

Avoid simple peak lists.

AI Prompt

Interpret every FTIR peak individually.

For each absorption band explain:

• What molecular vibration produces the peak?
• Which functional groups may contribute?
• Why this peak appears at this position?
• What chemical information does it provide about the material?

Peak positions:

[List peaks]

Best For

• Educational reports
• Comprehensive discussions

Expected Output

Detailed explanation for every peak.

Prompt 5 – Identify Unknown Peaks

Purpose

Interpret unexpected absorption bands.

AI Prompt

The following FTIR spectrum contains several unexpected absorption bands.

Known peaks:

[List known peaks]

Unknown peaks:

[List unknown peaks]

Suggest possible chemical species responsible for the unknown bands.

Discuss whether they may originate from:

• impurities
• oxidation
• degradation
• residual solvent
• by-products
• contamination

Provide scientific reasoning for each possibility.

Best For

• Failed synthesis
• Quality control
• Troubleshooting

Prompt 6 – Major vs Minor Peaks

Purpose

Determine which peaks are scientifically important.

AI Prompt

Analyze the FTIR spectrum and classify every absorption band as either:

• Major Peak
• Minor Peak

Explain why each peak should or should not be emphasized in a scientific publication.

Peak positions:

[List peaks]

Best For

• Journal preparation
• Presentation figures

Prompt 7 – Peak Assignment with Literature Comparison

Purpose

Support interpretations with published knowledge.

AI Prompt

Assign all FTIR peaks and compare each assignment with commonly reported literature values.

For every peak discuss:

• Typical reported wavenumber range
• Functional group
• Agreement with published FTIR studies
• Possible causes of small peak shifts

Best For

• High-impact journals
• Reviewer responses

Prompt 8 – Publication-Ready Peak Discussion

Purpose

Convert assignments into manuscript text.

AI Prompt

Using the following FTIR peak assignments, write a publication-ready Results and Discussion section suitable for an SCI journal.

Peak positions:

[List peaks]

The discussion should be written in formal scientific language without bullet points.

Best For

• Research papers
• Thesis chapters

Prompt 9 – Verify Existing Peak Assignments

Purpose

Check whether an interpretation is scientifically correct.

AI Prompt

Review the following FTIR peak assignments.

Determine whether every assignment is scientifically reasonable.

Correct any inaccurate interpretations.

Suggest improvements and explain the reasons behind every correction.

Existing assignments:

[Paste your interpretation]

Best For

• Manuscript revision
• Reviewer comments

Prompt 10 – Expert-Level Peak Assignment

Purpose

Generate the most comprehensive interpretation possible.

AI Prompt

Act as an internationally recognized FTIR spectroscopy expert.

Analyze the FTIR spectrum of:

[Material Name]

Major peaks:

[List peaks]

Prepare an expert-level interpretation including:

• Peak assignment
• Vibrational modes
• Functional groups
• Chemical significance
• Peak intensity discussion
• Possible intermolecular interactions
• Evidence supporting the proposed structure
• Limitations of FTIR interpretation
• Suggestions for complementary characterization techniques (XPS, Raman, NMR, XRD, TGA, etc.)

Write the discussion in a style suitable for publication in a high-impact Q1 journal.

Best For

• Q1 journal manuscripts
• PhD dissertations
• Industrial R&D reports

Expected Output

A comprehensive, publication-ready interpretation that goes beyond simple peak assignment by integrating structural chemistry, critical analysis, and recommendations for complementary characterization.

Functional Group Identification AI Prompts (11–20)

Identifying functional groups is one of the primary objectives of FTIR spectroscopy. While peak assignment focuses on matching individual absorption bands to vibrational modes, functional group identification goes one step further by interpreting the overall chemical structure of the material. AI can significantly accelerate this process by recognizing characteristic spectral patterns, correlating multiple absorption bands, and explaining how different functional groups contribute to the observed spectrum.

The following prompts are designed to help researchers accurately identify functional groups, distinguish overlapping absorptions, and generate scientifically sound interpretations suitable for research publications.

Prompt 11 – Identify All Functional Groups

Purpose

Determine every functional group present in the sample.

AI Prompt

Act as an FTIR spectroscopy expert.

Analyze the following FTIR spectrum.

Major absorption bands:

[List peak positions]

Identify every functional group that is likely present in the sample.

For each functional group explain:

• Which peaks support its presence.
• Why those peaks are characteristic.
• Whether the identification is definitive or tentative.

Finally, summarize the overall chemical composition suggested by the spectrum.

Best For

• Initial FTIR interpretation
• Material characterization
• Journal manuscripts

Expected Output

Complete functional group identification with supporting evidence.

Prompt 12 – Identify the Dominant Functional Groups

Purpose

Focus only on the chemically significant groups.

AI Prompt

Analyze the FTIR spectrum and identify only the dominant functional groups that define the chemical nature of the material.

Ignore insignificant or weak absorptions unless they have important chemical meaning.

Explain why these functional groups are considered dominant.

Best For

• Abstract writing
• Conclusions
• Figure captions

Prompt 13 – Distinguish Similar Functional Groups

Purpose

Avoid confusion between overlapping assignments.

AI Prompt

Several FTIR absorption bands could correspond to more than one functional group.

Using accepted FTIR principles, distinguish between the possible assignments.

Discuss why one assignment is more likely than the others.

Peak positions:

[List peaks]

Best For

• Complex organic compounds
• Reviewer responses

Prompt 14 – Explain Broad Absorption Bands

Purpose

Interpret broad and overlapping peaks.

AI Prompt

Interpret the broad absorption bands observed in the FTIR spectrum.

Discuss whether the peak broadening may result from:

• Hydrogen bonding
• Water adsorption
• Polymer interactions
• Surface hydroxyl groups
• Structural disorder

Provide scientific justification for each explanation.

Best For

• Hydrogels
• Biomaterials
• Polymers
• Oxides

Prompt 15 – Functional Group Changes After Modification

Purpose

Determine how chemical modification affected the material.

AI Prompt

Compare the FTIR spectra before and after chemical modification.

Identify:

• Newly appearing functional groups.
• Disappearing functional groups.
• Peak shifts.
• Changes in peak intensity.

Explain what these changes reveal about the modification process.

Best For

• Surface functionalization
• Composite preparation
• Nanomaterials

Prompt 16 – Identify Surface Functional Groups

Purpose

Focus specifically on surface chemistry.

AI Prompt

Identify the surface functional groups present in the material using the FTIR spectrum.

Discuss how these functional groups may influence:

• Surface reactivity
• Hydrophilicity
• Adsorption behavior
• Chemical stability
• Interfacial bonding

Support every conclusion using the observed absorption bands.

Best For

• Adsorbents
• Catalysts
• Coatings
• Nanoparticles

Prompt 17 – Determine Oxygen-Containing Functional Groups

Purpose

Identify oxygen-containing species.

AI Prompt

Analyze the FTIR spectrum and identify all oxygen-containing functional groups.

Discuss the presence of:

• Hydroxyl groups
• Carbonyl groups
• Carboxyl groups
• Ether groups
• Ester groups
• Epoxy groups

Explain which absorption bands support each assignment.

Best For

• Graphene oxide
• Biochar
• Biomass
• Oxidized materials

Prompt 18 – Determine Nitrogen-Containing Functional Groups

Purpose

Identify nitrogen chemistry.

AI Prompt

Identify all nitrogen-containing functional groups present in the FTIR spectrum.

Discuss possible evidence for:

• Primary amines
• Secondary amines
• Amides
• Imides
• Nitriles
• Heterocyclic nitrogen compounds

Explain how the observed peaks support your conclusions.

Best For

• Polymers
• Drug molecules
• Corrosion inhibitors
• Organic synthesis

Prompt 19 – Functional Group Confidence Assessment

Purpose

Evaluate the reliability of each identification.

AI Prompt

Identify the functional groups present in the FTIR spectrum.

For every identified group provide:

• Supporting peak positions.
• Confidence level (High / Medium / Low).
• Possible alternative assignments.
• Scientific reasoning.

Summarize which assignments are highly reliable and which require confirmation using complementary techniques.

Best For

• Unknown samples
• Industrial quality control
• Scientific reports

Prompt 20 – Expert-Level Functional Group Interpretation

Purpose

Generate a comprehensive structural interpretation.

AI Prompt

Act as an internationally recognized FTIR spectroscopy specialist.

Using the following FTIR spectrum:

[Insert peak positions]

Identify all probable functional groups.

Discuss:

• Characteristic absorption bands.
• Functional group interactions.
• Hydrogen bonding.
• Chemical environment.
• Evidence supporting the proposed molecular structure.
• Functional groups that are absent.
• Possible limitations of FTIR interpretation.
• Additional techniques (XPS, Raman, NMR, XRD, TGA, MS) that could confirm the assignments.

Prepare a publication-ready discussion suitable for a Q1 journal in materials science or chemistry.

Best For

• High-impact publications
• PhD dissertations
• Advanced materials research
• Industrial R&D

Expected Output

An expert-level functional group analysis that not only identifies chemical groups but also explains their structural significance, discusses uncertainties, and recommends complementary characterization methods.

Polymer & Composite FTIR AI Prompts (21–30)

Polymers and polymer-based composites are among the most widely studied materials in FTIR spectroscopy. Unlike simple inorganic compounds, polymer spectra often contain overlapping absorption bands, hydrogen bonding effects, crosslinking signatures, and interactions between the polymer matrix and reinforcing fillers.

Artificial Intelligence can greatly simplify these complex interpretations by identifying characteristic functional groups, comparing modified and unmodified polymers, evaluating intermolecular interactions, and generating publication-ready discussions.

The following prompts are specifically designed for polymer scientists, materials engineers, nanotechnology researchers, biomaterials specialists, and composite developers.

Prompt 21 – Complete Polymer FTIR Interpretation

Purpose

Generate a comprehensive interpretation of a polymer spectrum.

AI Prompt

Act as a polymer FTIR spectroscopy expert.

Analyze the FTIR spectrum of:

[Polymer Name]

Major absorption bands:

[List peak positions]

Identify all functional groups, explain their corresponding molecular vibrations, discuss the polymer backbone structure, and prepare a publication-ready discussion suitable for an SCI journal.

Best For

• Polymer characterization
• Research papers
• Thesis writing

Prompt 22 – Hydrogen Bonding Analysis

Purpose

Evaluate hydrogen bonding in polymer systems.

AI Prompt

Analyze the FTIR spectrum and determine whether hydrogen bonding is present.

Discuss evidence based on:

• Peak broadening
• Peak shifts
• Changes in O–H stretching
• Changes in N–H stretching
• Carbonyl peak shifts

Explain how hydrogen bonding influences the material properties.

Best For

• Hydrogels
• PVA
• Chitosan
• Cellulose
• Gelatin
• Biopolymers

Prompt 23 – Crosslinking Confirmation

Purpose

Determine whether crosslinking has occurred.

AI Prompt

Compare the FTIR spectra before and after crosslinking.

Determine whether crosslinking has successfully occurred.

Identify:

• New absorption bands
• Disappearing peaks
• Peak shifts
• Changes in hydrogen bonding

Explain the crosslinking mechanism supported by the FTIR evidence.

Best For

• Hydrogels
• Polymer networks
• Biomedical materials

Prompt 24 – Polymer Composite Analysis

Purpose

Interpret polymer–filler interactions.

AI Prompt

Analyze the FTIR spectrum of a polymer composite.

Matrix:

[Polymer]

Reinforcement:

[Filler]

Explain:

• Polymer functional groups
• Filler-related peaks
• Polymer–filler interactions
• Evidence of successful incorporation
• Chemical compatibility
• Interfacial bonding

Write the discussion in publication-ready scientific language.

Best For

• Polymer nanocomposites
• Fiber-reinforced composites
• Hybrid materials

Prompt 25 – Nanoparticle Incorporation

Purpose

Confirm successful nanoparticle loading.

AI Prompt

Compare the FTIR spectra of the pure polymer and the nanoparticle-reinforced composite.

Determine whether FTIR provides evidence that nanoparticles were successfully incorporated.

Discuss:

• Peak shifts
• Intensity changes
• New absorption bands
• Interfacial interactions

Explain the possible bonding mechanism.

Best For

• ZnO
• TiO₂
• SiO₂
• Fe₃O₄
• Graphene oxide
• MXene

Prompt 26 – Polymer Blend Compatibility

Purpose

Evaluate miscibility between polymers.

AI Prompt

Analyze the FTIR spectrum of a polymer blend.

Determine whether the polymers appear to be compatible.

Discuss evidence including:

• Hydrogen bonding
• Peak shifts
• Band broadening
• New interactions

Explain whether FTIR supports good miscibility between the polymers.

Best For

• Polymer blends
• Copolymers
• Biopolymer mixtures

Prompt 27 – Functional Group Changes After Aging

Purpose

Evaluate degradation.

AI Prompt

Compare the FTIR spectra before and after aging.

Identify chemical changes caused by:

• Thermal aging
• UV exposure
• Moisture
• Oxidation

Discuss newly formed or disappearing functional groups and explain the degradation mechanism.

Best For

• Durability studies
• Weathering
• Stability evaluation

Prompt 28 – Polymer Degradation Mechanism

Purpose

Interpret degradation pathways.

AI Prompt

Analyze the FTIR spectrum of a degraded polymer.

Discuss evidence for:

• Chain scission
• Oxidation
• Hydrolysis
• Carbonyl formation
• Loss of functional groups

Relate the spectral changes to the degradation mechanism.

Best For

• Biomedical polymers
• Packaging materials
• Environmental degradation

Prompt 29 – Publication-Ready Composite Discussion

Purpose

Prepare manuscript-quality discussion.

AI Prompt

Write a publication-ready FTIR discussion for the following polymer composite.

Material:

[Material Name]

Major peaks:

[List peaks]

Discuss:

• Functional groups
• Polymer-filler interactions
• Chemical compatibility
• Structural modifications
• Scientific significance

Use formal scientific language suitable for publication in a Q1 journal.

Best For

• Manuscript preparation
• SCI journals
• Conference papers

Prompt 30 – Expert-Level Polymer Interpretation

Purpose

Generate the most comprehensive polymer analysis.

AI Prompt

Act as an internationally recognized polymer spectroscopy expert.

Analyze the FTIR spectrum of:

[Material Name]

Discuss:

• Complete peak assignments
• Functional groups
• Polymer backbone structure
• Crosslinking evidence
• Hydrogen bonding
• Polymer-filler interactions
• Structural changes
• Chemical compatibility
• Relationship between FTIR results and material properties
• Limitations of FTIR
• Complementary characterization techniques (XRD, XPS, Raman, SEM, TEM, DSC, TGA, DMA)

Prepare a publication-ready discussion suitable for a high-impact polymer or materials science journal.

Best For

• Q1 journal manuscripts
• PhD dissertations
• Advanced composite research
• Industrial R&D

Expected Output

A comprehensive, publication-quality interpretation that integrates FTIR peak assignments with polymer chemistry, composite interfaces, intermolecular interactions, and material performance.

Nanomaterials FTIR AI Prompts (31–40)

Nanomaterials often exhibit unique FTIR characteristics due to their high surface area, abundant surface functional groups, quantum size effects, and strong interactions with organic molecules. Unlike bulk materials, nanoparticles frequently show peak broadening, reduced intensities, surface hydroxylation, ligand adsorption, and interfacial bonding, making their interpretation considerably more challenging.

Artificial Intelligence can assist researchers by identifying surface functional groups, evaluating nanoparticle modifications, confirming successful synthesis, and generating publication-ready discussions that connect FTIR results with nanomaterial properties.

The following prompts are specifically designed for nanotechnology, materials science, chemistry, biomedical engineering, and energy-related applications.

Prompt 31 – Complete Nanoparticle FTIR Interpretation

Purpose

Generate a comprehensive interpretation of nanoparticle FTIR spectra.

AI Prompt

Act as an expert in nanomaterial characterization.

Analyze the FTIR spectrum of:

[Nanomaterial Name]

Major absorption bands:

[List peak positions]

Identify all functional groups, explain their vibrational modes, discuss surface chemistry, and determine whether the spectrum confirms successful nanoparticle synthesis.

Prepare a publication-ready discussion suitable for a Q1 journal.

Best For

• Metal oxide nanoparticles
• Biomedical nanoparticles
• Nanocatalysts

Prompt 32 – Surface Functional Group Analysis

Purpose

Identify surface chemistry.

AI Prompt

Analyze the FTIR spectrum and identify all surface functional groups present on the nanoparticles.

Discuss:

• Hydroxyl groups
• Adsorbed water
• Organic ligands
• Surface modifiers
• Surface oxidation

Explain how these functional groups influence nanoparticle stability and reactivity.

Best For

• Surface-modified nanoparticles
• Catalysts
• Adsorbents

Prompt 33 – Compare Bare and Functionalized Nanoparticles

Purpose

Confirm successful surface modification.

AI Prompt

Compare the FTIR spectra of bare nanoparticles and functionalized nanoparticles.

Identify:

• Newly appearing peaks
• Missing peaks
• Peak shifts
• Changes in peak intensity

Explain whether the FTIR data confirm successful functionalization and describe the likely bonding mechanism.

Best For

• Amino-functionalization
• Polymer coating
• Drug loading

Prompt 34 – Ligand Attachment Analysis

Purpose

Verify ligand binding.

AI Prompt

Determine whether the FTIR spectrum confirms successful attachment of the organic ligand onto the nanoparticle surface.

Discuss:

• Characteristic ligand peaks
• Surface interaction
• Possible coordination mechanism
• Evidence of chemical bonding versus physical adsorption.

Best For

• Drug delivery
• Surface chemistry
• Biosensors

Prompt 35 – Metal Oxide Nanoparticle Analysis

Purpose

Interpret metal oxide FTIR spectra.

AI Prompt

Interpret the FTIR spectrum of metal oxide nanoparticles.

Discuss:

• Metal–oxygen vibrations
• Surface hydroxyl groups
• Adsorbed species
• Residual synthesis precursors
• Organic contaminants

Explain how the spectrum supports successful oxide formation.

Best For

• ZnO
• TiO₂
• Fe₂O₃
• CuO
• MgO
• CeO₂

Prompt 36 – Nanocomposite FTIR Analysis

Purpose

Evaluate interactions within nanocomposites.

AI Prompt

Analyze the FTIR spectrum of the nanocomposite.

Matrix:

[Material]

Nanofiller:

[Material]

Explain:

• Chemical interactions
• Interfacial bonding
• Hydrogen bonding
• Evidence of nanoparticle incorporation
• Structural modifications

Write the discussion in publication-ready scientific language.

Best For

• Polymer nanocomposites
• Ceramic nanocomposites
• Hybrid materials

Prompt 37 – Graphene, GO and MXene Analysis

Purpose

Interpret carbon nanomaterial spectra.

AI Prompt

Analyze the FTIR spectrum of graphene-based or MXene-based nanomaterials.

Identify evidence for:

• Hydroxyl groups
• Carboxyl groups
• Epoxy groups
• Carbonyl groups
• Surface terminations
• Functionalization reactions

Discuss how these groups influence material performance.

Best For

• Graphene oxide
• Reduced graphene oxide
• MXenes
• Carbon nanomaterials

Prompt 38 – MOF and Hybrid Nanostructure Analysis

Purpose

Interpret FTIR spectra of advanced porous materials.

AI Prompt

Analyze the FTIR spectrum of the metal-organic framework (MOF) or hybrid nanostructure.

Discuss:

• Organic linker vibrations
• Metal–ligand coordination
• Framework stability
• Guest molecule interactions
• Evidence supporting successful framework formation.

Best For

• MOFs
• COFs
• Hybrid nanomaterials

Prompt 39 – Correlate FTIR with Other Characterization Techniques

Purpose

Integrate FTIR with complementary analyses.

AI Prompt

Interpret the FTIR spectrum together with XRD, XPS, Raman, SEM, TEM, BET, and TGA results.

Explain how FTIR complements each technique.

Discuss whether the combined evidence supports successful synthesis and structural characterization.

Best For

• Complete characterization studies
• High-impact journal papers

Prompt 40 – Expert-Level Nanomaterial Interpretation

Purpose

Produce the most comprehensive AI-generated discussion.

AI Prompt

Act as an internationally recognized nanomaterials characterization expert.

Analyze the FTIR spectrum of:

[Material Name]

Prepare an expert-level discussion including:

• Complete peak assignments
• Surface functional groups
• Interfacial interactions
• Surface chemistry
• Functionalization mechanism
• Structural changes
• Comparison with similar nanomaterials
• Relationship between FTIR results and material properties
• Potential limitations of FTIR interpretation
• Suggestions for additional characterization techniques

Write the discussion in the style of a publication suitable for a high-impact Q1 nanotechnology or materials science journal.

Best For

• Nature-index journals
• Advanced Materials
• ACS Nano
• Nano Energy
• Journal of Materials Chemistry
• Industrial R&D

Expected Output

A publication-quality interpretation that integrates FTIR spectroscopy with nanomaterial chemistry, surface science, and complementary characterization methods while providing critical scientific reasoning rather than simple peak assignments.

Biomass & Biochar FTIR AI Prompts (41–50)

Biomass-derived materials such as biochar, hydrochar, activated carbon, agricultural residues, lignocellulosic fibers, and carbon-rich adsorbents have become increasingly important in environmental engineering, renewable energy, carbon sequestration, and wastewater treatment.

FTIR spectroscopy is one of the most valuable techniques for investigating the chemical transformation of biomass during thermal treatment, hydrothermal carbonization, pyrolysis, activation, and surface functionalization. AI can accelerate these analyses by identifying functional group evolution, explaining reaction mechanisms, and generating publication-ready discussions.

The following prompts are specifically designed for researchers working with biomass, biochar, hydrochar, activated carbon, and bio-based adsorbents.

Prompt 41 – Complete Biomass FTIR Interpretation

Purpose

Generate a full interpretation of biomass FTIR spectra.

AI Prompt

Act as an expert in biomass characterization.

Analyze the FTIR spectrum of:

[Biomass Name]

Major absorption bands:

[List peak positions]

Identify all functional groups and explain their molecular vibrations.

Discuss the chemical composition of the biomass, including cellulose, hemicellulose, lignin, proteins, extractives, and moisture.

Prepare a publication-ready discussion suitable for an SCI journal.

Best For

• Agricultural residues
• Natural fibers
• Plant biomass
• Forestry waste

Prompt 42 – Raw Biomass vs Biochar Comparison

Purpose

Evaluate chemical changes after carbonization.

AI Prompt

Compare the FTIR spectra of raw biomass and biochar.

Discuss:

• Disappearance of cellulose peaks
• Hemicellulose degradation
• Lignin transformation
• Formation of aromatic carbon
• Loss of oxygen-containing functional groups

Explain how thermal treatment changes the chemical structure.

Best For

• Pyrolysis studies
• Carbonization research
• Biochar production

Prompt 43 – Hydrothermal Carbonization (HTC) Analysis

Purpose

Interpret hydrochar formation.

AI Prompt

Analyze the FTIR spectrum of hydrochar produced by hydrothermal carbonization.

Discuss:

• Dehydration reactions
• Decarboxylation
• Aromatization
• Formation of oxygen-containing functional groups
• Changes in cellulose, hemicellulose, and lignin

Explain how the FTIR spectrum reflects the HTC process.

Best For

• Hydrochar
• HTC research
• Renewable materials

Prompt 44 – Effect of Temperature on Biomass

Purpose

Evaluate thermal evolution.

AI Prompt

Compare the FTIR spectra of biomass treated at different temperatures.

Discuss how increasing temperature affects:

• Hydroxyl groups
• Carbonyl groups
• Ether bonds
• Aromatic structures
• Aliphatic chains

Explain the thermal decomposition mechanism using FTIR evidence.

Best For

• Pyrolysis
• Calcination
• Thermal treatment studies

Prompt 45 – Activated Carbon Surface Chemistry

Purpose

Interpret activated carbon spectra.

AI Prompt

Analyze the FTIR spectrum of activated carbon.

Identify the major surface functional groups including:

• Hydroxyl
• Carboxyl
• Carbonyl
• Lactone
• Phenolic groups

Discuss how these groups influence adsorption performance.

Best For

• Activated carbon
• Adsorbents
• Water treatment

Prompt 46 – Adsorption Mechanism Investigation

Purpose

Explain adsorption using FTIR.

AI Prompt

Compare the FTIR spectra of the adsorbent before and after adsorption.

Determine whether the adsorption mechanism involves:

• Hydrogen bonding
• Electrostatic attraction
• π–π interactions
• Surface complexation
• Ion exchange

Support every conclusion using the observed spectral changes.

Best For

• Dye adsorption
• Heavy metals
• Pharmaceutical removal

Prompt 47 – Biomass Functional Group Evolution

Purpose

Track chemical evolution.

AI Prompt

Analyze how the functional groups evolve during biomass conversion.

Discuss:

• Which groups disappear
• Which groups become stronger
• Which new groups appear
• Structural implications of these changes

Relate the observations to the conversion mechanism.

Best For

• Biofuel research
• Carbon materials
• Biomass conversion

Prompt 48 – Publication-Ready Biomass Discussion

Purpose

Prepare a manuscript-quality discussion.

AI Prompt

Write a publication-ready FTIR Results and Discussion section for biomass conversion.

Discuss:

• Peak assignments
• Functional groups
• Structural evolution
• Thermal decomposition
• Chemical modification
• Scientific significance

Use formal language suitable for submission to a Q1 journal.

Best For

• Journal manuscripts
• PhD dissertations

Prompt 49 – Correlate FTIR with TGA and Elemental Analysis

Purpose

Integrate multiple characterization techniques.

AI Prompt

Interpret the FTIR spectrum together with:

• TGA
• DTG
• Elemental analysis (CHNS/O)
• BET
• XRD

Explain how the combined characterization supports biomass conversion and structural evolution.

Discuss agreements and possible inconsistencies.

Best For

• Comprehensive characterization
• High-impact publications

Prompt 50 – Expert-Level Biomass Interpretation

Purpose

Generate the most comprehensive biomass discussion.

AI Prompt

Act as an internationally recognized biomass characterization expert.

Analyze the FTIR spectrum of:

[Material Name]

Prepare a publication-ready discussion including:

• Complete peak assignments
• Functional group evolution
• Cellulose, hemicellulose, and lignin transformations
• Aromatization
• Dehydration
• Decarboxylation
• Carbonization mechanism
• Surface chemistry
• Adsorption implications
• Relationship between FTIR and TGA, BET, XRD, SEM, and elemental analysis
• Limitations of FTIR interpretation
• Recommendations for complementary characterization

Write the discussion in the style of a Q1 journal in biomass, environmental science, or renewable energy.

Best For

• Biochar research
• Hydrochar studies
• Environmental engineering
• Renewable energy
• Industrial R&D

Expected Output

A comprehensive, publication-quality interpretation explaining how biomass chemistry evolves during thermal or hydrothermal treatment, how functional groups influence adsorption and reactivity, and how FTIR findings correlate with complementary characterization techniques.

Catalysts & MOFs FTIR AI Prompts (51–60)

Fourier Transform Infrared (FTIR) spectroscopy is one of the most powerful techniques for investigating heterogeneous catalysts, photocatalysts, metal oxides, zeolites, metal-organic frameworks (MOFs), covalent organic frameworks (COFs), and hybrid catalytic materials. Beyond identifying functional groups, FTIR provides valuable insights into metal–ligand coordination, catalyst surface chemistry, active sites, adsorbed intermediates, framework stability, and catalytic reaction mechanisms.

Artificial Intelligence can significantly improve catalyst interpretation by correlating spectral features with catalytic performance, identifying structural modifications after reactions, and generating publication-ready discussions suitable for high-impact journals.

The following prompts are specifically designed for researchers working in catalysis, photocatalysis, electrocatalysis, MOFs, COFs, and advanced porous materials.

Prompt 51 – Complete Catalyst FTIR Interpretation

Purpose

Generate a comprehensive interpretation of a catalyst FTIR spectrum.

AI Prompt

Act as an expert in catalyst characterization.

Analyze the FTIR spectrum of:

[Catalyst Name]

Major absorption bands:

[List peak positions]

Identify all functional groups, assign the corresponding molecular vibrations, discuss catalyst surface chemistry, and explain how the observed functional groups may contribute to catalytic activity.

Prepare a publication-ready discussion suitable for a Q1 catalysis journal.

Best For

• Metal oxide catalysts
• Heterogeneous catalysts
• Photocatalysts

Prompt 52 – Surface Active Site Identification

Purpose

Identify chemically active surface groups.

AI Prompt

Analyze the FTIR spectrum and identify the surface functional groups that are likely to serve as catalytic active sites.

Discuss:

• Surface hydroxyl groups
• Lewis acid sites
• Brønsted acid sites
• Metal–oxygen bonds
• Oxygen vacancies

Explain how these species influence catalytic performance.

Best For

• Oxide catalysts
• Zeolites
• Acid catalysts

Prompt 53 – MOF Structure Verification

Purpose

Confirm successful MOF synthesis.

AI Prompt

Analyze the FTIR spectrum of the synthesized MOF.

Discuss:

• Organic linker vibrations
• Metal–ligand coordination
• Characteristic framework peaks
• Evidence of successful framework formation
• Residual precursor signals
• Framework stability

Prepare a publication-ready interpretation.

Best For

• UiO-66
• ZIF-8
• MIL series
• HKUST-1
• MOF derivatives

Prompt 54 – Compare Fresh and Used Catalysts

Purpose

Evaluate catalyst stability.

AI Prompt

Compare the FTIR spectra of the fresh catalyst and the spent catalyst.

Identify:

• Newly formed peaks
• Missing peaks
• Peak shifts
• Surface poisoning
• Coke deposition
• Structural degradation

Explain how these spectral changes affect catalyst performance.

Best For

• Catalyst recycling
• Stability studies
• Industrial catalysis

Prompt 55 – Adsorbed Reaction Intermediate Analysis

Purpose

Identify reaction intermediates.

AI Prompt

Analyze the FTIR spectrum collected after catalytic reaction.

Identify possible adsorbed intermediates.

Discuss whether the observed bands correspond to:

• Carbonate species
• Bicarbonate
• Formate
• Acetate
• Hydroxyl intermediates
• Organic reaction products

Relate the observations to the proposed catalytic mechanism.

Best For

• CO₂ reduction
• Photocatalysis
• Electrocatalysis

Prompt 56 – Metal–Ligand Coordination Analysis

Purpose

Interpret coordination chemistry.

AI Prompt

Interpret the FTIR spectrum to determine the coordination environment between metal ions and organic ligands.

Discuss:

• Coordination-induced peak shifts
• Symmetric and asymmetric stretching
• Binding mode
• Chelation evidence
• Coordination geometry

Explain how FTIR supports the proposed coordination structure.

Best For

• MOFs
• Coordination polymers
• Metal complexes

Prompt 57 – Catalyst Modification Confirmation

Purpose

Verify successful catalyst functionalization.

AI Prompt

Compare the FTIR spectra before and after catalyst modification.

Determine whether the modification was successful.

Discuss:

• New functional groups
• Surface grafting
• Organic modifiers
• Surface interactions
• Chemical bonding

Support every conclusion using FTIR evidence.

Best For

• Functionalized catalysts
• Hybrid catalysts
• Surface engineering

Prompt 58 – Correlate FTIR with Catalytic Performance

Purpose

Connect spectroscopy with activity.

AI Prompt

Interpret the FTIR spectrum together with catalytic performance data.

Discuss how the observed functional groups and surface chemistry may explain:

• Higher catalytic activity
• Improved selectivity
• Better stability
• Faster reaction kinetics
• Enhanced adsorption

Relate the spectral observations to catalyst performance.

Best For

• Reaction mechanism studies
• Performance optimization

Prompt 59 – Publication-Ready Catalyst Discussion

Purpose

Prepare manuscript-quality interpretation.

AI Prompt

Write a publication-ready FTIR Results and Discussion section for the catalyst.

Include:

• Peak assignments
• Surface chemistry
• Metal–oxygen vibrations
• Organic functional groups
• Catalyst modification
• Reaction mechanism
• Scientific significance

Write in formal language suitable for submission to a Q1 catalysis journal.

Best For

• Journal manuscripts
• Conference papers
• PhD theses

Prompt 60 – Expert-Level Catalyst & MOF Interpretation

Purpose

Generate the most comprehensive catalyst discussion.

AI Prompt

Act as an internationally recognized catalyst characterization expert.

Analyze the FTIR spectrum of:

[Material Name]

Prepare an expert-level discussion including:

• Complete peak assignments
• Surface functional groups
• Metal–ligand coordination
• Framework integrity
• Active catalytic sites
• Adsorbed intermediates
• Catalyst modification
• Relationship between FTIR and catalytic activity
• Correlation with XRD, XPS, Raman, BET, SEM, TEM, TGA, and catalytic performance data
• Limitations of FTIR interpretation
• Recommendations for complementary characterization techniques

Write the discussion in the style of a high-impact Q1 journal in catalysis, chemistry, or materials science.

Best For

• Advanced Catalysis
• Applied Catalysis A/B
• ACS Catalysis
• Journal of Catalysis
• Chemical Engineering Journal
• Industrial R&D

Expected Output

A publication-quality discussion that integrates FTIR spectroscopy with catalyst surface chemistry, coordination chemistry, catalytic mechanisms, structural stability, and complementary characterization techniques, providing deep scientific insight beyond conventional peak assignments.

Corrosion & Coatings FTIR AI Prompts (61–70)

Corrosion science is one of the most important application areas of FTIR spectroscopy. Researchers frequently use FTIR to investigate corrosion inhibitors, protective polymer coatings, conversion coatings, self-healing systems, passive films, hybrid organic–inorganic coatings, and surface modifications.

Rather than simply identifying functional groups, FTIR helps explain how inhibitors adsorb onto metal surfaces, how protective films are formed, whether chemical bonding occurs, and why corrosion resistance improves.

Artificial Intelligence can accelerate this interpretation by correlating FTIR spectra with electrochemical measurements such as EIS, Tafel polarization, salt spray testing, immersion tests, and surface characterization techniques.

The following prompts are designed specifically for corrosion scientists, coating engineers, electrochemists, and materials researchers.

Prompt 61 – Complete Corrosion Inhibitor FTIR Interpretation

Purpose

Generate a comprehensive interpretation of corrosion inhibitor FTIR spectra.

AI Prompt

Act as an expert in corrosion science and FTIR spectroscopy.

Analyze the FTIR spectrum of:

[Corrosion Inhibitor Name]

Major absorption bands:

[List peak positions]

Identify all functional groups, explain their vibrational modes, discuss their potential adsorption behavior on metallic surfaces, and explain how they contribute to corrosion inhibition.

Prepare a publication-ready discussion suitable for a Q1 corrosion journal.

Best For

• Organic corrosion inhibitors
• Green inhibitors
• Drug inhibitors
• Ionic liquids

Prompt 62 – Corrosion Inhibitor Adsorption Mechanism

Purpose

Determine how the inhibitor interacts with the metal surface.

AI Prompt

Analyze the FTIR spectrum before and after adsorption of the corrosion inhibitor onto the metal surface.

Discuss:

• Peak shifts
• Disappearing peaks
• New absorption bands
• Evidence of chemisorption
• Evidence of physisorption
• Coordination between inhibitor molecules and metal atoms

Explain the most probable adsorption mechanism.

Best For

• Steel inhibitors
• Aluminum alloys
• Copper alloys
• Magnesium alloys

Prompt 63 – Polymer Coating Characterization

Purpose

Interpret protective coating chemistry.

AI Prompt

Analyze the FTIR spectrum of the protective polymer coating.

Discuss:

• Functional groups
• Crosslinking
• Polymer backbone
• Adhesion-promoting groups
• Barrier-forming functional groups

Explain how these chemical features improve corrosion protection.

Best For

• Epoxy coatings
• Polyurethane
• Acrylic coatings
• Sol-gel coatings

Prompt 64 – Compare Coating Before and After Corrosion

Purpose

Evaluate coating degradation.

AI Prompt

Compare the FTIR spectra of the coating before and after corrosion testing.

Identify:

• New oxidation products
• Hydrolysis
• Polymer degradation
• Loss of functional groups
• Formation of corrosion products

Explain how the coating deteriorated during exposure.

Best For

• Salt spray tests
• Immersion tests
• Weathering studies

Prompt 65 – Self-Healing Coating Analysis

Purpose

Evaluate healing mechanisms.

AI Prompt

Analyze the FTIR spectrum of a self-healing coating.

Determine whether FTIR provides evidence for:

• Capsule rupture
• Healing agent release
• Polymerization
• Crosslinking
• New chemical bond formation

Discuss how these changes contribute to self-healing behavior.

Best For

• Self-healing coatings
• Smart coatings
• Microcapsule systems

Prompt 66 – Passive Film Characterization

Purpose

Investigate passive layer formation.

AI Prompt

Interpret the FTIR spectrum of the passive film formed on the metal surface.

Discuss:

• Metal hydroxides
• Metal oxides
• Adsorbed inhibitor molecules
• Water adsorption
• Surface functional groups

Explain how the passive film improves corrosion resistance.

Best For

• Stainless steel
• Titanium
• Aluminum
• Magnesium

Prompt 67 – Hybrid Organic–Inorganic Coatings

Purpose

Interpret hybrid coating chemistry.

AI Prompt

Analyze the FTIR spectrum of the hybrid organic–inorganic coating.

Discuss:

• Organic functional groups
• Inorganic network formation
• Siloxane bonds
• Hydrogen bonding
• Chemical compatibility
• Interfacial bonding

Explain how these interactions improve coating performance.

Best For

• Sol-gel coatings
• Hybrid nanocoatings
• Ceramic-polymer coatings

Prompt 68 – Correlate FTIR with Electrochemical Tests

Purpose

Combine spectroscopy with corrosion measurements.

AI Prompt

Interpret the FTIR spectrum together with:

• EIS
• Potentiodynamic polarization
• OCP
• Salt spray testing
• Weight loss measurements

Explain how the identified functional groups relate to corrosion resistance and electrochemical performance.

Best For

• Corrosion publications
• Electrochemical studies

Prompt 69 – Publication-Ready Corrosion Discussion

Purpose

Generate a manuscript-quality discussion.

AI Prompt

Write a publication-ready FTIR Results and Discussion section for a corrosion inhibition study.

Include:

• Peak assignments
• Functional groups
• Adsorption mechanism
• Surface interactions
• Protective film formation
• Scientific significance

Use formal language suitable for submission to Corrosion Science or Progress in Organic Coatings.

Best For

• SCI journals
• PhD dissertations
• Conference papers

Prompt 70 – Expert-Level Corrosion & Coating Interpretation

Purpose

Produce the most comprehensive corrosion analysis.

AI Prompt

Act as an internationally recognized corrosion scientist and FTIR spectroscopy expert.

Analyze the FTIR spectrum of:

[Material Name]

Prepare an expert-level discussion including:

• Complete peak assignments
• Functional groups
• Adsorption mechanism
• Chemisorption versus physisorption
• Protective film formation
• Crosslinking reactions
• Polymer degradation (if applicable)
• Correlation between FTIR results and corrosion resistance
• Relationship with EIS, polarization, SEM, EDS, XPS, Raman, AFM, and contact angle measurements
• Limitations of FTIR interpretation
• Recommendations for complementary characterization techniques

Write the discussion in the style of a high-impact Q1 journal such as Corrosion Science, Progress in Organic Coatings, Surface & Coatings Technology, or Journal of Materials Science & Technology.

Best For

• Corrosion Science
• Progress in Organic Coatings
• Surface & Coatings Technology
• Electrochimica Acta
• Industrial coating R&D

Expected Output

A publication-quality interpretation that integrates FTIR spectroscopy with corrosion mechanisms, inhibitor adsorption, coating chemistry, electrochemical performance, and complementary surface characterization techniques to produce a scientifically rigorous discussion.

Comparative FTIR Analysis AI Prompts (71–80)

Comparative analysis is one of the most common tasks in FTIR spectroscopy. Rather than interpreting a single spectrum, researchers often compare multiple samples to understand how synthesis conditions, additives, thermal treatment, aging, chemical modification, or environmental exposure influence molecular structure.

Artificial Intelligence can rapidly identify subtle spectral differences, quantify peak shifts, explain intensity variations, recognize emerging or disappearing functional groups, and produce publication-ready discussions that would otherwise require extensive manual interpretation.

The following prompts are designed to help researchers compare two or more FTIR spectra in a scientifically rigorous manner.

Prompt 71 – Compare Two FTIR Spectra

Purpose

Perform a detailed comparison between two samples.

AI Prompt

Act as an expert FTIR spectroscopy analyst.

Compare the following two FTIR spectra.

Sample A:
[Description]

Sample B:
[Description]

Major peaks:

[List peak positions]

Discuss:

• Similarities
• Differences
• Peak shifts
• Intensity changes
• Newly appearing peaks
• Missing peaks

Explain the structural and chemical reasons behind the observed differences.

Write the discussion in publication-ready scientific language.

Best For

• Before vs after treatment
• Material modification
• Control vs experimental samples

Prompt 72 – Compare Multiple FTIR Spectra

Purpose

Analyze several spectra simultaneously.

AI Prompt

Compare the FTIR spectra of the following samples:

[List sample names]

Identify trends in:

• Functional groups
• Peak positions
• Peak intensities
• Band broadening
• Structural evolution

Explain how the observed changes relate to the processing conditions.

Best For

• Temperature series
• Time-dependent studies
• Concentration effects

Prompt 73 – Identify Peak Shifts

Purpose

Explain spectral shifts.

AI Prompt

Analyze the FTIR spectra and identify all significant peak shifts.

For every shifted peak discuss:

• Original position
• New position
• Shift magnitude
• Possible molecular explanation

Explain whether the shifts indicate hydrogen bonding, coordination, structural changes, or chemical reactions.

Best For

• Functionalization
• Surface modification
• Composite formation

Prompt 74 – Compare Peak Intensities

Purpose

Interpret intensity changes.

AI Prompt

Compare the peak intensities among the FTIR spectra.

Discuss:

• Stronger peaks
• Weaker peaks
• Relative changes
• Possible reasons for intensity variation

Explain whether the changes indicate compositional differences or structural modifications.

Best For

• Quantitative comparison
• Polymer blends
• Biomass conversion

Prompt 75 – Evaluate Treatment Effects

Purpose

Assess the impact of processing conditions.

AI Prompt

Compare the FTIR spectra before and after treatment.

Treatment:

[Describe treatment]

Discuss:

• Chemical changes
• Functional group evolution
• Structural modifications
• Evidence supporting successful treatment

Explain the treatment mechanism using FTIR evidence.

Best For

• Annealing
• Calcination
• Plasma treatment
• Acid treatment
• Surface activation

Prompt 76 – Compare Different Synthesis Routes

Purpose

Determine the effect of synthesis method.

AI Prompt

Compare the FTIR spectra of materials prepared using different synthesis methods.

Discuss:

• Functional group differences
• Surface chemistry
• Structural evolution
• Purity
• Residual precursor signals

Determine which synthesis route produced the highest-quality material.

Best For

• Sol-gel
• Hydrothermal
• Microwave synthesis
• Green synthesis

Prompt 77 – Correlate FTIR Differences with Material Properties

Purpose

Connect spectral differences to performance.

AI Prompt

Compare the FTIR spectra and explain how the observed chemical differences influence:

• Mechanical properties
• Thermal stability
• Corrosion resistance
• Adsorption capacity
• Catalytic activity
• Electrical conductivity

Support every conclusion using spectral evidence.

Best For

• Structure–property relationship studies
• Journal publications

Prompt 78 – Comparative Publication-Ready Discussion

Purpose

Generate a manuscript-quality comparison.

AI Prompt

Write a publication-ready comparative FTIR discussion for the following samples.

Discuss:

• Peak assignments
• Similarities
• Differences
• Structural evolution
• Chemical interactions
• Scientific significance

Use formal language suitable for submission to a Q1 journal.

Best For

• Scientific manuscripts
• Conference papers
• PhD theses

Prompt 79 – Correlate FTIR with Multiple Characterization Techniques

Purpose

Integrate FTIR with complementary analyses.

AI Prompt

Compare the FTIR spectra together with:

• XRD
• XPS
• Raman
• SEM
• TEM
• BET
• TGA

Explain how the combined characterization supports the observed structural differences between the samples.

Discuss agreements and possible inconsistencies.

Best For

• Comprehensive characterization
• High-impact publications

Prompt 80 – Expert-Level Comparative FTIR Interpretation

Purpose

Generate the most comprehensive comparison.

AI Prompt

Act as an internationally recognized FTIR spectroscopy expert.

Compare the FTIR spectra of:

[List samples]

Prepare a publication-ready discussion including:

• Complete peak assignments
• Functional group evolution
• Peak shifts
• Intensity variations
• Hydrogen bonding
• Structural modifications
• Chemical interactions
• Comparison with published literature
• Relationship between FTIR observations and material properties
• Correlation with XRD, XPS, Raman, SEM, TEM, BET, TGA, DSC, and electrochemical measurements
• Limitations of FTIR interpretation
• Recommendations for additional characterization

Write the discussion in the style of a high-impact Q1 journal.

Best For

• Advanced Materials
• ACS Applied Materials & Interfaces
• Journal of Materials Chemistry
• Chemical Engineering Journal
• Materials Today journals
• Industrial R&D

Expected Output

A publication-quality comparative analysis that systematically explains spectral similarities and differences, correlates them with material chemistry and performance, and integrates FTIR results with complementary characterization techniques to produce a robust scientific interpretation.

Scientific Writing & Publication FTIR AI Prompts (81–90)

Interpreting an FTIR spectrum is only the first step. For most researchers, the ultimate goal is to transform spectral data into a high-quality scientific publication. Whether preparing an SCI journal manuscript, responding to reviewer comments, writing a thesis, or creating a conference paper, presenting FTIR results clearly and professionally is essential.

Artificial Intelligence can significantly improve scientific writing by converting raw spectral observations into publication-ready discussions, refining technical language, ensuring logical flow, eliminating repetitive expressions, and producing text that meets the standards of high-impact journals.

The following prompts are designed specifically for researchers preparing manuscripts, dissertations, reports, and reviewer responses.

Prompt 81 – Write a Publication-Ready FTIR Discussion

Purpose

Generate a complete FTIR Results and Discussion section.

AI Prompt

Act as an internationally recognized scientific writer specializing in FTIR spectroscopy.

Using the following FTIR data:

[List peak positions]

Write a publication-ready Results and Discussion section.

The discussion should include:

• Complete peak assignments
• Functional group interpretation
• Scientific explanation
• Comparison with established FTIR principles
• Overall structural conclusions

Use formal academic English suitable for submission to a Q1 journal.

Best For

• SCI journal manuscripts
• Thesis writing
• Conference papers

Prompt 82 – Improve My Existing FTIR Discussion

Purpose

Refine existing text.

AI Prompt

Improve the following FTIR discussion.

Requirements:

• Improve scientific language.
• Remove repetition.
• Increase clarity.
• Improve logical flow.
• Make the writing suitable for a high-impact journal.
• Do not change the scientific meaning.

Text:

[Paste your discussion]

Best For

• Manuscript revision
• Journal resubmission
• Thesis editing

Prompt 83 – Write Figure Caption

Purpose

Generate professional figure captions.

AI Prompt

Write a publication-quality caption for the following FTIR figure.

The caption should describe:

• Sample name
• Experimental purpose
• Main spectral characteristics
• Significant observations

Use concise scientific language appropriate for an SCI journal.

Best For

• Journal figures
• Dissertation figures
• Conference posters

Prompt 84 – Compare with Published Literature

Purpose

Place results in scientific context.

AI Prompt

Based on the FTIR spectrum, write a discussion comparing the observed functional groups with those commonly reported in published literature.

Explain whether the results are:

• Consistent with previous studies
• Different from previous reports
• Scientifically significant

Do not fabricate references. Instead, describe the types of studies that should be cited.

Best For

• Discussion sections
• Literature comparison
• Review articles

Prompt 85 – Write Reviewer Response

Purpose

Respond to reviewer comments professionally.

AI Prompt

Act as an experienced journal editor.

Reviewer comment:

[Paste comment]

My FTIR results:

[Paste results]

Write a professional, polite, and scientifically convincing response explaining how the FTIR analysis supports the manuscript.

Use a respectful tone appropriate for SCI journals.

Best For

• Manuscript revision
• Reviewer rebuttal letters

Prompt 86 – Write FTIR Interpretation for a Thesis

Purpose

Generate dissertation-quality writing.

AI Prompt

Write a comprehensive FTIR discussion suitable for a PhD dissertation.

Include:

• Background
• Peak assignments
• Functional groups
• Scientific interpretation
• Structural implications
• Summary

Use formal academic writing while maintaining readability.

Best For

• MSc theses
• PhD dissertations

Prompt 87 – Generate a Scientific Conclusion

Purpose

Summarize FTIR findings.

AI Prompt

Based on the FTIR analysis, write a concise scientific conclusion.

Summarize:

• Major functional groups
• Structural characteristics
• Scientific significance
• Relationship to the overall study

Limit the conclusion to approximately 150–200 words.

Best For

• Manuscript conclusions
• Reports
• Abstract preparation

Prompt 88 – Write an Abstract Based on FTIR Results

Purpose

Create publication-ready abstracts.

AI Prompt

Using the FTIR interpretation below, write an abstract suitable for a scientific journal.

Include:

• Research objective
• Key FTIR findings
• Scientific significance
• Main conclusion

Keep the abstract concise, professional, and publication-ready.

Best For

• Journal submission
• Conference abstracts

Prompt 89 – Correlate FTIR with the Entire Study

Purpose

Integrate FTIR into the broader research.

AI Prompt

Interpret the FTIR results together with all other characterization techniques used in the study.

Include discussion of:

• XRD
• SEM
• TEM
• XPS
• Raman
• TGA
• BET
• Electrochemical tests (if applicable)

Explain how FTIR contributes to the overall scientific conclusions.

Best For

• Comprehensive manuscripts
• High-impact journals

Prompt 90 – Expert-Level Publication Writing

Purpose

Generate a journal-ready discussion at the highest academic standard.

AI Prompt

Act as an internationally recognized materials scientist, FTIR spectroscopy expert, and scientific editor.

Using the following FTIR data:

[Insert FTIR data]

Prepare a publication-ready Results and Discussion section that includes:

• Complete peak assignments
• Functional group identification
• Molecular structure interpretation
• Scientific reasoning
• Comparison with previous studies (without inventing references)
• Relationship with complementary characterization techniques
• Discussion of material properties
• Study limitations
• Future research directions

Write in the style of a high-impact Q1 journal such as Advanced Materials, ACS Applied Materials & Interfaces, Chemical Engineering Journal, Journal of Hazardous Materials, Corrosion Science, or Materials Today.

Best For

• High-impact journal submissions
• Major revisions
• Research proposals
• Industrial technical reports

Expected Output

A polished, publication-quality manuscript section that goes far beyond simple peak assignments, providing rigorous scientific interpretation, logical structure, and professional academic writing suitable for top-tier journals.

Advanced & Universal FTIR AI Prompts (91–100)

After mastering peak assignments, functional group identification, polymer characterization, nanomaterials, biomass, catalysts, corrosion studies, comparative analysis, and scientific writing, researchers often require flexible prompts that can be applied to virtually any FTIR spectrum.

These advanced prompts are designed to maximize the capabilities of modern AI models such as ChatGPT, Claude, Gemini, and other large language models. They combine spectroscopy expertise, materials science knowledge, scientific writing, and critical reasoning into a single prompt.

Whether you are working on polymers, ceramics, metals, nanomaterials, pharmaceuticals, catalysts, biomaterials, or environmental samples, these universal prompts can dramatically improve the quality of AI-assisted FTIR interpretation.

Prompt 91 – Universal FTIR Expert Analysis

Purpose

Generate a complete expert interpretation for any material.

AI Prompt

Act as an internationally recognized FTIR spectroscopy expert with extensive experience in materials science, chemistry, polymers, nanotechnology, environmental engineering, and biomaterials.

Analyze the following FTIR spectrum:

Material:
[Material Name]

Major peaks:
[List peak positions]

Provide:

• Complete peak assignments
• Functional group identification
• Molecular vibration explanation
• Structural interpretation
• Surface chemistry (if applicable)
• Chemical interactions
• Scientific significance
• Overall conclusions

Write the discussion in publication-ready language suitable for a Q1 journal.

Best For

• Any FTIR study
• Unknown materials
• General research

Prompt 92 – Analyze an Unknown FTIR Spectrum

Purpose

Identify possible unknown materials.

AI Prompt

Analyze the following FTIR spectrum of an unknown material.

Based solely on the observed absorption bands:

[List peaks]

Determine:

• Possible functional groups
• Likely chemical composition
• Possible material class
• Confidence level for each interpretation
• Alternative possibilities

Explain your reasoning step by step.

Avoid unsupported conclusions.

Best For

• Unknown samples
• Quality control
• Industrial analysis

Prompt 93 – Generate a Complete FTIR Report

Purpose

Create a professional report.

AI Prompt

Prepare a complete FTIR analysis report.

Include the following sections:

1. Introduction
2. Experimental overview
3. Peak assignment table
4. Functional group analysis
5. Structural interpretation
6. Scientific discussion
7. Conclusions
8. Recommendations

Write the report in professional scientific English.

Best For

• Industrial reports
• Consultancy
• Laboratory documentation

Prompt 94 – Critical Review of My FTIR Interpretation

Purpose

Evaluate existing interpretations.

AI Prompt

Critically evaluate my FTIR interpretation.

My interpretation:

[Paste text]

Identify:

• Incorrect assignments
• Weak scientific arguments
• Missing observations
• Unsupported conclusions
• Suggestions for improvement

Provide constructive scientific feedback.

Best For

• Manuscript revision
• Student supervision
• Peer review

Prompt 95 – Generate Reviewer Questions

Purpose

Prepare for peer review.

AI Prompt

Act as a reviewer for a high-impact journal.

Based on the following FTIR discussion:

[Paste discussion]

Generate ten realistic reviewer questions focusing on:

• Peak assignments
• Scientific interpretation
• Experimental evidence
• Missing analyses
• Logical consistency

Then provide model responses for each question.

Best For

• Manuscript submission
• Reviewer preparation

Prompt 96 – Integrate FTIR with Complete Characterization

Purpose

Produce a holistic scientific interpretation.

AI Prompt

Interpret the FTIR results together with:

• XRD
• SEM
• TEM
• XPS
• Raman
• BET
• TGA
• DSC
• UV–Vis
• EIS
• Mechanical testing

Explain how each characterization technique complements the FTIR findings and contributes to understanding the material.

Best For

• Comprehensive characterization studies
• High-impact journal papers

Prompt 97 – AI Research Advisor

Purpose

Receive expert research recommendations.

AI Prompt

Act as my scientific research advisor.

After interpreting the FTIR spectrum, recommend:

• Additional characterization techniques
• Control experiments
• Possible mechanisms
• Missing discussions
• Future research directions
• Publication opportunities

Provide detailed scientific reasoning for every recommendation.

Best For

• Research planning
• PhD projects
• Grant proposals

Prompt 98 – Journal Editor Mode

Purpose

Assess publication readiness.

AI Prompt

Act as the editor of a top Q1 journal.

Evaluate my FTIR Results and Discussion.

Assess:

• Scientific quality
• Novelty
• Clarity
• Organization
• Language
• Technical accuracy
• Publication readiness

Score each category from 1 to 10 and explain how the manuscript can be improved before submission.

Best For

• Final manuscript review
• Journal preparation

Prompt 99 – AI FTIR Consultant

Purpose

Obtain expert consultancy.

AI Prompt

Act as an FTIR consultant with over 20 years of experience in academia and industry.

Analyze my FTIR spectrum and provide:

• Scientific interpretation
• Practical implications
• Industrial relevance
• Potential applications
• Possible errors
• Additional experiments
• Recommendations for publication

Explain every conclusion using scientific reasoning.

Best For

• Industrial R&D
• Consultancy projects
• Advanced research

Prompt 100 – The Ultimate FTIR Master Prompt

Purpose

The most comprehensive FTIR prompt in this collection.

AI Prompt

Act as one of the world's leading experts in FTIR spectroscopy, materials science, chemistry, polymer science, nanotechnology, catalysis, corrosion engineering, environmental science, and scientific publishing.

Analyze the following FTIR spectrum:

Material:
[Material Name]

Experimental details:
[Experimental Conditions]

Observed peaks:
[List peak positions]

Generate a complete scientific interpretation including:

• Complete peak assignments
• Functional group identification
• Molecular vibration analysis
• Structural evolution
• Surface chemistry
• Chemical interactions
• Hydrogen bonding
• Crosslinking (if applicable)
• Adsorption mechanism (if applicable)
• Coordination chemistry (if applicable)
• Correlation with XRD, XPS, Raman, SEM, TEM, BET, TGA, DSC, UV–Vis, and electrochemical results
• Relationship between chemical structure and material properties
• Comparison with commonly reported findings in the scientific literature (without inventing references)
• Limitations of FTIR spectroscopy
• Recommended complementary analyses
• Publication-ready Results and Discussion
• Reviewer-level critical evaluation
• Suggestions to improve the scientific quality of the study

Write in polished academic English suitable for submission to the highest-impact journals in materials science, chemistry, nanotechnology, environmental engineering, or corrosion science.

Best For

• High-impact Q1 journals
• Nature Portfolio journals
• Advanced Materials
• ACS journals
• Elsevier flagship journals
• Wiley journals
• Springer Nature journals
• Industrial research and development
• PhD dissertations
• Scientific consulting

Expected Output

A complete, publication-quality FTIR analysis that integrates spectroscopy, chemistry, materials science, scientific writing, and critical evaluation into a single comprehensive report. This prompt is designed to produce expert-level interpretations that go far beyond basic peak assignments, helping researchers accelerate data interpretation, improve manuscript quality, and prepare work suitable for submission to leading international journals.

Final Thoughts

Artificial Intelligence is rapidly transforming how researchers analyze FTIR spectra. While AI can dramatically reduce interpretation time and improve the quality of scientific writing, it should always be used as an expert assistant rather than a replacement for scientific judgment. The most reliable results come from combining AI-generated insights with experimental evidence, domain expertise, and complementary characterization techniques.

These 100 AI prompts provide a practical toolkit for researchers working across polymers, nanomaterials, biomass, catalysts, corrosion, coatings, biomaterials, environmental science, pharmaceuticals, and advanced functional materials. By adapting these prompts to your own experiments, you can streamline data interpretation, strengthen your publications, and produce more rigorous, publication-ready FTIR analyses.

Whether you are a graduate student writing your first manuscript or an experienced researcher preparing a paper for a high-impact journal, these prompts can help you unlock the full potential of AI-assisted FTIR analysis while maintaining scientific accuracy and integrity.

20 Expert Prompt Templates

The previous 100 prompts focused on specific FTIR analysis tasks. However, experienced researchers often need flexible prompt templates that can be quickly customized for different materials, experiments, and publication goals.

These expert templates are designed to be reusable across virtually any FTIR project. Simply replace the placeholders with your own material, experimental conditions, and research objectives.