Artificial Intelligence in Spectroscopy: A Summary of Spectroscopy Magazine's Coverage, 2024–2026

Over the past two years, Spectroscopy magazine—published by MJH Life Sciences and available through Spectroscopy Online—has mounted a sustained editorial coverage to document, interpret, and explain the rapidly accelerating integration of artificial intelligence (AI) into modern spectroscopic practice. Through feature articles, two-part technical series, news reports, expert practitioner interviews, editorial reviews, and podcast episodes, the magazine has tracked a cautionary tale its editors and contributors describe as anything from “another hype” to among the most consequential advancement in the field of spectroscopy and data processing. This article synthesizes the major themes, findings, and perspectives that have emerged from our coverage.

Establishing the Foundation: Defining AI for Spectroscopists

A challenge that Spectroscopy has addressed early and repeatedly is the terminological confusion surrounding artificial intelligence (AI), machine learning (ML), deep learning (DL), and chemometrics—terms frequently used interchangeably but carrying meaningfully distinct definitions. The two-part Chemometrics in Spectroscopy column series "From Classical Regression to AI and Beyond: The Chronicles of Calibration in Spectroscopy," published in the second and seventh issues of Spectroscopy volume 40 in 2025, traced the lineage of calibration science from classical regression and principal component analysis (PCA) through partial least squares (PLS) regression and into the territory of neural networks (NNs), gradient-boosted trees, and transformer-based models.¹˒² The overarching argument was that AI methods do not simply replace classical chemometrics but extend it into domains of nonlinearity and complexity that older methods could not handle. Other views are more sober-minded stating that AI is an extension of current chemometrics tools and will mature more slowly as domain knowledge and expertise learn to properly apply these tools.

The Analytically Speaking podcast, produced jointly by Spectroscopy and LCGC, has been a particularly valuable vehicle for contextualizing these distinctions through direct conversations with leading experts. Discussions on the precise meanings of chemometrics, AI, ML, and neural networks within the context of analytical chemistry and process analysis has been explored to equip practitioners with a grounded, non-hype-driven vocabulary for navigating these technologies. A December 2024 overview article by Spectroscopy further synthesized two years of the magazine's AI-related content across its podcast archive, the Chemometrics in Spectroscopy column, and its feature and news coverage, providing readers with a curated, actively linked reference for the rapidly growing body of work.³

The Podcast Conversations: Voices from the Field

Among Spectroscopy's most distinctive contributions to this coverage has been the Analytically Speaking podcast series, which gave voice to some of the field's most accomplished practitioners in extended, substantive conversations about AI, automation, and the future of chemometrics.

In Episode 3, Spectroscopy featured Prof. Karl Booksh of the Department of Chemistry and Biochemistry at the University of Delaware—a specialist in Raman and Raman imaging, LIBS, fluorescence, portable chemical sensors, and data-driven science.⁴ Booksh discussed the National Science Foundation (NSF) workshop he was co-organizing with Prof. Barry Lavine entitled "Data-Driven Measurements and Instruments for Chemistry," an initiative aimed at defining a research agenda for portable chemical sensors for environmental, biomedical, and industrial process monitoring, and articulating the data analysis requirements such sensors demand.⁴ Booksh's core conviction, shared with the podcast audience, was that building small, reliable chemical sensors capable of field measurement is inherently more valuable than collecting samples for later laboratory analysis—a philosophy that places AI-driven data analysis directly at the point of measurement rather than after the fact. The workshop with Lavine represented a formal effort by the NSF to channel academic and industrial expertise into a coherent vision for the next generation of data-driven analytical instrumentation.

In Episode 9, Spectroscopy spoke with Prof. Rasmus Bro of the University of Copenhagen, one of the most-cited scientists in chemometrics, with (at that time) nearly 37,000 citations and an h-index of 78.⁵ Bro has spent his career developing and automating chemometric methods—including fuzzy logic, deep learning, analysis of variance, and tensor modeling—and has made most of his algorithms and datasets freely available online. The episode focused on automating advanced chemometric methods for spectroscopic data processing. Bro offered a notably measured perspective on the AI moment, cautioning that enthusiasm for ML and AI often leads practitioners to believe they no longer need to think carefully about experimental design, sampling error, and analytical quality. "When that happens," he observed, "those projects typically fail, because these new and excellent methods don't actually replace the responsibility for you to actually know what you are doing."⁵ It is a warning that Spectroscopy returned to throughout its broader coverage—enthusiasm for AI must be paired with rigorous analytical discipline.

In Episode 31, Spectroscopy spoke with Dr. Barry M. Wise, Founder and President of Eigenvector Research, Inc., about the meaning and relationships among chemometrics, artificial intelligence, machine learning, and neural networks within the context of analytical chemistry and process analysis.⁶ The conversation placed the new wave of AI techniques in perspective from a guest who has been at the heart of chemometrics and software development for decades. Wise addressed a persistent tension in terminology: chemometrics — the discipline using mathematical and statistical methods to extract maximum chemical information from data — remains little known even among chemistry graduates, while "artificial intelligence" draws considerable managerial enthusiasm despite often describing tasks that well-established chemometric methods already handle. He observed that most modern AI tools are designed for big data sets involving millions of samples and data structures not typical of process analysis or analytical chemistry—a mismatch practitioners should weigh carefully before adopting the latest advanced methods. The episode offers a grounding reference for scientists seeking clarity on what AI actually adds to the analytical chemist's toolkit.

In Episode 33, Spectroscopy hosted Dr. Brian G. Rohrback, President of Infometrix, Inc., who has been active in chemometrics research and developing software for complex calibrations and multivariate data analysis since 1983.⁷ Infometrix was co-founded in 1978 by the pioneering chemometrician Profs. Bruce Kowalski and Gerry Erickson, and Rohrback has led the company's decades-long effort to automate the calibration process for optical spectrometers. The episode, titled "Automating Multivariate Calibrations: Chronicling the Steps for Replacing the Human Brain in Most Calibration Situations," addressed one of the central practical challenges in applied spectroscopy: the gap between the growing power of chemometric and ML methods and the scarcity of trained chemometricians available to implement them in industrial and laboratory settings.⁷ Rohrback described Infometrix's Ai-Metrix platform, which automates the installation and maintenance of multivariate calibration models for any optical spectrometer and any application—an embodiment of the principle that ML can encode expert best practices and make them accessible without deep specialist training. Taken together, these three podcast conversations—with Booksh and Lavine's agenda-setting NSF vision, Bro's automated algorithms and measured cautions, and Rohrback's decades of practical automation—gave Spectroscopy's readers a rare window into the debates and convictions shaping the field's direction from research conception to industrial deployment.

Honoring the Founders: Bruce R. Kowalski and the Origins of Chemometrics

Running through Spectroscopy's AI coverage is a consistent effort to situate modern developments in their historical context—and no figure looms larger in that history than Bruce R. Kowalski (1942–2012). In the September/October 2025 issue, Spectroscopy published "Bruce R. Kowalski: The Maverick Mind Behind Chemometrics" as part of its Icons of Spectroscopy series.⁸ The article described Kowalski as the pioneering analytical chemist who, more than any other individual, established chemometrics as a formal scientific discipline—integrating advanced mathematics with chemistry to extract meaningful information from complex spectroscopic datasets.

Spectroscopy documented Kowalski's foundational contributions: co-founding the International Chemometrics Society with Svante Wold in 1974; co-founding the Journal of Chemometrics; co-founding Infometrix (the company later led by Brian Rohrback); and developing landmark theoretical frameworks including the Theory of Analytical Chemistry and tensorial calibration methods for first- and second-order data. His laboratory at the University of Washington trained many of the researchers who now lead the field—including Rasmus Bro, who co-authored a major review of chemometrics applied to spectroscopy with Kowalski in 1996, and Karl Booksh, whose theoretical work on the net analyte signal was developed in direct collaboration with Kowalski.⁸ By honoring Kowalski in an issue otherwise centered on the AI transformation of chemometrics, Spectroscopy made an implicit but powerful argument: the algorithmic revolution underway is not a rupture with the past but a fulfillment of the vision Kowalski pursued throughout his career—making chemical data analysis powerful, systematic, and universally accessible.

Chemometrics in the AI Era: Reviews and Research

Beyond its podcast conversations and historical tribute, Spectroscopy published an extensive body of review and research-oriented content surveying the state of AI-driven chemometrics. In a two-part series published in November 2025, Spectroscopy offered a comprehensive assessment of recent research in chemometrics and AI.^9˒10 Part I established definitional and conceptual foundations, explaining how traditional chemometric methods such as PCA and PLS regression are now enhanced by ML, DL, and generative AI—automating feature extraction and handling nonlinear data more effectively than their predecessors. Part II examined emerging applications, with emphasis on explainable AI (XAI), generative modeling, and multimodal deep learning frameworks deployed across food safety, biomedical diagnostics, and environmental monitoring.

A companion article surveyed how AI and ML are reshaping chemometrics' mathematical infrastructure, enabling the handling of complex, high-dimensional data sets with algorithms that were inconceivable when PCA was first introduced.¹¹ Spectroscopy also published a dedicated glossary of generative AI terms for spectroscopy in early 2026, equipping practitioners with a standardized vocabulary for tools such as variational autoencoders (VAEs), generative adversarial networks (GANs), and transformer architectures.¹² Grounding this in industrial reality, Spectroscopy reported on the concept of an Expert Calibration System (ECS) for spectroscopic process analytical chemistry—an AI-assisted framework for automating calibration model construction that draws directly on the intellectual lineage running from Kowalski and Booksh through Rohrback.⁷

Explainable AI: The Interpretability Imperative

One of the most persistent themes in Spectroscopy's AI coverage has been the tension between predictive power and interpretability. Neural networks and deep learning models can classify spectra and predict chemical properties with remarkable accuracy, but they have long been criticized as "black boxes"—opaque to scientists who need to understand why a model reached a particular conclusion. Spectroscopy editorial coverage tried to address the coverage of this problem from multiple angles.

In October 2025, Spectroscopy published an article examining how explainable AI is transforming spectroscopy, followed by a full tutorial titled "Demystifying the Black Box: Making Machine Learning Models Explainable in Spectroscopy."¹³ The tutorial provided in-depth discussion of XAI methods such as SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations), which help identify which spectral regions most influence a model's predictions. High-dimensional data and nonlinear models complicate feature attribution, the article noted, and both SHAP and LIME lack standardized metrics for assessing chemical relevance. Future research, it argued, should focus on scalable XAI algorithms that integrate domain knowledge and on hybrid models balancing predictive accuracy with scientific transparency. Spectroscopy also reported on scholarly work providing a broader review of (Explainable AI) XAI specifically for spectroscopy data, signaling to readers that the research community was converging on interpretability as a shared priority.¹³ The magazine's coverage of the agricultural sector echoed this theme: a news article on explainable AI in agriculture summarized a systematic review showing how XAI techniques improve transparency and trust in AI-driven quality assessment using NIR and Raman spectroscopy.¹⁴

Generative AI: Synthesizing Spectra and Solving Inverse Problems

Among the most forward-looking threads in Spectroscopy's recent coverage is the emergence of generative AI as a tool not just for analyzing spectra but for creating them. The magazine's 2025 and 2026 reporting described how generative models can synthesize realistic training spectra to address the chronic problem of scarce labeled data, solve the inverse problem of inferring chemical structure from measured spectra, and accelerate materials and molecular modeling discovery.

Spectroscopy's early 2026 glossary and review of generative AI described how these models synthesize realistic spectra, solve inverse spectral problems, and automate molecular structural elucidation.¹² A separate article, "From Calibration to Interpretation: How Generative AI Is Rewriting Chemical Measurement," framed the forward/inverse paradigm more broadly—explaining how physics-informed Variational Autoencoders (VAEs) embed Beer–Lambert law and scattering theory directly into their latent spaces, and how transformer-based models map molecular identifiers (SMILES and InChI strings) to spectral fingerprints for end-to-end structure elucidation.¹⁵ A notable milestone covered by Spectroscopy was SpectroGen—a physics-informed variational autoencoder published in the journal Matter at the close of 2025—which embeds analytical spectral line-shape distributions directly into its latent space, demonstrating near-perfect fidelity while remaining physically interpretable.¹²

Vibrational Spectroscopy: Raman, NIR, FT-IR, and Hyperspectral Imaging

Spectroscopy's coverage of AI applications across specific spectroscopic techniques was extensive throughout 2024 and 2025, documenting AI's impact on Raman spectroscopy, near-infrared (NIR) analysis, Fourier transform infrared (FT-IR) spectroscopy, and hyperspectral imaging (HSI)—individually and in multimodal combinations.

In a year-end review of 2025's most important vibrational spectroscopy trends, Spectroscopy described a period marked by the convergence of deep learning, advanced simulation, and portable instrumentation.¹⁶ Key achievements documented include deep-learning Raman detection of microplastics in environmental samples; soil carbon quantification using mid-infrared (MIR) convolutional neural networks (CNNs); surface-enhanced Raman spectroscopy (SERS) combined with AI classifiers for biomedical diagnostics; and NIR-based explosive detection enhanced by ML models. Transformer-based models and tools like Vib2Mol set new benchmarks in spectrum-to-structure prediction. Spectroscopy also reported on research showing AI reshaping the study of molecular vibrations and phonon dynamics across infrared, Raman, neutron, and X-ray scattering techniques,¹⁷ and documented AI-driven product advances in vibrational and atomic spectroscopy from 2025 to 2026 describing the field as evolving toward an integrated, intelligent ecosystem enabling higher sensitivity, miniaturization, multimodal analysis, and real-time decision-making.¹⁸

Biomedical and Clinical Applications

The clinical dimension of AI-powered spectroscopy received sustained attention in Spectroscopy's coverage. In early 2025, Spectroscopy published an interview with Juergen Popp of the Leibniz Institute for Photonic Technology on AI-enhanced Raman spectroscopy for tumor classification, describing how AI-interpreted Raman spectra are mapping tumor microenvironments and supporting treatment selection for patient-specific immunotherapy strategies.¹⁹ Spectroscopy also reported on a landmark review in Journal of Pharmaceutical Analysis summarizing how AI-guided Raman spectroscopy is advancing biomedical applications from drug component detection to disease biomarker identification.²⁰ Wearable SERS "smart skin" sensors received dedicated coverage as a potential platform for molecular-level wearable medicine.¹⁶

Food Safety, Agriculture, and Environmental Monitoring

Spectroscopy's news and feature coverage documented extensive AI applications in food safety and agriculture. Spectroscopy reported that AI-powered spectroscopy faces specific hurdles in rapid food analysis—including variability in sample matrices and the challenge of generalizing calibration models across different growing regions and seasons.²¹ Additional reports covered the application of random forest ML algorithms combined with Raman spectroscopy for detecting sweeteners in food, and the use of NIR hyperspectral imaging combined with AI to estimate soil moisture from drone-mounted platforms. Environmental monitoring also featured prominently: between 2024 and 2026, Spectroscopy documented how NIR, FT-IR, and Raman spectroscopy are being deployed to address microplastics contamination, soil organic matter quantification, indoor air quality monitoring, and pesticide residue detection.¹⁶ A news article on AI and ML in water quality assessment summarized peer-reviewed findings in TrAC Trends in Analytical Chemistry showing how these technologies can improve detection of pollutants and waterborne pathogens.²²

Autonomous Laboratories and Real-Time Analysis

A forward-looking strand of Spectroscopy's coverage focused on the emergence of autonomous analytical laboratories in which AI-powered spectroscopy systems operate without continuous human intervention. Spectroscopy reported on IR-Bot—an autonomous robotic system for real-time chemical mixture analysis using infrared spectroscopy and ML—whose explainable ML component identified influential vibrational features such as carbon–boron and carbonyl stretching modes while quantifying mixture compositions in real time, demonstrating that autonomous analysis need not sacrifice interpretability for speed.²³ Coverage of symbiotic AI in polymer chemistry and spectroscopy described self-driving laboratories integrating high-throughput experimentation, robotics, and machine learning to explore chemical space with unprecedented efficiency.²⁴ A 2026 Pittcon symposium covered by Spectroscopy—the James L. Waters Symposium on "Generative AI in the Analytical Chemist's Toolbox for Chemical Measurements"—reflected the field's growing institutional recognition of generative AI as a new and practical laboratory tool.²⁵

Pharmaceuticals and the Regulatory Frontier

Spectroscopy's coverage included the pharmaceutical sector's unique regulatory considerations. A contribution from the United States Pharmacopeia (USP) discussed how data-driven methodologies are set to transform pharmaceutical spectroscopy in 2026 and beyond—particularly in the context of USP standards development and the challenge of incorporating AI into validated analytical workflows.²⁶ Spectroscopy also reviewed pharmaceutical spectroscopy research capturing how NIR, Raman, and other techniques are increasingly paired with ML for in-line process monitoring in pharmaceutical bioprocessing, driven by Process Analytical Technology (PAT) initiatives.²⁷

Looking Ahead: Challenges and the Path to Intelligent Spectroscopy

Across its two years of coverage, Spectroscopy has been consistent in identifying the challenges that remain between the current state of AI in spectroscopy and the fully autonomous, interpretable, and scalable systems that researchers envision. These include the absence of universal, curated spectral databases; domain-specific interpretability gaps; regulatory acceptance of AI-driven results in clinical and industrial settings; and the need for physics-aware models that do not sacrifice chemical accuracy for predictive performance.

The magazine has also consistently highlighted the tools and frameworks emerging to address these challenges. Open-source platforms such as SpectraML are described as essential for standardization and reproducibility in AI-driven chemometrics.^9˒10 Foundation models—large, pre-trained architectures adaptable to specific spectroscopic tasks with minimal labeled data—and multimodal reasoning systems are identified as the most transformative near-term developments.¹⁶ The thread connecting all of it—from Kowalski's early theoretical frameworks, through Booksh and Lavine's vision of portable data-driven sensors, through Bro's algorithms for automated chemometric modeling, through Wise’s and Rohrback's decades of practical calibration application and automation, and into today's deep learning and generative AI systems—is a single enduring aspiration: to make chemical measurement smarter, faster, and more accessible, without ever abandoning the scientific rigor that gives those measurements meaning.

References

(1) Workman, J., Jr.; Mark, H. From Classical Regression to AI and Beyond: The Chronicles of Calibration in Spectroscopy: Part I. Spectroscopy 2025, 40 (2), 13–18. DOI: 10.56530/spectroscopy.pu3090t7

(2) Workman, J., Jr.; Mark, H. From Classical Regression to AI and Beyond: The Chronicles of Calibration in Spectroscopy: Part II. Spectroscopy 2025, 40 (7), 6–10. DOI: 10.56530/spectroscopy.fc1076p9

(3) Workman, J., Jr. AI, Deep Learning, and Machine Learning in the Dynamic World of Spectroscopy. Spectroscopy Online, December 2, 2024. https://www.spectroscopyonline.com/view/ai-deep-learning-and-machine-learning-in-the-dynamic-world-of-spectroscopy (accessed May 13, 2026).

(4) Workman, J., Jr. Ep. 3: The Future of Chemometrics—Data-Driven Measurements and Instruments for Chemistry. Analytically Speaking Podcast, Spectroscopy/LCGC, Episode 3. https://www.spectroscopyonline.com/view/ep-3-the-future-of-chemometrics-data-driven-measurements-and-instruments-for-chemistry (accessed May 13, 2026).

(5) Workman, J., Jr. Ep. 9: Automating Advanced Chemometric Methods for Data Processing. Analytically Speaking Podcast, Spectroscopy/LCGC, Episode 9. https://www.spectroscopyonline.com/view/ep-9-automating-advanced-chemometric-methods-for-data-processing (accessed May 13, 2026).

(6) Workman, J., Jr. Ep. 31: Clarifying the Meaning of Chemometrics, Artificial Intelligence (AI), Machine Learning (ML), and Neural Networks (NNs). Analytically Speaking Podcast, Spectroscopy/LCGC, Episode 31. https://www.spectroscopyonline.com/view/ep-31-clarifying-the-meaning-of-chemometrics-artificial-intelligence-ai-machine-learning-ml-and-neural-networks-nns (accessed May 13, 2026).

(7) Workman, J., Jr. Ep. 33: Automating Multivariate Calibrations: Chronicling the Steps for Replacing the Human Brain in Most Calibration Situations. Analytically Speaking Podcast, Spectroscopy/LCGC, Episode 33. https://www.spectroscopyonline.com/view/ep-33-automating-multivariate-calibrations-chronicling-the-steps-for-replacing-the-human-brain-in-most-calibration-situations (accessed May 13, 2026).

(8) Workman, J., Jr. Bruce R. Kowalski: The Maverick Mind Behind Chemometrics. Spectroscopy 2025, 40 (7). DOI: 10.56530/spectroscopy.jc2281k1.

(9) Workman, J., Jr. Recent Research in Chemometrics and AI for Spectroscopy, Part I: Foundations, Definitions, and the Integration of Artificial Intelligence in Chemometric Analysis. Spectroscopy Online, November 3, 2025. https://www.spectroscopyonline.com/view/recent-research-in-chemometrics-and-ai-for-spectroscopy-part-i-foundations-definitions-and-the-integration-of-artificial-intelligence-in-chemometric-analysis (accessed May 13, 2026).

(10) Workman, J., Jr. Recent Research in Chemometrics and AI for Spectroscopy, Part II: Emerging Applications, Explainable AI, and Future Trends. Spectroscopy Online, November 4, 2025. https://www.spectroscopyonline.com/view/recent-research-in-chemometrics-and-ai-for-spectroscopy-part-ii-emerging-applications-explainable-ai-and-future-trends (accessed May 13, 2026).

(11) Workman, J., Jr. The Evolution of Chemometrics: From Classical Statistics to the AI Era. Spectroscopy Online, 2025. https://www.spectroscopyonline.com/view/the-evolution-of-chemometrics-from-classical-statistics-to-the-ai-era (accessed May 13, 2026).

(12) Workman, J., Jr. Generative Artificial Intelligence in Spectroscopy: What's New and a Glossary of Terms. Spectroscopy Online, 2026. https://www.spectroscopyonline.com/view/generative-artificial-intelligence-in-spectroscopy-what-s-new-and-a-glossary-of-terms (accessed May 13, 2026).

(13) Workman, J., Jr. Demystifying the Black Box: Making Machine Learning Models Explainable in Spectroscopy. Spectroscopy Online, 2025. https://www.spectroscopyonline.com/view/demystifying-the-black-box-making-machine-learning-models-explainable-in-spectroscopy (accessed May 13, 2026).

(14) Wetzel, W. The Role of Explainable AI in Agriculture. Spectroscopy Online, 2025. https://www.spectroscopyonline.com/view/the-role-of-explainable-ai-in-agriculture (accessed May 13, 2026).

(15) Workman, J., Jr. From Calibration to Interpretation: How Generative AI Is Rewriting Chemical Measurement. Spectroscopy Online, 2026. https://www.spectroscopyonline.com/view/from-calibration-to-interpretation-how-generative-ai-is-rewriting-chemical-measurement (accessed May 13, 2026).

(16) Workman, J., Jr. AI Developments That Changed Vibrational Spectroscopy in 2025. Spectroscopy Online, 2025. https://www.spectroscopyonline.com/view/ai-developments-that-changed-vibrational-spectroscopy-in-2025 (accessed May 13, 2026).

(17) Workman, J., Jr. AI Shakes Up Spectroscopy as New Tools Reveal the Secret Life of Molecules. Spectroscopy Online, 2025. https://www.spectroscopyonline.com/view/ai-shakes-up-spectroscopy-as-new-tools-reveal-the-secret-life-of-molecules (accessed May 13, 2026).

(18) Workman, J., Jr. New Product Advances in Vibrational and Atomic Spectroscopy (2025–2026). Spectroscopy Online, 2026. https://www.spectroscopyonline.com/view/new-product-advances-in-vibrational-and-atomic-spectroscopy-2025-2026- (accessed May 13, 2026).

(19) Wetzel, W. Enhancing Tumor Classification with AI and Raman: A Conversation with Juergen Popp. Spectroscopy Online, 2025. https://www.spectroscopyonline.com/view/enhancing-tumor-classification-with-ai-and-raman-a-conversation-with-juergen-popp (accessed May 13, 2026).

(20) Wetzel, W. AI-Powered Raman Spectroscopy Signals New Era for Drug Development and Disease Diagnosis. Spectroscopy Online, 2025. https://www.spectroscopyonline.com/view/ai-powered-raman-spectroscopy-signals-new-era-for-drug-development-and-disease-diagnosis (accessed May 13, 2026).

(21) Workman, J., Jr. AI-Powered Spectroscopy Faces Hurdles in Rapid Food Analysis. Spectroscopy Online, 2024. https://www.spectroscopyonline.com/view/ai-powered-spectroscopy-faces-hurdles-in-rapid-food-analysis (accessed May 13, 2026).

(22) Wetzel, W. Artificial Intelligence and Machine Learning: Assessing Water Quality. Spectroscopy Online, 2024. https://www.spectroscopyonline.com/view/artificial-intelligence-and-machine-learning-assessing-water-quality (accessed May 13, 2026).

(23) Workman, J., Jr. AI-Powered 'IR-Bot' Brings Real-Time Spectrochemical Analysis to Autonomous Labs. Spectroscopy Online, 2025. https://www.spectroscopyonline.com/view/ai-powered-ir-bot-brings-real-time-spectrochemical-analysis-to-autonomous-labs (accessed May 13, 2026).

(24) Workman, J., Jr. Humans and Machines Unite Using Symbiotic AI to Transform Polymer Chemistry and Spectroscopy. Spectroscopy Online, 2025. https://www.spectroscopyonline.com/view/humans-and-machines-unite-using-symbiotic-ai-to-transform-polymer-chemistry-and-spectroscopy (accessed May 13, 2026).

(25) Workman, J., Jr. Pittcon 2026 Preview: The James L. Waters Annual Symposium Explores Generative AI in Chemical Measurements. Spectroscopy Online, 2026. https://www.spectroscopyonline.com/view/pittcon-2026-preview-the-james-l-waters-annual-symposium-explores-generative-ai-in-chemical-measurements (accessed May 13, 2026).

(26) Liu, Y.; Wetzel, W. How Will Spectroscopy Benefit from Data-Driven Approaches? Spectroscopy Online, December 22, 2025. https://www.spectroscopyonline.com/view/how-will-spectroscopy-benefit-from-data-driven-approaches (accessed May 13, 2026).

(27) Workman, J., Jr. A Review of the Latest Spectroscopic Research in Pharmaceutical and Biopharmaceutical Applications. Spectroscopy 2024, 39 (6), 25–29. DOI: 10.56530/spectroscopy.at8171q5.