Data Analytics, Statistics, Chemometrics, and Artificial Intelligence

A recent review article explored the Brazilian coffee industry and how spectroscopic- and chemometrics-based approaches are helping to ensure the authenticity and quality of Brazilian coffee.

Top articles published this week include a peer-reviewed article that discuss two multivariate calibration algorithms for the spectrophotometric analysis of a drug containing antazoline hydrochloride (AN) and naphazoline hydrochloride (NP), an article about chemometric calibrations, and a feature about the 2024 Emerging Leader in Molecular Spectroscopy awardee.

This study applied principal component regression (PCR) and partial least squares (PLS) algorithms for the spectrophotometric analysis of a drug containing antazoline hydrochloride (AN) and naphazoline hydrochloride (NP) without chemical separation. Both methods showed high accuracy and precision, with results closely matching those from a reference HPLC method, and were successfully validated for analyzing commercial pharmaceutical products.

This column is the continuation of our previous column that describes and explains some algorithms and data transforms beyond those most commonly used. We present and discuss algorithms that are rarely, if ever, seen or used in practice, despite that they have been proposed and described in the literature.

The advent of artificial intelligence (AI) and machine learning (ML) has propelled spectroscopic instrumentation to new heights.

Some of the most recent articles in data analytics, statistics, machine learning, and artificial intelligence are presented below.

A recent study in beverage analysis showcased the capability of a new electronic tongue (e-tongue) prototype in analyzing liquid samples such as coconut water.

Top articles published this week include a preview of our upcoming “The Future of Forensic Analysis” e-book, a few select offerings from “The Future of Forensic Analysis,” and a news story about next-generation mineral identification.

A recent review article evaluates how artificial intelligence (AI) and machine learning (ML) are being used to assess water quality.

A pioneering study integrates laser-induced breakdown spectroscopy (LIBS) with Raman spectroscopy (RS) and applies machine learning (ML) to achieve exceptional accuracy in mineral identification. The combined approach not only leverages the strengths of both techniques but also enhances classification precision, achieving up to 98.4% accuracy.

This article offers some insight into using attenuated total reflectance Fourier transform infrared (ATR FT-IR) spectroscopy at crime scenes.

A recent study reveals on the challenges and limitations of AI-driven spectroscopy methods for rapid food analysis. Despite the promise of these technologies, issues like small sample sizes, misuse of advanced modeling techniques, and validation problems hinder their effectiveness. The authors suggest guidelines for improving accuracy and reliability in both research and industrial settings.

Researchers from Zhejiang University have developed a new non-linear memory-based learning (N-MBL) model that enhances the prediction accuracy of soil properties using visible near-infrared (vis-NIR) spectroscopy. By comparing N-MBL with traditional machine learning and local modeling methods, the study reveals its superior performance, particularly in predicting soil organic matter and total nitrogen.

Food authentication is becoming increasingly important. In this article, the editors of Spectroscopy outline the methodology used in a recent study used to analyze paprika.

By providing automated tools and guidance, an ECS would aim to streamline the calibration process, improve calibration transfer, enhance operator efficiency, and improve the overall consistency and reliability of analytical results produced using advanced chemometrics and machine earning techniques.

A recent study from Sichuan, China, leveraged a few spectroscopic techniques with chemometrics to analyze key components of the beer brewing process.

Here, we spotlight a few recent studies that explored the integration of artificial intelligence (AI) with spectroscopic techniques.

Artificial intelligence (AI) is reshaping analytical chemistry by enhancing data analysis and optimizing experimental methods. This study explores AI's advancements, challenges, and future directions in the field, emphasizing its transformative potential and the need for ethical considerations.

Researchers have proposed an innovative approach to tackling fluorescence interference in Raman spectroscopy by using LEGO blocks as standard samples. This new method offers a low-cost, rugged, and reproducible alternative to the complex liquid mixtures traditionally used in such studies, marking a significant advancement in the field of spectroscopic analysis.

Harun Hano, Charles H. Lawrie, and Beatriz Suarez, et al. from the Department of Physics at the University of the Basque Country (UPV/EHU), in Spain; and the IKERBASQUE─Basque Foundation for Science in Spain have published a research paper in the journal ACS Omega describing the use of Raman spectroscopy with specialized data treatment for the diagnosis of lung cancer.

A recent study from Central South University in China examined how to assess cobalt content in soil.

Korean scientists recently tested a new light detection and ranging (LiDAR)-based system for improving autonomous recognition systems.

The emergence of artificial intelligence (AI) has revolutionized spectroscopic techniques, including surface-enhanced Raman spectroscopy (SERS).

A recent study examined two chemometric methods for generating prediction rules.

Henan University scientists recently developed a new deep learning-based prediction model for classifying nonclassical secreted proteins.

Scientists at Saint Petersburg Electrotechnical University introduced a new method for leveraging Fourier Transform Infrared Reflection Anisotropy Spectroscopy for the analysis of semiconductors.

Researchers at the Leibniz Institute of Photonic Technology have developed a rapid method to correct infrared attenuated total reflection (ATR) infrared spectra, essential for accurate analysis in various scientific fields. By bypassing iterative processes, this approach enhances efficiency and precision.

Researchers from Tsinghua University and Beihang University in Beijing have developed a deep-learning-based data processing framework that significantly improves the accuracy of dual-comb absorption spectroscopy (DCAS) in gas quantification analysis. By using a U-net model for etalon removal and a modified U-net combined with traditional methods for baseline extraction, their framework achieves high-fidelity absorbance spectra, even in challenging conditions with complex baselines and etalon effects.

A Researcher from Lomonosov Moscow State University has developed a convolutional neural network (CNN) model for Fourier transform infrared (FT-IR) spectra recognition. This AI-based system is capable of classifying 17 functional groups and 72 coupling oscillations with remarkable accuracy, providing a significant boost to material analysis in fields like organic chemistry, materials science, and biology.

Two researchers hailing from Wageningen University and the Norwegian University of Life Sciences collaborated on a new method that improves on existing multilinear predictive modeling methods.