This “Chemometrics in Spectroscopy” column traces the historical and technical development of these methods, emphasizing their application in calibrating spectrophotometers for predicting measured sample chemical or physical properties—particularly in near-infrared (NIR), infrared (IR), Raman, and atomic spectroscopy—and explores how AI and deep learning are reshaping the spectroscopic landscape.
Researchers at Zhengzhou Police University have developed an AI-powered Raman spectroscopy method that achieves 100% accuracy in identifying plastic beverage bottles.
Researchers from Jiangsu University review advancements in computer vision and spectroscopy for non-destructive citrus quality assessment, highlighting the role of AI, automation, and portable spectrometers in improving efficiency, accuracy, and accessibility in the citrus industry.
Researchers have developed a novel approach to improve the accuracy of near-infrared spectroscopy (NIRS or NIR) in quantifying highly porous, patient-specific drug formulations. By combining machine learning with advanced Raman imaging, the study enhances the precision of non-destructive pharmaceutical analysis, paving the way for better personalized medicine.
Researchers have successfully demonstrated that human nails can serve as a reliable biological matrix for detecting fentanyl use. By combining attenuated total reflectance-Fourier transform infrared (ATR FT-IR) spectroscopy with machine learning, the study achieved over 80% accuracy in distinguishing fentanyl users from non-users. These findings highlight a promising, noninvasive method for toxicological and forensic analysis.
Scientists from China and Finland have developed an advanced method for detecting cardiovascular drugs in blood using surface-enhanced Raman spectroscopy (SERS) and artificial intelligence (AI). This innovative approach, which employs "molecular hooks" to selectively capture drug molecules, enables rapid and precise analysis, offering a potential advance for real-time clinical diagnostics.
Top articles published this week include a video interview that explores using label-free spectroscopic techniques for tumor classification, an interview discussing how near-infrared (NIR) spectroscopy can classify different types of horsetails, and a news article about detecting colorless microplastics (MPs) using NIR spectroscopy and machine learning (ML).
Spectroscopy sat down with Juergen Popp of the Leibniz Institute for Photonic Technology to talk about the Photonics West Conference, as well as his work using label-free spectroscopy techniques for precise tumor margin control.
This new study highlights the potential of visible-near-infrared (Vis-NIR) spectroscopy for predicting phosphorus sorption parameters.
Researchers have developed a small near-infrared (NIR) spectrometer dedicated to achieve painless, accurate glucose measurements.
A research team is claiming significantly enhanced accuracy of non-invasive blood-glucose testing by upgrading Fourier transform infrared spectroscopy (FT-IR) with multiple-reflections, quantum cascade lasers, two-dimensional correlation spectroscopy, and machine learning. The study, published in Spectrochimica Acta Part A, reports achieving a record-breaking 98.8% accuracy, surpassing previous benchmarks for non-invasive glucose detection.
A team of researchers from Nankai University has developed an advanced method to classify tea types using near-infrared spectroscopy (NIRS) and artificial intelligence (AI). Their approach, involves a fine-tuned 1DResNet model, outperforms traditional methods, and offers an accurate, non-destructive, and efficient classification solution for the tea industry.
Researchers have explored the potential of combining near-infrared spectroscopy (NIRS) with machine learning (ML) to create a non-invasive, rapid diagnostic tool for liver fibrosis detection, a key factor in transplant surgery planning. These approaches could offer a more accurate and accessible alternative to traditional methods like biopsy.
Scientists demonstrate a self-supervised learning framework that dramatically improves near-infrared spectroscopy classification results, even with minimal labeled data.
A new study published in Food Control introduces an approach for assessing antioxidant levels in edible oils using artificial intelligence and spectroscopy, offering significant potential for improving food quality control.
A recent study combines hyperspectral imaging (HSI) technology with chemometrics to deliver improved quality control of black garlic.
A recent study developed an accurate, non-destructive geo-traceability method using NIR spectroscopy and machine learning to authenticate the geographic origins of Gastrodia elata Bl.
A recent study used surface-enhanced Raman spectroscopy (SERS) combined with chemometrics to assess polycyclic aromatic hydrocarbons (PAHs) in water.
A recent study examined how Raman spectroscopy, when combined with machine learning (ML), can detect and analyze fertilizer nutrients.
In this study, laser-induced breakdown spectroscopy (LIBS) was applied in conjunction with principal component analysis (PCA) to identify and classify flower species.
A recent review article explores the evolving landscape of pigment analysis in cultural heritage (CH).
Over the past two years Spectroscopy Magazine has increased our coverage of artificial intelligence (AI), deep learning (DL), and machine learning (ML) and the mathematical approaches relevant to the AI topic. In this article we summarize AI coverage and provide the reference links for a series of selected articles specifically examining these subjects. The resources highlighted in this overview article include those from the Analytically Speaking podcasts, the Chemometrics in Spectroscopy column, and various feature articles and news stories published in Spectroscopy. Here, we provide active links to each of the full articles or podcasts resident on the Spectroscopy website.
Researchers have developed a novel method combining near-infrared (NIR) and mid-infrared (MIR) diffuse reflectance spectroscopy with advanced data fusion techniques to improve the accuracy of non-structural carbohydrate estimation in diverse tree tissues, advancing carbon cycle research.
A recent study presents a new technique that combines femtosecond double-pulse laser-induced breakdown spectroscopy (fs-DP-LIBS) with machine learning (ML) algorithms to significantly enhance tissue discrimination and signal quality, paving the way for more precise biomedical diagnostics.
