Best of the Week: AI, Rapid Food Analysis, Agriculture Analysis, and Soil Property Prediction

This week, Spectroscopy published various articles that covered many topics in analytical spectroscopy. This week’s articles feature techniques including mid-infrared (MIR) spectroscopy, near-infrared (NIR) spectroscopy, and visible-NIR (vis-NIR) spectroscopy. Below, we’ve highlighted some of the most popular articles, according to our readers and subscribers. Happy reading!

AI-Powered Spectroscopy Faces Hurdles in Rapid Food Analysis

In this article, we recap a recent study that describes the challenges and limitations of AI-driven spectroscopy methods for rapid food analysis (1). The article also goes over the guidelines recommended by the authors of the study to help improve the accuracy and reliability of AI-driven spectroscopy methods in food analysis (1).

A Review of the Latest Spectroscopic Research in Agriculture Analysis

The agriculture industry uses spectroscopic techniques to analyze the health of their crops and soil. In this review article, the latest advancements in several key spectroscopic methods, including atomic, vibrational, molecular, electronic, and X-ray techniques, are described, along with a description as to how these techniques are advancing the agriculture industry (2).

Rapid Quantitative Method in the Determination of Total Flavonoids in Tibetan Medicine Meconopsis integrifolia (Maxim.) Franch. from Qinghai-Tibet Plateau by Near Infrared Spectroscopy

This peer-reviewed article focuses on developing a rapid, accurate method for evaluating the quality of Meconopsis integrifolia, a traditional Tibetan medicine, using near-infrared spectroscopy (NIR) and chemometrics. The study used 372 samples from 14 populations in the Qinghai-Tibet Plateau and measured total flavonoid content, which ranged from 1.63% to 10.17%, using both NIR and ultraviolet-visible spectrophotometry (UV-vis) (3). A quantitative model based on partial least squares was developed, yielding good calibration, validation, and cross-validation results, with a residual predictive deviation (RPD) of 3.59, indicating high predictive accuracy (3). The analysis also showed that altitude was a significant factor influencing compound accumulation, with low altitudes being more favorable (3). This model can be used for fast quality assessments of M. integrifolia, aiding its selection and use in medicine.

Non-Linear Memory-Based Learning Advances Soil Property Prediction Using vis-NIR Spectral Data

This article examines a recent study that was conducted by researchers from Zhejiang University. In their study, the researchers developed a new non-linear memory-based learning (N-MBL) model that can improve the prediction accuracy of soil properties using visible near-infrared (vis-NIR) spectroscopy (4). By comparing N-MBL with traditional machine learning and local modeling methods, the study reveals that N-MBL performs better than other traditional methods in predicting soil organic matter and total nitrogen (4).

Examining the Cheese Ripening Process with Mid-Infrared and Synchronous Fluorescence Spectroscopy

Biochemical reactions are a key part of the cheese ripening process. These reactions help give cheese its sensory attributes to help make this product more desirable for consumers.

A joint French-Canadian study examined the ripening process of Comté and cheddar cheeses, utilizing mid-infrared (mid-IR) and synchronous fluorescence spectroscopy (SFS) in their analysis (5). Christophe Cordella, a professor in the Department of Food Sciences at Laval University, Quebec, Canada, is the lead author on a paper that resulted from this work, and he spoke to Spectroscopy about his group’s efforts and the findings of their research (5).

References

(1) Workman, Jr., J. AI-Powered Spectroscopy Faces Hurdles in Rapid Food Analysis. Spectroscopy. Available at: https://www.spectroscopyonline.com/view/ai-powered-spectroscopy-faces-hurdles-in-rapid-food-analysis (accessed 2024-09-05).

(2) Workman, Jr., J. A Review of the Latest Spectroscopic Research in Agriculture Analysis. Spectroscopy. Available at: https://www.spectroscopyonline.com/view/a-review-of-the-latest-spectroscopic-research-in-agriculture-analysis (accessed 2024-09-05).

(3) Li, D.; Li, P.-P.; Long, R.; et al. Rapid Quantitative Method in the Determination of Total Flavonoids in Tibetan Medicine Meconopsis integrifolia (Maxim.) Franch. from Qinghai-Tibet Plateau by Near Infrared Spectroscopy. Spectroscopy Suppl. 2024, 39 (s8), 6–14. https://www.spectroscopyonline.com/view/rapid-quantitative-method-in-the-determination-of-total-flavonoids-in-tibetan-medicine-meconopsis-integrifolia-maxim-franch-from-qinghai-tibet-plateau-by-near-infrared-spectroscopy

(4) Workman, Jr., J. Non-Linear Memory-Based Learning Advances Soil Property Prediction Using vis-NIR Spectral Data. Spectroscopy. Available at: https://www.spectroscopyonline.com/view/non-linear-memory-based-learning-advances-soil-property-prediction-using-vis-nir-spectral-data (accessed 2024-09-05).

(5) Chasse, J. Examining the Cheese Ripening Process with Mid-Infrared and Synchronous Fluorescence Spectroscopy. Spectroscopy Suppl. 2024, 39 (s8), 16–18. https://www.spectroscopyonline.com/view/examining-the-cheese-ripening-process-with-mid-infrared-and-synchronous-fluorescence-spectroscopy