ATR‐FTIR Spectroscopy and Deep Learning for Chemometric Analysis and Geographical Classification of Red Wines
Journal of Food Science · 2026
DOI: 10.1111/1750-3841.70872 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Food Science, 2026. Verfasst von Shengwei Wang und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering, Northwest Normal University, Lanzhou, China. Hauptthemen laut MEDLINE: Wine, Deep Learning. Die Arbeit nennt 52 Literaturangaben. Gefördert von: Gansu Key Research and Development Special Project for Ecological Civilization Construction, National Natural Science Foundation of China, Gansu Provincial Department of Education: Industry Support Program Project, China.
Abstract (Originalsprache)
This study leverages attenuated total reflection Fourier‐transform infrared (ATR‐FTIR) spectroscopy combined with a novel residual composite convolutional neural network (Res‐MCNN) to address the critical challenge of geographical origin authentication in red wines. By analyzing 200 samples from distinct Chinese regions (Xinjiang and Hebei), we demonstrate the efficacy of ATR‐FTIR in capturing region‐specific spectral fingerprints, particularly highlighting the role of titratable acids and phenolic compounds as discriminative markers. The proposed Res‐MCNN model integrates advanced preprocessing techniques, including competitive adaptive reweighted sampling (CARS) for wavelength selection and decision tree pooling for feature optimization, achieving an exceptional classification accuracy of 97.975%. Our findings reveal that while alcohol and sugar content variations introduce sensitivity in model performance, the robust extraction of high‐dimensional nonlinear spectral features ensures reliable origin traceability when key chemical parameters are controlled. The proposed Res‐MCNN model achieved a classification accuracy of 97.975%, a sensitivity of 98.2%, a specificity of 97.6%, and an AUC of 0.989, demonstrating highly reliable geographical discrimination performance. Furthermore, controlled experiments showed that variations in alcohol (10%–15%) and sugar content (1–20 g/L) altered accuracy by no more than 0.6%, confirming that the model maintains stable traceability performance when key chemical parameters remain within typical ranges.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- School of Computer Science and Engineering, Northwest Normal University, Lanzhou, China.
ORCID-Profile: Shengwei Wang
Förderung
- Gansu Key Research and Development Special Project for Ecological Civilization Construction
- National Natural Science Foundation of China
- Gansu Provincial Department of Education: Industry Support Program Project, China
Zitieren
APA
Wang, S., Chen, K., & Wang, Y. (2026). ATR‐FTIR Spectroscopy and Deep Learning for Chemometric Analysis and Geographical Classification of Red Wines. Journal of Food Science. https://doi.org/10.1111/1750-3841.70872
Vancouver
Wang S, Chen K, Wang Y. ATR‐FTIR Spectroscopy and Deep Learning for Chemometric Analysis and Geographical Classification of Red Wines. Journal of Food Science. 2026. doi:10.1111/1750-3841.70872
BibTeX
@article{Wang2026,
author = {Wang, Shengwei and Chen, Keda and Wang, Yize},
title = {ATR‐FTIR Spectroscopy and Deep Learning for Chemometric Analysis and Geographical Classification of Red Wines},
journal = {Journal of Food Science},
year = {2026},
doi = {10.1111/1750-3841.70872}
}
EUVIMED