Near‐infrared spectroscopy coupled with Gramian angular field two‐dimensional convolutional neural network for white tea adulteration detection
Journal of the Science of Food and Agriculture · 30.08.2025 · 105 (11) · 6269-6279
DOI: 10.1002/jsfa.14353 ↗Kurz gefasst
Evaluationsstudie in der Zeitschrift Journal of the Science of Food and Agriculture, online erschienen am 23.05.2025. Verfasst von Peng Zhang und 7 weiteren Autor:innen. Beteiligte Einrichtung: College of Horticulture, Fujian Agriculture and Forestry University, Fuzhou, China. Hauptthemen laut MEDLINE: Tea, Food Contamination, Camellia sinensis. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 42 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Institute of Chinese White Tea Open Subjects, special fund for science and technology innovation of Fujian Zhang Tianfu tea development foundation (FJZTF01).
Abstract (Originalsprache)
BACKGROUND The flavor profile and product quality of white tea, heavily dependent on its place of origin, significantly influence consumers' purchasing decisions. Quantitative adulteration testing for tea origin has encountered challenges due to the poor performance in random external validation, which has severely hindered the practical application of near‐infrared (NIR) technology. RESULTS This study employs a two‐dimensional convolutional neural network (2D‐CNN) deep learning model combined with Gramian angular field (GAF) image coding technology (GAF‐2D‐CNN) to quantitatively detect geographical origin adulteration of white tea using near‐infrared spectral (NIRS) data. The results demonstrate that the GAF‐2D‐CNN model can effectively process raw spectral data and predict the untrained random adulteration ratio data with high accuracy. The average R 2 and root mean square error in the external verification of the original data reach 0.9754 and 0.0349, respectively, which meet practical production needs. Moreover, the GAF‐2D‐CNN significantly outperforms traditional regression models and 1D‐CNN models. CONCLUSION This study introduces the application of the NIR spectral image coding method in tea regression and highlights the advantages of deep learning image processing in the tea industry. © 2025 Society of Chemical Industry.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- College of Horticulture, Fujian Agriculture and Forestry University, Fuzhou, China.
- College of Mechanical and Electrical Engineering, Fujian Agriculture and Forestry University, Fuzhou, China.
- Anxi College of Tea Science, Fujian Agriculture and Forestry University, Quanzhou, China.
ORCID-Profile: Peng Zhang
Förderung
- National Natural Science Foundation of China
- Institute of Chinese White Tea Open Subjects
- special fund for science and technology innovation of Fujian Zhang Tianfu tea development foundation (FJZTF01)
- Spark Program of Fujian Provincial Department of Science and Technology (2024S0066)
Zitieren
APA
Zhang, P., Cheng, J., Chen, Q., Zheng, Z., Wei, C., Zou, T., Sun, W., & Huang, Y. (2025). Near‐infrared spectroscopy coupled with Gramian angular field two‐dimensional convolutional neural network for white tea adulteration detection. Journal of the Science of Food and Agriculture, 105(11), 6269-6279. https://doi.org/10.1002/jsfa.14353
Vancouver
Zhang P, Cheng J, Chen Q, Zheng Z, Wei C, Zou T, et al. Near‐infrared spectroscopy coupled with Gramian angular field two‐dimensional convolutional neural network for white tea adulteration detection. Journal of the Science of Food and Agriculture. 2025;105(11):6269-6279. doi:10.1002/jsfa.14353
BibTeX
@article{Zhang2025,
author = {Zhang, Peng and Cheng, Jun and Chen, Qinglan and Zheng, Zhiqiang and Wei, Chengjiang and Zou, Tengyue and Sun, Weijiang and Huang, Yan},
title = {Near‐infrared spectroscopy coupled with Gramian angular field two‐dimensional convolutional neural network for white tea adulteration detection},
journal = {Journal of the Science of Food and Agriculture},
year = {2025},
volume = {105},
number = {11},
pages = {6269--6279},
doi = {10.1002/jsfa.14353}
}
EUVIMED