Prediction Model of Flavonoids Content in Ancient Tree Sun−Dried Green Tea under Abiotic Stress Based on LASSO−Cox
-
Published:2024-02-12
Issue:2
Volume:14
Page:296
-
ISSN:2077-0472
-
Container-title:Agriculture
-
language:en
-
Short-container-title:Agriculture
Author:
Li Lei1, Wu Yamin1, Wang Houqiao1, He Junjie1, Wang Qiaomei1, Xu Jiayi1, Xia Yuxin2, Yuan Wenxia1, Chen Shuyi1, Tao Lin3, Wang Xinghua1, Wang Baijuan1
Affiliation:
1. College of Tea Science, Yunnan Agricultural University, Kunming 650201, China 2. College of Mechanical and Electrical Engineering, Yunnan Agricultural University, Kunming 650201, China 3. Pu’er Wenbang Tea Co., Ltd., Pu’er 666500, China
Abstract
To investigate the variation in flavonoids content in ancient tree sun–dried green tea under abiotic stress environmental conditions, this study determined the flavonoids content in ancient tree sun−dried green tea and analyzed its correlation with corresponding factors such as the age, height, altitude, and soil composition of the tree. This study uses two machine−learning models, Least Absolute Shrinkage and Selection Operator (LASSO) regression and Cox regression, to build a predictive model based on the selection of effective variables. During the process, bootstrap was used to expand the dataset for single−factor and multi−factor comparative analyses, as well as for model validation, and the goodness−of−fit was assessed using the Akaike information criterion (AIC). The results showed that pH, total potassium, nitrate nitrogen, available phosphorus, hydrolytic nitrogen, and ammonium nitrogen have a high accuracy in predicting the flavonoids content of this model and have a synergistic effect on the production of flavonoids in the ancient tree tea. In this prediction model, when the flavonoids content was >6‰, the area under the curve of the training set and validation set were 0.8121 and 0.792 and, when the flavonoids content was >9‰, the area under the curve of the training set and validation set were 0.877 and 0.889, demonstrating good consistency. Compared to modeling with all significantly correlated factors (p < 0.05), the AIC decreased by 32.534%. Simultaneously, a visualization system for predicting flavonoids content in ancient tree sun−dried green tea was developed based on a nomogram model. The model was externally validated using actual measurement data and achieved an accuracy rate of 83.33%. Therefore, this study offers a scientific theoretical foundation for explaining the forecast and interference of the quality of ancient tree sun−dried green tea under abiotic stress.
Funder
Yunnan Provincial Science and Technology Department People’s Government of Yunnan Province Key Technologies Research and Development Program Major Science and Technology Projects in Yunnan Province Science Research Foundation of Yunnan Education Bureau
Reference49 articles.
1. Identifying key non-volatile compounds in ready-to-drink green tea and their impact on taste profile;Yu;Food Chem.,2014 2. Molecular definition of black tea taste by means of quantitative studies, taste reconstitution, and omission experiments;Scharbert;J. Agric. Food Chem.,2005 3. Tang, G.-Y., Zhao, C.-N., Xu, X.-Y., Gan, R.-Y., Cao, S.-Y., Liu, Q., Shang, A., Mao, Q.-Q., and Li, H.-B. (2019). Phytochemical composition and antioxidant capacity of 30 Chinese teas. Antioxidants, 8. 4. Antioxidant properties of catechins: Comparison with other antioxidants;Grzesik;Food Chem.,2018 5. Beneficial effects of flavonoids against Parkinson’s disease;Jung;J. Med. Food,2018
|
|