Predictive geographical authentication of green tea with protected designation of origin using a random forest model. (January 2020)

• Record Type: Journal Article
• Authors: Deng, Xunfei; Liu, Zhi; Zhan, Yu; Ni, Kang; Zhang, Yongzhi; Ma, Wanzhu; Shao, Shengzhi; Lv, Xiaonan; Yuan, Yuwei; Rogers, Karyne M.
• Is Part Of: Food control. Volume 107(2020)
• Publication Date: 2020-01
• Subjects: Geographical origin -- Green tea -- Random forest -- Geochemical proxies -- Predictive model -- Classification; Food -- Quality -- Periodicals; Food -- Analysis -- Periodicals; Food handling -- Periodicals; Food industry and trade -- Quality control -- Periodicals; Aliments -- Industrie et commerce -- Qualité -- Contrôle -- Périodiques; Aliments -- Qualité -- Périodiques; Aliments -- Analyse -- Périodiques; Hygiène alimentaire -- Périodiques; Food -- Analysis; Food handling; Food -- Quality; Periodicals; Electronic journals; 664.07
• DOI: 10.1016/j.foodcont.2019.106807
• Languages: English
• ISSNs: 0956-7135

Abstract

Abstract: Reliable origin authentication methods are critical for protecting high-value food products with designated geographical origins. A total of 623 tea samples were collected from important green tea production regions around China from 2012 to 2016. A Random Forest model (RF) with 19 input predictors (e.g., δ 13 C, 24 Mg, 85 Rb, and 206 Pb/ 207 Pb) was developed. Our RF model not only discriminated Westlake Xihu Longjing green tea (XHLJ) from other regions with an accuracy of 97.6%, but also correctly identified green tea from surrounding regions with an accuracy of 97.9%. The geographical discrimination of tea subsequently harvested in the following years also showed good reliability. Predictive accuracies were higher than 91%. 85 Rb, 24 Mg, δ 13 C and 39 K were the most important geographical proxies for determining geographical origin of tea with a relative contribution of 20.6%, 12.5%, 12.1% and 7.4%, respectively. This RF model showed higher classification accuracy than other commonly used chemometrics models and provides a new insight into the use of predictive models utilizing historical data for geographical authentication of agricultural products with Protected Designation of Origin (PDO). Highlights: XHLJ tea was differentiated from tea produced in nearby origins by random forest. Multiple year data strengthened the prediction reliability of data for future years. Random forest showed superior predictive ability than PCA-based models. 85 Rb, 24 Mg, δ 13 C and 39 K were important contributors for tea origin differentiation.