Establishment of a rapid detection model for the sensory quality and components of Yuezhou Longjing tea using near-infrared spectroscopy

Abstract

Quantitative prediction models for sensory quality scores, total catechins, and caffeine based on near-infrared spectroscopy were established for different quality grades of Yuezhou Longjing tea. One-way ANOVA and multiple comparison test analyses were first conducted on the obtained sensory quality scores and physical and chemical quality indices to check the accuracy and reliability of the experimental data. There were significant differences in the sensory quality, total catechins, and caffeine of different grades of tea. Secondly, the obtained near-infrared spectrum data were preprocessed, and then the competitive adaptive reweighted sampling (CARS) and variables combination population analysis combined with iterative retained information variable algorithm (VCPA-IRIV) were used to screen the optimal characteristic wavenumbers of each quality index. Along with principal component analysis (PCA) to establish prediction models for the partial least squares regression (PLSR), support vector regression (SVR), and random forest algorithm (RF). The results showed that the best predictive models for sensory scores, total catechins, and caffeine were VCPA-IRIV + SVR, VCPA-IRIV + RF, and CARS + SVR, and the relative percent deviation (RPD) were 2.485, 2.584, and 2.873, respectively. Indicates that the model has good predictive performance. In conclusion, it is feasible to evaluate the quality of Yuezhou Longjing tea with near-infrared spectroscopy.