Determination of Tibetan tea quality by hyperspectral imaging technology and multivariate analysis

Tibetan tea is a dark tea native to Ya'an, and its taste and quality are closely related to the contents of tea polyphenols (TPs) and free amino acids (FAAs). In this study, TPs and FAAs were determined by chemometrics and the grades of Tibetan tea were distinguished. Then, hyperspectral data were collected, a variety of preprocessing methods were used to preprocess the spectral data, and principal component analysis (PCA) was used for feature dimensionality reduction. Results showed that the combination of the preprocessing method and machine learning (ML) could achieve a higher prediction effect. Savitzky Golay (SG)-Standard Normal Variable (SNV)-PCA-Extratree had the best predictive ability for TPs (Rp2=0.9248, RMSEP=0.4842, and RPD=3.646). For detecting FAAs, SG-Multiplicative Scatter Correction (MSC)-PCA-Extratree had the best predictive ability (Rp2=0.8736, RMSEP=0.159, and RPD=2.813). In addition, tea grade can be determined by SG-MSC-PCA-Support Vector Machine (SVM) with 100% accuracy, recall, and precision. In sum, hyperspectral imaging technology (HSI) can be used as an alternative method for rapid, non-destructive testing of tea quality.