Tea polyphenol and epigallocatechin gallate (EGCG) were considered as key components of tea. The rapid prediction of these two components can be beneficial for tea quality control and product development for tea producers, breeders and consumers. This study aimed to develop reliable models for tea polyphenols and EGCG content prediction during the breeding process using Fourier Transform–near infrared (FT-NIR) spectroscopy combined with machine learning algorithms. Various spectral preprocessing methods including Savitzky–Golay smoothing (SG), standard normal variate (SNV), vector normalization (VN), multiplicative scatter correction (MSC) and first derivative (FD) were applied to improve the quality of the collected spectra. Partial least squares regression (PLSR) and least squares support vector regression (LS-SVR) were introduced to establish models for tea polyphenol and EGCG content prediction based on different preprocessed spectral data. Variable selection algorithms, including competitive adaptive reweighted sampling (CARS) and random forest (RF), were further utilized to identify key spectral bands to improve the efficiency of the models. The results demonstrate that the optimal model for tea polyphenols calibration was the LS-SVR with R_p = 0.975 and RPD = 4.540 based on SG-smoothed full spectra. For EGCG detection, the best model was the LS-SVR with R_p = 0.936 and RPD = 2.841 using full original spectra as model inputs. The application of variable selection algorithms further improved the predictive performance of the models. The LS-SVR model for tea polyphenols prediction with R_p = 0.978 and RPD = 4.833 used 30 CARS-selected variables, while the LS-SVR model build on 27 RF-selected variables achieved the best predictive ability with R_p = 0.944 and RPD = 3.049, respectively, for EGCG prediction. The results demonstrate a potential of FT-NIR spectroscopy combined with machine learning for the rapid screening of genotypes with high tea polyphenol and EGCG content in tea leaves.

Tea polyphenols are considered as an important indicator of tea quality. Rapid detection of tea polyphenol content plays a valuable role for tea breeding and quality inspection during tea production. In this work, a portable rapid non-destructive detection device of tea polyphenols in fresh tea leaves was developed, which integrated the fusion technology of visible/short-wave (400–1050 nm) and long-wave (1000–1650 nm) near-infrared spectroscopy (Vis/NIR). Experimental results indicated that the spectra within the overlapping region (1000–1050 nm) were assembled by applying the spectral data fusing method. Followed by spectral data preprocessing with the Savitzky–Golay smoothing (SG) method, least squares support vector regression (LS–SVR) models were established for detecting the tea polyphenol content of fresh tea leaves. Based on the fused Vis/NIR spectra (dual-band), the correlation coefficient of calibration (R_C), root mean square error of calibration (RMSEC), correlation coefficient of prediction (R_P), root mean square error of prediction (RMSEP), and residual predictive deviation (RPD) reached 0.976, 0.679%, 0.893, 0.897%, and 2.230, respectively, which were better than the visible/short-wave or long-wave near infrared spectral data (single-band). The sensitive spectral wavebands of tea polyphenols extracted using the random frog (RF) algorithm were distributed in 402–448 nm, 555–600 nm, 810–1042 nm, 1056–1103 nm, 1219–1323 nm, 1406–1416 nm, and 1499–1511 nm. This demonstrated that the prediction of tea polyphenol content using fused spectral data combined with the LS–SVR model depended on various functional groups such as auxochromes, chromogenic groups, and hydrogen-containing groups. The proposed device is capable of non-destructive detection of tea polyphenol content in fresh tea leaves, which can provide effective technical support for tea breeding and tea leaf quality control.