Research on Dual-Sensor Hyperspectral Fusion for Prediction of Sorghum Tannin Content Oriented to Liquor Brewing

In response to Chinese liquor brewing industry's need for precise control of sorghum tannin content and the issues of low efficiency and high cost associated with traditional detection methods, this study proposes a non-destructive detection method for sorghum tannin content based on the fusion of dual hyperspectral sensor features. Based on 240 representative sorghum samples covering different varieties and production regions, visible and near-infrared (VNIR) and short-wave infrared (SWIR) hyperspectral data were sequentially collected, and the tannin content was determined using standard chemical methods as reference values. Using the competitive adaptive reweighted sampling (CARS) method, characteristic wavelength bands were extracted and fused feature subsets were constructed. Combined with partial least squares (PLS), support vector machine (SVM), and convolutional neural network (CNN) algorithms, the performance of models built from both full-data concatenation and feature fusion of VNIR and SWIR data was systematically compared. The results demonstrated that the feature-based models exhibited superior performance to the full-spectrum models, while the model incorporating dual-sensor feature fusion achieved the best overall results. And the Fused-Feature-CNN model achieved the optimal prediction performance, with values of 0.8298 for RP2, 0.2894 for RMSEP, and 2.4239 for RPDP. This study confirms that the integration of multi-sensor feature fusion with deep learning strategies can provide an effective technical pathway for the rapid, non-destructive detection of sorghum tannin content and the development of online sorting equipment.