Prediction of nutritional quality characteristics of faba bean based on deep learning method

This study established an integrated analytical method based on near-infrared spectroscopy (NIRS) for the rapid, non-destructive, and quantitative detection of four major nutritional components in faba beans: starch, protein, moisture, and dietary fiber. By systematically comparing individual and combined spectral preprocessing strategies, optimal preprocessing combinations for each component were identified. Seven feature wavelength selection algorithms, including Competitive Adaptive Reweighted Sampling (CARS), were employed to extract key spectral variables. Predictive models were subsequently developed using four modeling approaches: Partial Least Squares (PLS), Random Forest (RF), Support Vector Machine (SVM), and Multilayer Perceptron (MLP). The results demonstrated that combined preprocessing methods significantly outperformed single techniques. The CARS algorithm exhibited the most robust performance in feature extraction, and the MLP model consistently surpassed traditional machine learning methods in predicting all components. The optimal modeling pipelines for each component were ultimately determined as follows: starch (MLP + CARS + MSC + SG + MSS, R² = 0.92), protein (MLP + CARS + SD + SNV + MSC + MSS, R² = 0.94), moisture (MLP + SPA + SG + SNV, R² = 0.9973), and dietary fiber (MLP + PCA + FD + SNV, R² = 0.9999). This study verifies the effectiveness of combining NIRS with deep learning for the simultaneous detection of multiple components in faba beans and provides a reliable methodological framework for the non-destructive quality assessment of agricultural products.