Application of Raman Spectroscopy-Driven Multi-Model Ensemble Modeling in Soil Nutrient Prediction

Rapid and non-destructive acquisition of soil nutrient information is crucial for precision fertilization and soil quality monitoring. This study aims to establish a Raman spectroscopy-based framework for predicting key soil fertility indicators, including alkali-hydrolyzable nitrogen (AN), total nitrogen (TN), total phosphorus (TP), and organic matter (OM). The framework systematically integrates three typical spectral preprocessing methods (Standard Normal Variate transformation (SNV), Savitzky–Golay first derivative (SG_D1), and wavelet transform (Wavelet)), three feature selection strategies (Recursive Feature Elimination, XGBoost importance, and Random Forest importance), and 14 mainstream regression models to construct a multi-combination modeling system. Model performance was evaluated using five-fold cross-validation, with 80% of samples used for training and 20% for validation in each fold. Preprocessed Raman spectral features served as input variables, while the corresponding nutrient contents were used as outputs. Results showed significant differences in prediction performance across various combinations of preprocessing methods and regression algorithms for the four soil nutrient indicators. For AN prediction, the combination of Raw_SNV preprocessing with ElasticNet and BayesianRidge models achieved the best performance, with Test R 2 values of 0.713 and 0.721, and corresponding Test NRMSE as low as 0.092. For OM prediction, the same Raw_SNV preprocessing with ElasticNet and BayesianRidge also performed well, yielding Test R 2 values of 0.825 and 0.832, and Test NRMSE of 0.100 and 0.098, respectively. In TN prediction, both ElasticNet and BayesianRidge under Raw_SNV preprocessing achieved consistent Test R 2 of 0.74 and Test NRMSE around 0.20, indicating stable reliability. For TP prediction, the BayesianRidge model with Raw_SNV preprocessing outperformed all others with a Test R 2 of 0.71 and Test NRMSE of just 0.089, followed closely by ElasticNet (Test R 2 = 0.70, Test NRMSE = 0.092). Overall, the Raw_SNV preprocessing method demonstrated superior performance compared to SG_D1_SNV and Wavelet_SNV. Both BayesianRidge and ElasticNet consistently achieved high R 2 and low NRMSE across multiple targets, showcasing strong generalization and robustness, making them optimal model choices for Raman spectroscopy-based soil nutrient prediction. This study demonstrates that Raman spectroscopy, when combined with appropriate preprocessing and modeling techniques, can effectively predict soil organic matter and nitrogen in specific soil types under laboratory conditions. These results provide initial methodological insights for future development of intelligent soil nutrient diagnostics.