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

Guardado en:
Detalles Bibliográficos
Publicado en:Agriculture vol. 15, no. 17 (2025), p. 1901-1929
Autor principal: Zhang Xiuquan
Otros Autores: Wang Juanling, Li, Zhiwei, Song, Haiyan, Zheng Decong
Publicado:
MDPI AG
Materias:
Acceso en línea:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!

MARC

LEADER 00000nab a2200000uu 4500
001 3249613178
003 UK-CbPIL
022 |a 2077-0472 
024 7 |a 10.3390/agriculture15171901  |2 doi 
035 |a 3249613178 
045 2 |b d20250101  |b d20251231 
084 |a 231331  |2 nlm 
100 1 |a Zhang Xiuquan  |u College of Agricultural Engineering, Shanxi Agricultural University, Jinzhong 030801, China; zhangxiuquan@sxau.edu.cn (X.Z.); yybbao@sxau.edu.cn (H.S.); zhengdecong@sxau.edu.cn (D.Z.) 
245 1 |a Application of Raman Spectroscopy-Driven Multi-Model Ensemble Modeling in Soil Nutrient Prediction 
260 |b MDPI AG  |c 2025 
513 |a Journal Article 
520 3 |a 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 R2 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 R2 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 R2 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 R2 of 0.71 and Test NRMSE of just 0.089, followed closely by ElasticNet (Test R2 = 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 R2 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. 
653 |a Accuracy 
653 |a Performance evaluation 
653 |a Nitrogen 
653 |a Regression analysis 
653 |a Regression models 
653 |a Indicators 
653 |a Soil types 
653 |a Organic matter 
653 |a Feature selection 
653 |a Fertilization 
653 |a Soil fertility 
653 |a Raman spectroscopy 
653 |a Soil organic matter 
653 |a Potassium 
653 |a Wavelet transforms 
653 |a Soil nutrients 
653 |a Spectroscopy 
653 |a Agriculture 
653 |a Machine learning 
653 |a Phosphorus 
653 |a Preprocessing 
653 |a Oxidation 
653 |a Spectrum analysis 
653 |a Predictions 
653 |a Soil quality 
653 |a Molybdenum 
653 |a Organic phosphorus 
653 |a Methods 
653 |a Algorithms 
653 |a Nutrients 
653 |a Spectroscopic analysis 
653 |a Environmental 
700 1 |a Wang Juanling  |u Shanxi Institute of Organic Dryland Farming, Shanxi Agricultural University, Key Laboratory of Sustainable Dryland Agriculture of Shanxi Province, Taiyuan 030001, China 
700 1 |a Li, Zhiwei  |u College of Information Science and Engineering, Shanxi Agricultural University, Jinzhong 030801, China; lizw@sxau.edu.cn 
700 1 |a Song, Haiyan  |u College of Agricultural Engineering, Shanxi Agricultural University, Jinzhong 030801, China; zhangxiuquan@sxau.edu.cn (X.Z.); yybbao@sxau.edu.cn (H.S.); zhengdecong@sxau.edu.cn (D.Z.) 
700 1 |a Zheng Decong  |u College of Agricultural Engineering, Shanxi Agricultural University, Jinzhong 030801, China; zhangxiuquan@sxau.edu.cn (X.Z.); yybbao@sxau.edu.cn (H.S.); zhengdecong@sxau.edu.cn (D.Z.) 
773 0 |t Agriculture  |g vol. 15, no. 17 (2025), p. 1901-1929 
786 0 |d ProQuest  |t Agriculture Science Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3249613178/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/3249613178/fulltextwithgraphics/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3249613178/fulltextPDF/embedded/L8HZQI7Z43R0LA5T?source=fedsrch