Soil salinization prediction through feature selection and machine learning at the irrigation district scale

Introduction Soil salinization is a critical environmental issue affecting agricultural productivity worldwide, particularly in arid and semi-arid regions. This study focuses on the Xinjiang region of China, specifically the Xiao Haizi and Sha Jingzi irrigation areas, to explore the use of remote sensing technology for surface soil salinity estimation.Methods Exhaustive and filter-based feature selection methods were employed by integrating soil salinity data measured on the ground with 32 spectral features derived from Landsat 8 OLI remote sensing images. A 5-fold cross-validation method was used to identify feature combinations that resulted in higher R 2 values. Moreover, the inversion accuracy of soil salinization monitoring models built using different feature combinations was compared across five machine learning algorithms: Support Vector Machine (SVM), XGBoost, Decision Tree (DT), Random Forest (RF), and AdaBoost.Results The results revealed that: (1) The AdaBoost and DT algorithms demonstrated high efficacy and precision in the prediction of soil salinity, with AdaBoost outperforming other algorithms in the validation set (R 2 value of 0.892, MAE of 1.558, RMSE of 2.043), and DT showing the best performance in the training set (R 2 value of 0.917, MAE of 0.838, RMSE of 1.182). (2) Feature combination 3, consisting of Salinity Index 5, Salinity Index 1, and Salinity Index 8, not only effectively extracted soil salinity information but also significantly improved the accuracy and efficiency of model estimations, effectively reflecting the actual situation of soil salinization in the irrigation area.Discussion This research provides robust methodological support for using remote sensing technology for soil salinity monitoring and management.