Global Soil Salinity Prediction by Open Soil Vis-NIR Spectral Library

Abstract

Soil salinization is one of the major degradation processes threatening food security and sustainable development. Detailed soil salinity information is increasingly needed to tackle this global challenge for improving soil management. Soil-visible and near-infrared (Vis-NIR) spectroscopy has been proven to be a potential solution for estimating soil-salinity-related information (i.e., electrical conductivity, EC) rapidly and cost-effectively. However, previous studies were mainly conducted at the field, regional, or national scale, so the potential application of Vis-NIR spectroscopy at a global scale needs further investigation. Based on an extensive open global soil spectral library (61,486 samples with both EC and Vis-NIR spectra), we compared four spectral predictive models (PLSR, Cubist, Random Forests, and XGBoost) in estimating EC. Our results indicated that XGBoost had the best model performance (R2 of 0.59, RMSE of 1.96 dS m−1) in predicting EC at a global scale, whereas PLSR had a relatively limited ability (R2 of 0.39, RMSE of 2.41 dS m−1). The results also showed that auxiliary environmental covariates (i.e., coordinates, elevation, climatic variables) could greatly improve EC prediction accuracy by the four models, and the XGBoost performed best (R2 of 0.71, RMSE of 1.65 dS m−1). The outcomes of this study provide a valuable reference for improving broad-scale soil salinity prediction by the coupling of the spectroscopic technique and easily obtainable environmental covariates.

Keywords

• open soil spectral library
• electrical conductivity
• machine learning
• environmental covariates