Soil Erosion Susceptibility Assessment Using Integrated RUSLE-GIS and Machine Learning Models in the Chittar River Basin, India
This study integrated the Revised Universal Soil Loss Equation (RUSLE) with Geographic Information System (GIS) and four machine learning models to assess soil erosion susceptibility in India's Chittar River Basin, finding that the Random Forest model achieved the highest predictive accuracy (AUC = 0.967) for identifying erosion-prone areas to support sustainable watershed management.