Hydrological drought prediction and its influencing factors analysis based on a machine learning model

Abstract. Predicting future drought conditions is crucial for effective disaster management. In this study, a machine learning framework is proposed to predict hydrological drought in the Huaihe River Basin, China. The interpretable Extreme Gradient Boosting (XGBoost) model is applied to forecast four drought categories in 28 grid regions, using 26 factors for monthly and 18 for seasonal predictions. The framework also integrates the Shapley Additive Explanation (SHAP) variable importance index to infer drought prediction factors. The model achieves 79.9 % accuracy in classifying droughts, with the Standard Precipitation Index (SPI) being the most influential factor. The SHAP values of SPI are 0.360, 0.261, 0.169, and 0.247 for spring, summer, autumn, and winter, respectively. Soil moisture content and evapotranspiration are particularly affected in spring and autumn, while large-scale climatic factors are more significant in summer and winter. Overall, this study offers valuable decision support for regional drought management and water resource allocation.