Applications and interpretations of different machine learning models in runoff and sediment discharge simulations.

• Predicted values calculated by different ML algorithms fit the measured values well. • Different ML models performed better in sediment discharge simulation. • XGB outperformed the other ML models on the training set. • RFR and SVR had best prediction ability in the AR and AS simulations, respectively. • Rainfall and runoff factor contributed most to the AR and AS changes, respectively. Predicting runoff and sediment discharge changes and understanding their drivers can provide insight into hydrological processes and aid in watershed management planning. In recent years, machine learning (ML) has become a popular tool for predicting runoff and sediment discharge in large rivers. In this study, six ML models, support vector regression (SVR), artificial neural network (ANN), random forest regression (RFR), extreme gradient boosting (XGB), k-nearest neighbor regression (kNNR), and bootstrap aggregating regression (BAR), were applied to simulate watershed runoff and sediment discharge. Notably, the Shapley additive explanation (SHAP) method was applied to identify the contribution of driving factors to runoff and sediment discharge generation. The results showed that the annual runoff and sediment discharge values predicted by the six ML algorithms fit well to the measured values. In particular, all models performed better in the sediment discharge simulation than in the runoff simulation. Combining the four evaluation indexes and their scores, the model performance hierarchy in runoff simulation was XGB > RFR > BAR > SVR > ANN > kNNR, while the model performance hierarchy in sediment discharge simulation was SVR > XGB > BAR > RFR > kNNR > ANN. After excluding the effects of sample order on the simulation results, XGB showed less empirical risk and better generalizability, while RFR and SVR showed better prediction ability in the annual runoff and annual sediment discharge simulations, respectively. Additionally, the rainfall factor contributed most to runoff changes, while the runoff factor contributed most to sediment discharge changes. Overall, the results of the present study can help assess river safety and promote sustainable river development. [ABSTRACT FROM AUTHOR]