水科学进展2026，Vol.37Issue(5)：869-879,11.DOI:10.14042/j.cnki.32.1309.2026.05.007
耦合SWAT与深度学习的径流模拟
Runoff simulation by coupling SWAT with deep learning
摘要
Abstract
To improve the accuracy of runoff simulation and enhance the interpretability of hydrological models,this study constructs a coupled model that integrates SWAT and deep learning.The Bayesian method is conducted for the optimization of parameters and the Stacking ensemble strategy is used to integrate the outputs of individual model during model construction in order to reduce the uncertainties of high-flow predictions.The results show that the coupled model is better than any single model in terms of higher coefficient of determination(R2)and Nash-Sutcliffe efficiency coefficient(ENS)and lower mean absolute error(EMA).Specifically,the R2,ENS and EMA obtained from SWAT-LSTM are close to 0.766,0.761 and 4.93 m3/s,respectively,in the testing phase.By introducing the SHAP-based interpretability analysis,the results also indicate that the performance of LSTM relies more heavily on precipitation because of its characteristic of sequential memory,whereas the Transformer focuses on lateral flow through its self-attention mechanism,revealing the differentiated mechanisms by which different deep learning models capture hydrological processes.Moreover,the performance of the Stacking-based ensemble model is close to an average of 0.81 in terms of ENS in the testing phase.This study provides a modeling approach for intelligent hydrological simulation and forecasting that maintain acceptable accuracy and interpretability.关键词
径流模拟/SWAT模型/深度学习/人工智能/可解释性分析Key words
runoff simulation/SWAT model/deep learning/artificial intelligence/interpretability analysis分类
建筑与水利引用本文复制引用
王一博,李海翔,许月萍,钟文祥,江衍铭..耦合SWAT与深度学习的径流模拟[J].水科学进展,2026,37(5):869-879,11.基金项目
浙江省科学技术厅尖兵领雁研发攻关计划项目(2024C03255) The study is financially supported by the Project of the Pioneer and Leading Goose Key R&D Program of the Zhejiang Provincial Department of Science and Technology,China(No.2024C03255). （2024C03255）
