水科学进展2025，Vol.36Issue(2)：204-216,13.DOI:10.14042/j.cnki.32.1309.2025.02.003
基于可微参数学习的积融雪新安江模型
Incorporating snow accumulation and melting into the Xin'anjiang model using differentiable parameter learning
摘要
Abstract
The Xin'anjiang model stands as one of the most important hydrological models.This paper develops a differentiable Xin'anjiang model coupled with the CemaNeige module(dMXAJ)under the framework of differentiable parameter learning.Specifically,the long short-term memory(LSTM)network is employed to generate parameters for the dMXAJ through forward propagation,using catchment attributes and meteorological data as inputs.These parameters are then fed into the dMXAJ and optimized via backpropagation.Four models are used to investigate the effectiveness of dMXAJ across 531 catchments from the Catchment Attributes and Meteorology for Large-sample Studies.The results show that the CemaNeige module effectively improves the performance of the Xin'anjiang model,increasing the median Kling-Gupta efficiency(EKG)from 0.58 to 0.68.For the local dMXAJ,the median EKG is improved to 0.70;for the regional dMXAJ,the median EKG is improved to 0.72.These improvements can be attributed to the consideration of snow accumulation and melting,the effectiveness of the differentiable parameter learning and synergistic effects.Overall,the differentiable parameter learning effectively facilitates the development and application of the Xin'anjiang model coupled with the CemaNeige module.关键词
水文模拟/新安江模型/机器学习/协同效应/长短时记忆神经网络Key words
hydrological modeling/Xin'anjiang model/machine learning/synergistic effect/long short-term memory分类
水利科学引用本文复制引用
陈泽鑫,赵铜铁钢..基于可微参数学习的积融雪新安江模型[J].水科学进展,2025,36(2):204-216,13.基金项目
国家自然科学基金项目(52379033) （52379033）
水利部粤港澳大湾区水安全保障重点实验室开放研究基金项目(WSGBA-KJ202308) The study is financially supported by the National Natural Science Foundation of China(No.52379033)and the Open Research Fund of Key Laboratory of Water Security Guarntee in Guangdong-Hong Kong-Marco Greater Bay Area of Ministry of Water Resources(No.WSGBA-KJ202308). （WSGBA-KJ202308）
