摘要
在洪水预报和防洪调度实践中,受多支流顶托影响的干流水位流量关系存在显著非线性特征,传统线性模型难以精准模拟其动态变化。为此,基于长短期记忆网络(LSTM)模型,提出了一种考虑多支流顶托效应的干流水位流量关系拟合模型;并以梯度增强回归树(GBRT)、随机森林(RF)、支持向量机回归(SVR)为基准模型,对比验证深度学习方法的优势;然后通过可解释性技术SHAP方法解析支流顶托因子的作用机制与贡献度。向家坝水文站应用结果表明:LSTM模型能有效拟合复杂顶托效应下的水文站水位流量关系,在测试期纳什效率系数达0.948,优于GBRT、RF和SVR模型。通过可解释性分析可知,当横江水文站流量大于300 m^(3)/s,高场水文站流量大于3000 m^(3)/s后,对向家坝水文站的顶托影响更为明显。研究提出的LSTM-SHAP可解释深度学习方法实现了受多支流顶托影响的复杂水位流量关系模拟,并量化了顶托影响的关键拐点,可为考虑支流顶托效应的防洪实时调度决策提供技术支撑。
In flood forecasting and reservoir flood control operation practices,the stage-discharge relation of mainstreams subject to multi-tributary water jacking exhibits significant nonlinear characteristics that conventional linear models fail to accurately capture.To address this limitation,we develop a Long Short-Term Memory(LSTM)-based stage-discharge relation modeling framework incorporating multi-tributary water jacking influences.The advantages of deep learning methods are compared and verified by using Gradient Boosting Regression Tree(GBRT),Random Forest(RF),and Support Vector Regression(SVR)as benchmark models.SHapley Additive exPlanations(SHAP)interpretability techniques are employed to quantify contribution weights and elucidate the mechanistic impacts of tributary water jacking factors.The application results of Xiangjiaba Hydrological Station show that:LSTM model effectively characterizes complex multi-tributary water jacking-affected stage-discharge relationships,achieving a Nash-Sutcliffe Efficiency(NSE)coefficient of 0.948 during test period,outperforming GBRT,RF,and SVR counterparts.Interpretability analysis reveals critical tributary water jacking thresholds:when Hengjiang Station's discharge exceeds 300 m^(3)/s concurrent with Gaochang Station's discharge surpassing 3000 m^(3)/s,significant tributary water jacking occurs.The integrated LSTM-SHAP methodology achieves accurate simulation of multi-tributary water jacking-affected stage-discharge relationships and quantitative identification of critical discharge thresholds.This framework provides technical foundations for real-time flood control operations accounting for tributary water interactions.
作者
郑雅莲
赵增辉
李妍清
王飞龙
熊丰
周恺
ZHENG Yalian;ZHAO Zenghui;LI Yanqing;WANG Feilong;XIONG Feng;ZHOU Kai(China Three Gorges Corporation,Yichang 443133,China;Bureau of Hydrology,Changjiang Water Resources Commission,Wuhan 430010,China)
出处
《人民长江》
北大核心
2025年第12期133-141,共9页
Yangtze River
基金
中国长江三峡集团有限公司科研项目(0704227)
国家重点研发计划项目(2022FY100203)。
关键词
水位流量关系
顶托效应
深度学习
长短期记忆网络
可解释性
向家坝水文站
stage-discharge relation
jacking influence
deep learning
Long Short-Term Memory Network
interpretability
Xiangjiaba Hydrological Station
