摘要
为提高生态流量预警预报精度及水利工程生态调度效率,本文以浙江省椒江流域为研究对象,采用水文学法计算断面生态流量及预警阈值,利用主成分分析法筛选模型预报因子,并提出了基于深度学习和概念水文模型的河湖生态流量预报预警新方法。结果表明:柏枝岙和沙段断面最适宜的生态流量核算值分别为2.89 m~3/s和1.92 m~3/s;选取降雨和蒸发作为输入因子,采用网格搜索法寻找最优参数,极值梯度提升算法(XGBoost)在所有年份的生态流量预警等级信息预报合格率都达到100%;基于XGBoost和新安江水文模型的耦合预报模型能够很好地完成生态流量预警预报和水库生态流量调度工作。研究成果可为河湖水资源保护和监管提供决策依据。
This paper develops a new ecological flow forecasting method based on deep learning and a conceptual hydrological model with application to the Jiaojiang River basin in Zhejiang Province to improve the forecast accuracy of ecological flow early warning and the efficiency of ecological operation of water conservancy projects.This method calculates the ecological flow and warning threshold using the hydrological method,and screens model forecast factors through the principal component analysis.The results reveal the check values of most suitable ecological flows are 2.89 m~3/s and 1.92 m~3/s at the Baizhiao and Shaduan stations,respectively.We use precipitation and evaporation as input factors and the grid search method for optimal parameters searching,and have achieved a 100% qualified rate of the ecological flow warning level forecasts in all the years by using the eXtreme Gradient Boosting(XGBoost)algorithm.Our coupling prediction model based on XGBoost and the Xin'anjiang model can well complete the ecological flow early warning prediction and reservoir ecological flow regulation,laying a basis of decision-making for protection and supervision of water resources in rivers and lakes.
作者
陈浩
王贝
何锡君
许月萍
郭玉雪
王冬
CHEN Hao;WANG Bei;HE Xijun;XU Yueping;GUO Yuxue;WANG Dong(College of Civil Engineering and Architecture,Zhejiang University,Hangzhou 310058,China;School of Water Conservancy and Environment Engineering,Zhejiang University of Water Resources and Electric Power,Hangzhou 310018,China;Zhejiang Hydrological Management Center,Hangzhou 310009,China;Zhejiang Hydrographic Technology Development and Operation Company,Hangzhou 310009,China)
出处
《水力发电学报》
CSCD
北大核心
2023年第8期10-20,共11页
Journal of Hydroelectric Engineering
基金
浙江省自然科学基金重点项目(LZ20E090001)
浙江省重点研发计划(2021C03017)
国家自然科学基金项目(91547106)。
关键词
生态流量
主成分分析法
深度学习算法
新安江模型
椒江流域
ecological flow
principal component analysis
deep learning algorithm
Xin’anjiang model
Jiaojiang River basin
作者简介
陈浩(1990-),男,助理研究员.E-mail:haochen1990@zju.edu.cn;通信作者:许月萍(1975-),女,教授.E-mail:yuepingxu@zju.edu.cn。
