摘要
水文预报及其径流变化趋势预测能够为防汛工作提供辅助决策,是水库调度兴利的重要手段.与传统分布式水文模型相比,利用长短期记忆网络(LSTM)建立降雨径流预报模型具有简单可行和精度较高的优点.该文以鄱阳湖抚河流域为研究对象,采用抚河流域的降雨和径流数据分别作为模型驱动数据和标签数据,通过LSTM网络实现抚河流域的径流模拟工作.结果表明:在使用气象站数据建立的日尺度径流模拟模型中,模拟结果与实测值相关性均达到0.9以上,偏差在±5%以内,模型表现非常好;在使用TRMM数据建立的月尺度模型中,整体模拟结果与实测值相关性在0.9以上,整体偏差在±5%以内,模型表现优秀.
Studies of the changing trend of runoff through hydrological prediction can provide auxiliary decision-making for flood control work, which is also an important method for reservoir regulation. Compared with the traditional SWAT model, the runoff simulation model based on LSTM network is more practical and accurate. Focusing on the Fuhe river basin of Poyang Lake, we use rainfall and runoff data collected from Fuhe river basin as model driving data and label data respectively, and achieve the runoff simulation through LSTM network. The results show as follows. In the daily runoff prediction using data observed from meteorological stations, the correlation between measured and simulated runoff is above 0.9 and Pbias is within ±5%, indicating that the model performs well. In the monthly runoff prediction using TRMM dataset, the overall correlation between measured and simulated runoff is above 0.9 and Pbias is within ±5%, illustrating the excellent performance of the model.
作者
姜淞川
陆建忠
陈晓玲
刘子旋
JIANG Songchuan;LU Jianzhong;CHEN Xiaoling;LIU Zixuan(State Key Laboratory of Information Engineering in Surveying,Mapping and Remote Sensing,Wuhan University,Wuhan 430079,China;Key Laboratory of Poyang Lake Wetland and Watershed Research,Ministry of Education,Jiangxi Normal University,Nanchang 330022,China)
出处
《华中师范大学学报（自然科学版）》
CAS
CSCD
北大核心
2020年第1期128-139,共12页
Journal of Central China Normal University：Natural Sciences
基金
国家重点研发计划项目(2018YFC1506506)
武汉市应用基础前沿项目(2019020701011502)
湖北省自然科学基金项目(2019CFB736)
中央高校基本科研业务费专项资金项目(2042018kf0220)
江西省水工程安全与资源高效利用工程研究中心开放基金项目(OF201601)
测绘遥感信息工程国家重点实验室专项科研经费项目
关键词
深度学习
神经网络
径流模拟
长短期记忆网络
鄱阳湖抚河流域
deep learning
neural network
runoff simulation
long-short-term memory network
Fuhe River Basin of Poyang Lake
作者简介
通讯联系人:陆建忠,E-mail:lujzhong@whu.edu.cn.
