邬强,
李常青,
陈游倩,
张力,
冉广,
胡彩虹,
郑州大学水利科学与工程学院，450000，河南郑州
基金项目:国家自然科学基金资助项目（51979250，51739009，31700370）；国家重点研发计划资助项目（2016YFC040240203）
详细信息
通讯作者:胡彩虹（1968—），女，教授，博士。 研究方向：水文学及水资源. e-mail：hucaihong@zzu.edu.cn
中图分类号:P333.2计量
文章访问数:160
HTML全文浏览量:46
PDF下载量:12
被引次数:0
出版历程
收稿日期:2020-05-07
网络出版日期:2020-07-29
刊出日期:2020-06-01
Simulation of the flood process in the middle reaches of the Yellow River by a long - short term memory (LSTM) neuro network
Yuanhao XU,Qiang WU,
Changqing LI,
Youqian CHEN,
Li ZHANG,
Guang RAN,
Caihong HU,
School of water conservancy science and engineering, Zhengzhou University, 450000, Zhengzhou, Henan,China
摘要
HTML全文
图
参考文献
相关文章
施引文献
资源附件
访问统计
摘要
摘要:洪水预报是防洪减灾的重要非工程措施，黄河中游地区水文情势近50 a发生显著变化，为提高变化环境下黄河中游半干旱半湿润地区洪水预报精度，本文以对时间序列数据具有良好模拟效果的深度学习神经网络（长短时记忆神经网络）为基础，建立不同预见期下的流域暴雨洪水模型，以探讨长短时记忆神经网络在黄河中游水文预报中的应用. 模型建立采用汾河上游静乐控制站1956—2014年98场暴雨洪水数据，其中以14个站点降雨及静乐站水文数据作为输入，不同预见期下的洪水过程作为输出，率定期为78场次，验证期为20场次. 结果显示：在预见期为0～6 h时预报精度较高，预见期为6 h以上时预报效果相对较差；预报精度随神经元数量和训练次数的增加而呈上升趋势，预见期为0～6 h时预报精度上升较为明显，而预见期6 h以上时预报精度上升较为均匀.
关键词:降雨径流模拟/
水文预报/
深度学习/
黄河中游
Abstract:Flood forecasting is an important non-engineering measure for flood prevention and disaster reduction. Hydrological situation in the middle reaches of the Yellow River has changed significantly in the past 50 years. To improve accuracy of flood forecasting in semi-arid and semi-humid areas in the middle reaches of the Yellow River, an in-depth learning neuro network model with good temporal resolution was used. The LSTM model was applied to data of 98 storms and floods from 1956 to 2014 at Jingle Control Station, located in the upper reaches of the Fenhe River. Rainfall data from 14 stations and hydrological data at Jingle Station were used as input; flood process under different foreseeable periods was used as output, with a regular rate of 78 events, and verification period of 20 events. Prediction accuracy was found to be higher when foresight period was 0 - 6 h, but relatively poor when foresight period was > 6 h. Prediction accuracy was found to increase with increased number of neurons and trainings. Prediction accuracy increased significantly when forecast period was increased from 0 to 6 h, but increased more uniformly when forecast period was > 6 h.
Key words:rainfall runoff simulation/
hydrological forecasting/
deep learning/
middle reaches of the Yellow River
