doi:10.12202/j.0476-0301.2020174王栋¹,
魏加华^{2, 3,,},
章四龙¹,
初海波³
1.北京师范大学水科学研究院，城市水循环与海绵城市技术北京市重点实验室，100875，北京
2.青海大学三江源生态与高原农牧业国家重点实验室，810016，青海西宁
3.清华大学水沙科学与水利水电工程国家重点实验室，100084，北京
基金项目:青海省重点研发与转化计划资助项目（2019-SF-146）；青海省自然科学基金资助项目（2019-ZJ-941Q）

详细信息

通讯作者:魏加华（1971—），男，陕西汉中人，教授，博士. 研究方向：水资源、水信息学. e-mail：weijiahua@tsinghua.edu.cn

中图分类号:P333

计量

文章访问数:61
HTML全文浏览量:11
PDF下载量:3
被引次数:0

出版历程

收稿日期:2019-11-26
网络出版日期:2020-07-29
刊出日期:2020-06-01

Hydrological temporal series of monthly runoff prediction by CEEMD-BP model

Dong WANG¹,
Jiahua WEI^{2, 3,,},
Silong ZHANG¹,
Haibo CHU³
1. Beijing Key Laboratory of Urban Hydrological Cycle and Sponge City Technology, College of Water Sciences, Beijing Normal University, 100875, Beijing, China
2. Skate Key Laboratory of Plateau Ecology and Agriculture, Qinghai University, 810016, Xining, Qinghai, China
3. Skate Key Laboratory of Hydroscience and Engineering, Tsinghua University, 100084, Beijing, China



摘要
HTML全文
图(9)表(1)
参考文献(18)
相关文章
施引文献
资源附件(0)
访问统计

摘要
摘要:水文时间序列月径流预测在水资源的规划与管理方面具有重要的作用，由于径流序列的非线性和非平稳性，对其准确地进行预测较为困难. 本文基于1956—2013年青海湟水河流域月径流序列，将完备的集合经验模态分解方法（complete ensemble empirical mode decomposition, CEEMD）与BP神经网络组合进行月径流预测. 结果表明：组合模型CEEMD-BP和EEMD-BP相比于单一的BP神经网络,可以更好地保留原始数据的信息，预测效果更好，其中CEEMD-BP在组合模型中的预测精度更高，可用于水文时间序列月径流预测.
关键词:径流预测/
EEMD-BP模型/
CEEMD-BP模型/
BP神经网络
Abstract:Monthly hydrological time series prediction plays an important role in the planning and management of water resources. Due to nonlinear and non-stationary nature of runoff sequences, it is difficult to predict accurately. Runoff sequence in the Huangshui River Basin of Qinghai Province from 1956 to 2013 was used to predict monthly runoff, combining complete ensemble empirical mode decomposition method (CEEMD) with BP neural network. The combined EEMD-BP and CEEMD-BP models were found to retain original data information better compared to single BP neural network, and prediction performance was better. CEEMD-BP was found to have better prediction accuracy in the combined model for hydrological monthly runoff prediction.
Key words:runoff prediction/
EEMD-BP model/
CEEMD-BP model/
BP neural network