中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 地理科学与资源研究所
  3. 中国科学院地理科学与资源研究所
Improving Daily Streamflow Forecasting Using Deep Belief Net-Work Based on Flow Regime Recognition

文献类型：期刊论文

作者Shen, Jianming1,2; Zou, Lei1; Dong, Yi1,2; Xiao, Shuai1,2; Zhao, Yanjun1,2; Liu, Chengjian1,2
刊名WATER
出版日期2022-07-01
卷号14期号:14页码:17
关键词daily streamflow forecasting regime recognition SOM RF DBN
DOI10.3390/w14142241
通讯作者Zou, Lei(zoulei@igsnrr.ac.cn)
英文摘要Streamflow forecasting is of great significance for water resources planning and management. In recent years, numerous data-driven models have been widely used for streamflow forecasting. However, the traditional single data-driven model ignores the utilization of different streamflow regimes. This study proposed an integrated framework for daily streamflow forecasting based on the regime recognition of flow sequences. The framework integrates self-organizing maps (SOM) for identifying streamflow sub-sequences, the random forests (RF) algorithm to select input variables for different streamflow sub-sequences, and a deep belief network (DBN) for establishing complex relationships between the selected input variables and streamflows for different sub-sequences. Specifically, the integrated framework was applied to forecast daily streamflow at the Xiantao hydrological station in the Hanjiang River Basin, China. The results show that the developed integrated framework has higher streamflow prediction accuracy than the single data-driven model (i.e., the DBN model in this study), with Nash efficiency coefficient (NSE) of 0.91/0.81 and coefficient of determination (R-2) of 0.93/0.89 for the integrated framework/DBN model during the validation period, respectively. Additionally, the prediction accuracy of the peak flood was also improved. The relative error of the peak flood derived from the integrated framework was reduced by 4.6%, compared with the single DBN model. Overall, the constructed integration framework, considering the complex characteristic of different flow regimes, could improve the accuracy for daily streamflow forecasting.
WOS关键词ARTIFICIAL NEURAL-NETWORK ; MODEL ; OPTIMIZATION ; SELECTION ; DROUGHT
资助项目Strategic Priority Research Program of the Chinese Academy of Sciences[XDA23040304] ; National Natural Science Foundation of China[41890823]
WOS研究方向Environmental Sciences & Ecology ; Water Resources
语种英语
出版者MDPI
WOS记录号WOS:000833285800001
资助机构Strategic Priority Research Program of the Chinese Academy of Sciences ; National Natural Science Foundation of China
源URL[http://ir.igsnrr.ac.cn/handle/311030/181306]  
专题中国科学院地理科学与资源研究所
通讯作者Zou, Lei
作者单位1.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Key Lab Cycle & Related Land Surface Proc, Beijing 100101, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式
GB/T 7714		 Shen, Jianming,Zou, Lei,Dong, Yi,et al. Improving Daily Streamflow Forecasting Using Deep Belief Net-Work Based on Flow Regime Recognition[J]. WATER,2022,14(14):17.
APA Shen, Jianming,Zou, Lei,Dong, Yi,Xiao, Shuai,Zhao, Yanjun,&Liu, Chengjian.(2022).Improving Daily Streamflow Forecasting Using Deep Belief Net-Work Based on Flow Regime Recognition.WATER,14(14),17.
MLA Shen, Jianming,et al."Improving Daily Streamflow Forecasting Using Deep Belief Net-Work Based on Flow Regime Recognition".WATER 14.14(2022):17.

入库方式： OAI收割

来源：地理科学与资源研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。