An improved hybrid data-driven model and its application in daily rainfall-runoff simulation

6th Digital Earth Summit

地球科学;计算机科学

Kan, Guangyuan^1,2 ; He, Xiaoyan^1 ; Ding, Liuqian^1 ; Li, Jiren^1 ; Lei, Tianjie^1 ; Liang, Ke^3 ; Hong, Yang^2,4

State Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, Research Center on Flood and Drought Disaster Reduction of the Ministry of Water Resources, China Institute of Water Resources and Hydropower Research, Beijing

100038, China^1

State Key Laboratory of Hydroscience and Engineering, Department of Hydraulic Engineering, Tsinghua University, Beijing, China^2

College of Hydrology and Water Resources, Hohai University, Nanjing

210098, China^3

Department of Civil Engineering and Environmental Science, University of Oklahoma, Norman

OK, United States^4

关键词: Calibration methodologies;    Daily rainfall-runoff simulations;    Forecasting capability;    K;    means clustering;    Nonlinear characteristics;    Numerical experiments;    Poor performance;    Xin-anjiang models;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/46/1/012029/pdf
DOI  :  10.1088/1755-1315/46/1/012029

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

In previous literatures, a coupled data-driven rainfall-runoff (RR) model, NU-PEK, has been proposed and successfully applied in hourly RR simulation task. However, numerical experiments show that its performance for daily RR simulation is unsatisfactory. It is noticed that the poor performance is due to the inability of the original model to capture the much higher non-linear characteristics contained in the daily data. In order to improve the nonlinearity simulation capability of the original model, an improved model named NU-PKEK and its calibration methodology are developed in this paper. The improved model is constituted by adding a K-means clustering module and utilizing multiple NU-PEK modules instead of using only one NU-PEK model. This study applies the improved model, the Xinanjiang model, and the original model for daily RR simulation in Chengcun catchment for intercomparison and verification. The simulation results prove that the NU-PKEK performs best, and has better simulation and forecasting capability.