Hybrid Wavelet-M5 Model Tree for Rainfall-Runoff Modeling

被引:53
作者
Nourani, Vahid [1 ,2 ]
Tajbakhsh, Ali Davanlou [1 ]
Molajou, Amir [3 ]
Gokcekus, Huseyin [4 ]
机构
[1] Univ Tabriz, Dept Water Resources Engn, Fac Civil Engn, Tabriz 51666, Iran
[2] Near East Univ, Dept Civil Engn, POB 99138,Mersin 10, Nicosia, North Cyprus, Cyprus
[3] Iran Univ Sci & Technol, Dept Water Resources Engn, Fac Civil Engn, Tehran 51546, Iran
[4] Near East Univ, Dept Civil Engn, Turkish Republ Northern Cyprus, CY-99138 Nicosia, Cyprus
关键词
Decision tree; M5 model tree; Multilinear model; Rainfall-runoff modeling; Wavelet transform; ARTIFICIAL NEURAL-NETWORK; PREDICTION; RIVER; ANNS;
D O I
10.1061/(ASCE)HE.1943-5584.0001777
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
In this study, the hybrid wavelet-M5 model was introduced to model the rainfall-runoff process via three different data division strategies (75%-25%, 60%-40%, and 50%-50%) for two different catchments at both daily and monthly scales. The performance of the wavelet-M5 model was also examined in the case of multi-step-ahead forecasting. In this way, first, the rainfall and runoff time series were decomposed using the wavelet transform to several sub-time series to handle the multiresolution characteristic of rainfall and runoff time series. Then the obtained subseries were applied to the M5 model tree as inputs. The obtained results showed the better performance of the wavelet-M5 model in comparison with individual artificial neural network (ANN) and M5 models so that the obtained determination coefficient was 0.80 by the hybrid wavelet-M5 model, while it was calculated as 0.23 and 0.19 by the ANN and M5 tree models, respectively. It was also concluded that the wavelet-M5 model could lead to better performance in the multi-step-ahead forecasting issue since the catchment showed a semilinear behavior because the error would be constant in linear models. (c) 2019 American Society of Civil Engineers.
引用
收藏
页数:14
相关论文
共 25 条
[1]   Two decades of anarchy? Emerging themes and outstanding challenges for neural network river forecasting [J].
Abrahart, Robert J. ;
Anctil, Francois ;
Coulibaly, Paulin ;
Dawson, Christian W. ;
Mount, Nick J. ;
See, Linda M. ;
Shamseldin, Asaad Y. ;
Solomatine, Dimitri P. ;
Toth, Elena ;
Wilby, Robert L. .
PROGRESS IN PHYSICAL GEOGRAPHY-EARTH AND ENVIRONMENT, 2012, 36 (04) :480-513
[2]   Closure to "Comparison of ANNs and empirical approaches for predicting watershed runoff " by Jagadeesh Anmala, Bin Zhang, and Rao S. Govindaraju [J].
Anmala, J ;
Zhang, B ;
Govindaraju, RS .
JOURNAL OF WATER RESOURCES PLANNING AND MANAGEMENT-ASCE, 2002, 128 (05) :381-381
[3]   Comparison of ANNs and empirical approaches for predicting watershed runoff [J].
Anmala, J ;
Zhang, B ;
Govindaraju, RS .
JOURNAL OF WATER RESOURCES PLANNING AND MANAGEMENT, 2000, 126 (03) :156-166
[4]  
[Anonymous], 2012, INT J ENG RES DEV, DOI DOI 10.1016/J.AGWAT.2019.02.041
[5]   Neural networks and M5 model trees in modelling water level-discharge relationship [J].
Bhattacharya, B ;
Solomatine, DP .
NEUROCOMPUTING, 2005, 63 :381-396
[6]  
Bureau of Meteorology, HYDR REF STAT
[7]   Hydrological modelling using artificial neural networks [J].
Dawson, CW ;
Wilby, RL .
PROGRESS IN PHYSICAL GEOGRAPHY-EARTH AND ENVIRONMENT, 2001, 25 (01) :80-108
[8]  
Govindaraju RS, 2000, J HYDROL ENG, V5, P124
[9]   ARTIFICIAL NEURAL-NETWORK MODELING OF THE RAINFALL-RUNOFF PROCESS [J].
HSU, KL ;
GUPTA, HV ;
SOROOSHIAN, S .
WATER RESOURCES RESEARCH, 1995, 31 (10) :2517-2530
[10]   Integrated approach to model decomposed flow hydrograph using artificial neural network and conceptual techniques [J].
Jain, A ;
Srinivasulu, S .
JOURNAL OF HYDROLOGY, 2006, 317 (3-4) :291-306