Optimized scenario for rainfall forecasting using genetic algorithm coupled with artificial neural network

被引:119
作者
Nasseri, M. [1 ,2 ]
Asghari, K. [3 ]
Abedini, M. J. [1 ]
机构
[1] Shiraz Univ, Fac Engn, Dept Civil Engn, Shiraz, Iran
[2] Sazeh Pardazi Co Engn, Dept Water & Environm Engn, Tehran, Iran
[3] Isfahan Univ Technol, Dept Civil Engn, Esfahan, Iran
关键词
rainfall forecasting; artificial neural networks; genetic algorithms; input determination;
D O I
10.1016/j.eswa.2007.08.033
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Rainfall forecasting plays many important role in water resources studies such as river training works and design of flood warning systems. Recent advancement in artificial intelligence and in particular techniques aimed at converting input to output for highly non-linear, non-convex and dimensionalized processes such as rainfall field, provide an alternative approach for developing rainfall forecasting model. Artificial neural networks (ANNs), which perform a nonlinear mapping between inputs and outputs, are such a technique. Current literatures on artificial neural networks show that the selection of network architecture and its efficient training procedure are major obstacles for their daily usage. In this paper, feed-forward type networks will be developed to simulate the rainfall field and a so-called back propagation (BP) algorithm coupled with genetic algorithm (GA) will be used to train and optimize the networks. The techniquc will be implemented to forecast rainfall for a number of times using rainfall hyetograph of recording rain gauges in the Upper Parramatta catchment in the western suburbs of Sydney, Australia. Results of the Study showed the structuring of ANN network with the input parameter selection, when coupled with GA, performed better compared to similar work of using ANN alone. (C) 2007 Elsevier Ltd. All rights reserved.
引用
收藏
页码:1415 / 1421
页数:7
相关论文
共 27 条
[1]  
[Anonymous], 1994, The 19th Annual SAS Users Group International Conference (SUGI 19), SAS Institute Inc., Dallas, TX
[2]   Input determination for neural network models in water resources applications. Part 1 - background and methodology [J].
Bowden, GJ ;
Dandy, GC ;
Maier, HR .
JOURNAL OF HYDROLOGY, 2005, 301 (1-4) :75-92
[3]   Input determination for neural network models in water resources applications. Part 2. Case study: forecasting salinity in a river [J].
Bowden, GJ ;
Maier, HR ;
Dandy, GC .
JOURNAL OF HYDROLOGY, 2005, 301 (1-4) :93-107
[4]   RAINFALL FORECASTING IN SPACE AND TIME USING A NEURAL NETWORK [J].
FRENCH, MN ;
KRAJEWSKI, WF ;
CUYKENDALL, RR .
JOURNAL OF HYDROLOGY, 1992, 137 (1-4) :1-31
[5]  
Goldberg D.E, 1989, GENETIC ALGORITHMS S
[6]  
Govindaraju RS, 2000, J HYDROL ENG, V5, P124
[7]  
Govindaraju RS, 2000, J HYDROL ENG, V5, P115
[8]  
HOLLAND JH, 1975, ADAPTATION NATURAL A
[9]  
Hsu K., 1996, P 3 INT WORKSH NHRI, V17
[10]  
Hsu KL, 1997, J APPL METEOROL, V36, P1176, DOI 10.1175/1520-0450(1997)036<1176:PEFRSI>2.0.CO