A Novel Hybrid RBF Neural Network EnsembleModel Using Least Squares Support Vector Regression for Rainfall Forecasting
Accurate forecasting of rainfall has been one of the most important issues in hydrological research. Due to rainfall forecasting involves a ratber complex nonlinear data pattern; there are lots of novel forecasting approaches to improve the forecasting accuracy. In this study, a novel hybrid Radial Basis Function Neural Network (RBF-NN) ensemble model using Least Squares Support Vector Regression (LS-SVR) is developed for rainfaH forecasting. In the process of ensemble modeling, the first stage the initial data set is divided into different tnining sets by used Bagging and Boosting technoloy. In the second stage, these training sets are input to the different individual RBF-NN models, and then various single RBF-NN predictors are produced based on diversity principle. In the third stage, the Partial Least Square (PLS) technology is used to choosing the appropriate number of neural nerwork ensemble members. In the final stage, LS-SVR is used for ensemble of the RBF-NN to prediction purpose. For testing purposes, this study compare the new ensemble models performance with some existing neural network ensemble approacbes in terms of monthly rainfall forecasting on Guangxi, China. Experimental results reveal that the predictions using the proposed approach are consistently better than those obtained using the other methods presented in this study in terms of the same measurements. Tbose results show that the proposed hybrid ensemble technique provides a promising alternative to rainfall prediction.
radial basis function neural network least squares support vector regression ensemble rainfall forecasting
Xiaoming Pan Jiansheng Wu
Department of Physics and Information Science Liuzhou Teachers College Liuzhou 545004, Guangxi, Chin Department of Mathematical and Computer Sciences Liuzhou Teachers College Liuzhou 545004, Guangxi, C
国际会议
昆明
英文
190-194
2010-10-17（万方平台首次上网日期，不代表论文的发表时间）