Wavelet Genetic Algorithm-Support Vector Regression (Wavelet GA-SVR) for Monthly Flow Forecasting

摘要

Highly reliable and accurate forecasts of river flows are of prime importance in water resources management. In this study, wavelet genetic algorithm-support vector regression (wavelet GA-SVR) and regular genetic algorithm-support vector regression (GA-SVR) models are employed for forecasting monthly flow on two rivers in northern Iran. In the developed models, the genetic algorithm is applied for selecting the optimal parameters of the support vector regression (SVR) models. The relative performance of the wavelet GA-SVR models was compared to regular GA-SVR models. It is found that the wavelet GA-SVR models are able to provide more accurate forecasting results than the regular GA-SVR models. These indicate that the wavelet GA-SVR models are a promising method than the regular GA-SVR models in forecasting monthly river flow data.