Support Vector Regression Based on Particle Swarm Optimization for Rainfall Forecasting

Abstract

This study applies a novel neural network technique, support vector regression (SVR), to rainfall forecasting. To build an effective SVR model, SVR's parameters must be set carefully. This study proposes a novel approach, known as particle swarm optimization algorithm (SVR-PSO), which searches for SVR's optimal parameters, and then adopts the optimal parameters to construct the SVR models. The monthly rainfall in the Guangxi of China during 1954-2008 were employed as the data set. The experimental results demonstrate that SVR-PSO outperforms the SVR models based on the normalized mean square error (NMSE) and mean absolute percentage error (MAPE).