Water Quality Prediction Using LS-SVM and Particle Swarm Optimization

Abstract

This paper deals with the study of a water quality prediction model through application of LS-SVM in Liuxi River in Guangzhou. To overcome the shortcomings of traditional BP algorithm as being slow to converge and easy to reach extreme minimum value, least squares support vector machine (LS-SVM) combined with particle swarm optimization (PSO) is used to time series prediction. The LS-SVM can overcome some shortcoming in the Multilayer Perceptron (MLP) and the PSO is used to tune the LS-SVM parameters automatically. It enhances the efficiency and the capability of prediction. Through simulation testing the model shows high efficiency in forecasting the water quality of the Liuxi River.