Research on the water quality forecast method based on SVM

In order to improve and protect human being's environment, water resource should be effectively monitored and managed. The support vector machine (SVM) is an algorithm based on structure risk minimizing principle and having high generalization ability. It is strong to solve the problem with small sample, nonlinear and high dimension. In this paper, based on a lot of research fruits of water quality forecast methods at home and abroad, a water forecast method based on support vector machine is put forward, and a water quality multi-classification forecasting model based on time sequence's SVM is established. Its water quality of Tai Lake is aimed and researched by the forecast method of water quality. Its correct rate of SVM model can reach 84.62%, its correct rate of back-propagation neutral network (BPNN) model is 80.77%. The simulation results have proved that its training speed and testing accuracy of SVM are higher than back-propagation neutral network. From the experimental result, the water quality forecast model based on SVM can correctly predict its grade of water quality and provide a new way for forecast of water quality.