SVR Smoggy Forecast Model Based on GA Method Optimization

Aiming at the difficult problem of Smoggy forecast, this paper puts forward a model which is based on support vector regression (SVR) method, and the GA method to optimal parameters is used. Factor analysis is used to reduce eigenvector dimension. Optimal parameters of SVR is find by the cross validation. GA method with optimal parameters is put into the SVR model to the predict PM2.5 of Baoding city. The prediction result and the actual are compared to select PM2.5 forecasting model.