Research on forecast model for sustainable development of economy-environment system based on PCA and SVM

According to the complexity of Economy-Environment system and many environmental indicators, which influence the development of economy, we first use Principal Component Analysis (PCA) to realize the dimension reduction of the environmental indicators. Then a non-linear method-Support Vector Regression (SVR), which is a part of Support Vector machine (SVM) is used to establish the forecast model for sustainable development of Economy-Environment system based on the data which are treated by PCA. Finally experiments based on the environmental indicators and Gross Domestic Product (GDP) of Hebei province is given. The research shows that compared with neural network, SVR has simple mathematical model and high forecast precision.