The forecast of C02 emissions in China based on RBF neural networks

Radial Basis Function (RBF, for short) neural networks are widely applied for their strong abilities in nonlinear mapping, fast learning, good generalization performance and great accuracy in numerical approximation. In this paper, a RBF neural network combined with time series on C0₂ emissions is proposed by using the characteristics. It examines the rationality and flexibility of the RBF neural network used in prediction of C0₂ emissions in China. The empirical result indicates that the RBF neural network improves the overall reliability of time series forecasting and has a high precision, meanwhile it is a baton to the next phase of the “energy saving and greenhouse gas emissions reduction” project, which is of practical and potential value in China.