Study on Prediction of Atmospheric PM2.5 Based on RBF Neural Network

Because of the varying concentration of atmospheric PM2.5 have strong nonlinear characteristics, the traditional forecast methods are difficult to make accurate prediction. In this paper the parameters included PM10, SO2, NO2, temperature, pressure, humidity, wind direction, wind speed are selected as the influence factors, and the prediction models based on RBF neural network are constructed. Then the model is used to predict the concentration of PM2.5 and compared with the classic BP network model. The result shows that the RBF neural network model has more advantages in the prediction of PM2.5.