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

Author

Zheng Haiming ; Shang Xiaoxiao

Author_Institution

Dept. of Mech. Eng., North China Electr. Power Univ., Baoding, China

fYear

2013

fDate

29-30 June 2013

Firstpage

1287

Lastpage

1289

Abstract

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.

Keywords

air pollution; atmospheric humidity; atmospheric pressure; atmospheric temperature; wind; NO₂; PM2.5 concentration; RBF neural network; SO₂; atmospheric PM2.5 prediction; classic BP network model; humidity parameter; pressure parameter; temperature parameter; traditional forecast methods; wind speed; Atmospheric modeling; Biological neural networks; Predictive models; Radial basis function networks; Training; Wind speed; Atmospheric PM2.5; Model Construction; Prediction; RBF Neural Network;

fLanguage

English

Publisher

ieee

Conference_Titel

Digital Manufacturing and Automation (ICDMA), 2013 Fourth International Conference on

Conference_Location

Qingdao

Type

conf

DOI

10.1109/ICDMA.2013.306

Filename

6598230