Prediction of pollutant levels in causeway bay area of Hong Kong using an improved neural network model

The prediction of air quality parameters is of great interest in environmental studies today due to the health impact caused by airborne pollutants [e.g., sulfur dioxide (SO2); nitrogen oxide (NO,); nitric oxide (NO); nitrogen dioxide (NO2); carbon monoxide (CO); respirable suspended particulates (RSPs), etc.] in urban areas. Artificial neural networks are regarded as a reliable and cost-effective method for prediction tasks. The work reported here develops an improved neural network model which combines both the principal component analysis (PCA) technique and the radial basis function (RBF) network to analyze and predict the pollutant data recorded. In the study, PCA is used to reduce and orthogonalize the original variables. The variables treated are then used as input vectors in a RBF neural network model to forecast the pollutant levels, e.g., the RSP level in the downtown area of Hong Kong. This improved method is evaluated based on hourly time series RSP concentrations collected at the Causeway Bay roadside gaseous monitoring station in Hong Kong during 1999. The simulation results show the effectiveness of the model. For high-dimensional input vectors including simpler network architecture and faster learning speed without compromising the generalization capability of the network, the proposed algorithm has advantages over traditional RBF network learning.