Modeling sulphur dioxide due to vehicular traffic using artificial neural network.

The dispersion characteristics of vehicular exhaust are highly non-linear. The deterministic as well as numerical models are unable to predict these air pollutants precisely. Artificial neural network (ANN), having the capability to recognize the non-linearity present in the noisy data, has been used in the present work to model the emission concentration of sulphur dioxide from vehicular source in an urban area. ANN model is developed with different combinations of traffic and meteorological parameters. The model prediction reveals that the artificial neural network trained with both traffic and meteorological parameters together shows better performance in predicting SO2 concentration.