Comparative evaluation of gaussian, stochastic and artificial neural network based line source models

This paper presents a comparative evaluation of deterministic, stochastic and artificial neural network (ANN) based line source models in predicting carbon monoxide (CO) concentrations near an urban roadway/intersection. The observed concentration data of CO for the critical winter period (21 st - 31st December. 1999). at two-air quality control regions- a traffic intersection and an arterial road in the Delhi city, have been compared with model predictions. A range of statistical indicators has been used for model performance evaluation. The results show that ANN based line source models are comparatively more accurate in predicting the CO concentration near urban roadway/intersection than the deterministic and univariate statistical models. Copyright © 2009 by IICAI.