The aim of the present work is to provide a methodological procedure to forecast hourly Ozone concentrations using Artificial Neural Networks (ANNs). The study area is the urban center of Chennai, and the results are presented here. The model can predict the mean surface ozone based on the parameters like concentration of Nitrogen-di-oxide, temperature, relative humidity, sun spot number, wind direction and wind speed. The model can perform well both in training and independent periods. The achieved results were satisfactory.