Study of atmospheric ozone formation by means of a neural network-based model

The occurrence of high ozone levels in the atmosphere of urban areas has be come a serious pollution problem in a number of large cities in the world. Although mathematical models have been proposed for predicting ozone concen trations as a function of a number of gas components, sometimes there are u ncertainties due to lack of the combined effects of meteorological factors and the complex chemical reaction system involved. The application of neural network models, based on measured values of air p ollutants and meteorological factors at different locations within the Sao Paulo Metropolitan Area, combine chemical and meteorological information. T his has shown to be a promising tool for predicting ozone concentration. Si mulations carried out with the model indicate the sensitivity of ozone in r elation to different air pollution and weather conditions. Predictions usin g this model have shown good agreement with measured values of ozone concen trations.