Correlation of air pollution and meteorological data using neural networks

In order to develop an environmental forecasting tool, the Neural Network method of computational intelligence is investigated. For this purpose, hourly and daily time series of CO, NO2 and O3, as well as a variety of meteorological variables are employed in various multi-layer percepton (MLP) models, in order to provide reliable air quality forecasts, using as a test case the city of Athens, Greece. The performance of the two most satisfactory models are presented thoroughly and compared using certain statistical indices. Results verify both the potential and the complicated nature of the method.