Neural Models for Prediction of Maximum Daily Particulate Matter PM10 Concentration in the Air in Big Cities as Ecological Safety Management Tools

The aim of the study was to examine the possibilities of the development of a prognostic instrument for the air quality management in cities. The study was focused on the development of the neural network models for prediction of the classes of the air quality state in relation to maximum daily dust PM10 concentration. The air quality class was predicted for the next day in relation to maximal daily concentrations. The models MLP and RBF were tested. The tests were carried out in the city of Lodz in central Poland. The results of the modelling were satisfactory. In the optimally constructed models false prognosis (in testing series) were only 7.4% in the case of predicting maximal daily concentration (test series) and 2.7% (training series). A low level of error prediction confirmed the fact, that the neural network models is an effective instrument of the air quality management in cities.