Short-time fuzzy DAP predictor for air pollution due to vehicular traffic

In this paper an air pollution mathematical model is proposed, based on fuzzy logic theory, which allows to take into account model uncertainties and, consequently, is able to describe the above-mentioned phenomenon. More precisely, the fuzzification procedure of a daily-DAP (Dosage Area Product) model [2] is explained; this model describes daily dynamics of a variable (DAP) representative of ground level pollution produced by vehicular traffic in urban areas complex orography. This procedure consists of two different phases. The first phase concerns prediction of meteorological and emission variables (model input) and is implemented through fuzzy prediction of time series. The second phase of modelling concerns the determination (using fuzzy inference methods) of the predicted meteorological classes, each of them contributes in determining model output (i.e. prediction of CO concentration). We applied this to the town of Palermo and carried out digital simulation experiments.