Concentration Prediction of Air Pollutants in Tehran

Air pollution is one of the most serious problems in Iran today and this project tries to be a part of the studies in this field. As Tehran, the capital city of Iran, is one of the most polluted cities, this paper includes modeling the concentration of air pollutants in this city. A hybrid model is represented in this project so as to simulate the hourly concentration of criteria air pollutants in Tehran in the year 1395 (March/20/2016 - March/20/2017). In this model, the observed data of pollutants concentrations are denoised by the wavelet transformation, then a neuro-fuzzy network with fuzzy clustering algorithm is used for modeling. This model simulates the hourly concentration of a pollutant in the station that has the most data of that pollutant in the specified time interval. The value of R-2 for the models is almost 0.9 that is a sign of their accuracy.