Prediction of Air Pollution in Tehran based on Evolutionary Models

With respect to the increasing problems of air pollution due to urban development, pollution control is necessary. The purpose of this study is to predict the density of particulate matter less than 10 microns (PM10), to plan and reduce its effects and to avoid reaching a crisis situation. For this purpose, the data of air pollutants and meteorological parameters recorded at Aghdasiyeh Weather Quality Control Station and Mehrabad Weather Station in Tehran were used as input parameters. Next, Artificial Neural Network with Back Propagation (BP), its hybrid with GA (BP-GA) and PSO (BP-PSO) were used and ultimately the performance of these three models was compared with each other. It was concluded that BP-PSO has the highest accuracy and performance. In addition it was also found that the results are more accurate for shorter time periods and this is because the large fluctuation of data in long-term returns negative effect on network performance. Also unregistered data have negative effect on predictions.