Artificial neural network forecast application for fine particulate matter concentration using meteorological data

Most parts of the urban areas are faced with the problem of floating fine particulate matter.Therefore, it is crucial to estimate the amounts of fine particulate matter concentrations through the urbanatmosphere. In this research, an artificial neural network technique was utilized to model the PM2.5 dispersionin Tehran City. Factors which are influencing the predicted value consist of weather-related and air pollutionrelateddata, i.e. wind speed, humidity, temperature, SO2, CO, NO2, and PM2.5 as target values. These factorshave been considered in 19 measuring stations (zones) over urban area across Tehran City during fouryears, from March 2011 to March 2015. The results indicate that the network with hidden layer includingsix neurons at training epoch 113, has the best performance with the lowest error value (MSE=0.049438)on considering PM2.5 concentrations across metropolitan areas in Tehran. Furthermore, the R value forregression analysis of training, validation, test, and all data are 0.65898, 0.6419, 0.54027, and 0.62331,respectively. This study also represents the artificial neural networks have satisfactory implemented forresolving complex patterns in the field of air pollution.

کلیدواژه ها:

Air pollution ، Artificial neural network (ANN) ، Meteorological data ، PM2.5 concentration ، Tehran City