Artificial neural networks based air pollution monitoring in industrial sites

Since several decades, industrial pollution and especially atmospheric pollution receive an important interest due to the fact that industries are more and more pollutants. Thanks to the development of many prediction techniques, scientists and industrials give more importance to pollution prediction. The prediction of industrial air pollutants concentrations allows taking preventive measures such as reducing pollutant emission in the atmosphere. The aim of this work is to predict two pollutants concentration (NOx and CO) in industrial sites by the use of a nonlinear Auto Regressive model (NARX) based Artificial Neural Network (ANN). Database used to train the neural network corresponds to historical time series of meteorological variables (wind speed, wind direction, temperature and relative humidity) and concentrations of pollutants in the petrochemical plant of Skikda site. The estimation performance is determined using the Roots Mean Square Error (RMSE) and Mean Absolute Error (MAE). Results will show the importance of the meteorological variable set on the prediction of pollutants concentrations and the neural network efficiency.