Prevision of industrial SO2 pollutant concentration applying ANNs

Air pollution is one of the most important environmental problems. Sulphur Dioxide (SO₂) and Suspended Particles are considered the most important atmospheric pollutants. The prevision of industrial SO₂ air pollutant concentrations would allow us to take preventive measures such as reducing the pollutant emission to the atmosphere. In This work we apply Feed Forward Artificial Neural Network to predict the air pollution concentrations in Salamanca, Mexico. The work focuses on the daily maximum concentration of SO₂. A 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 SO₂ along a year. Results of the experiments with the proposed system show the importance of the meteorological variable set on the prediction of SO₂ concentrations and the neural network efficiency. The performance estimation is determined using the Root Mean Square Error (RMSE) and Mean Absolute Error (MAE).