Estimation of PM10 concentration from air quality data in the vicinity of a major steelworks site in the metropolitan area of Aviles (Northern Spain) using machine learning techniques

Atmospheric particulate matter (PM) is one of the pollutants that may have a significant impact on human health. Data collected over 7years from the air quality monitoring station at the LD-III steelworks, belonging to the Arcelor-Mittal Steel Company, located in the metropolitan area of Aviles (Principality of Asturias, Northern Spain), is analyzed using four different mathematical models: vector autoregressive moving-average, autoregressive integrated moving-average (ARIMA), multilayer perceptron neural networks and support vector machines with regression. Measured monthly, the average concentration of pollutants (SO2, NO and NO2) and PM10 (particles with a diameter less than 10m) is used as input to forecast the monthly average concentration of PM10 from one to 7months ahead. Simulations showed that the ARIMA model performs better than the other models when forecasting 1month ahead, while in the forecast from one to 9months ahead the best performance is given by the support vector regression.