Abstract

We have analyzed the possibility to predict hourly averages of sulfur dioxide concentrations in the atmosphere at a site not far from the downtown area in the city of Santiago, Chile. We have compared the forecasts produced assuming persistence, linear regressions and feed forward neural networks. The effect of meteorological conditions is included by using forecasted values of temperature, relative humidity and wind speed at the time of the intended prediction as inputs to the different models. The best predictions for hourly averages are obtained with a three-layer neural network that has hourly averages of sulfur dioxide concentrations every 6h on the previous day plus the actual values of the meteorological variables as input. Training the network with 1995 data, error in 8h in advance prediction for 1996 data is of the order of 30%. Copyright © 2001 Elsevier Science Ltd.