Neural networks and Cao's method: A novel approach for air pollutants time series forecasting

Artificial neural networks are widely used as predictor systems for the pollutants time series. In recent years, the dynamic system theory has also been exploited to find the optimal sampling time interval and the minimum embedding dimension of environmental time series in order to get helpful information and to implement appropriately the forecasting networks. In this paper, we present a novel approach to predict the concentration level of air pollutants in the area of the Messina Strait, whose harbor represents the unique link to reach Sicily Island from Europe by cars and trucks. By coupling feedforward neural networks with Cao's method, we predict the level of carbon monoxide and hydrocarbons from one to ten hours ahead with an accuracy of more than 90%.