Abstract not found

We use a local learning algorithm to predict the abundance of the Alpine ibex population living in the Gran Paradiso National Park, Northern Italy. Population abundance, recorded for a period of 40 years, have been recently analyzed by Jacobson et al. (2004), who showed that the rate of increase of the population depends both on its density and snow depth. In the same paper, a threshold linear model is proposed for predicting the population abundance. In this paper,

Local linear models are developed and tested in this paper to predict the next day PM10 concentrations in two urban sites in Lombardy. The fast implementation of the algorithm, developed by IRIDIA, Brussels, and called lazy learning, is exploited to analyse several alternative combinations of meteorological and air quality input variables and to determine their relative importance. Most state-of-the-art modelling approaches, both physically based and black-box, such as feed-forward neural networks, are based on a unique relation between a number of input variables and the required output, namely the predicted concentration of a pollutant at a given point. However, such relations are difficult to assess and, apart from