Author(s)

G. Latini, R. Cocci Grifoni, L. Magnaterra & G. Passerini

Abstract

Comparing neural networks and transfer function models for ozone forecasting G. Latini, R. Cocci Grifoni, L. Magnaterra & G. Passerini Dipartimento di Energetics, Universitd Politecnica delle Marche, Italy. Abstract Surface ozone concentrations are determined by complex interactions between precursors and are triggered by meteorological conditions. Ozone concentrations are, in fact, strongly linked to meteorological conditions in the boundary layer and to land-sea breezes at coastal sites. The related relationships are typically complex and nonlinear and might be better captured by dynarnical models, namely Neural Networks and Transfer Function models. Aim of our work is the identification of proper Transfer Function models and the estimation of their parameters. Here we present an outline of the methodology that was used to develop the air pollution forecast model for a complex coastal valley. We also investigate the potential for using Neural Networks, namely Multi-Layer Perceptron networks,

Keywords