Neuro-fuzzy models for AIR quality planing: The case study of ozone in Northern Italy

Abstract

To design air quality plans, regional authorities need tools to understand both the impact of emission reduction strategies on pollution index and the costs of emission reduction. The problem can be formalized as a multi-objective mathematical program, integrating local pollutant-precursor models and the estimate of emission reduction costs. Both aspects present several complex elements. In particular the source-receptor models, describing transport phenomenon and chemical non linear dynamics, require deterministic modelling system with high computational cost. In this paper a method based on neuro-fuzzy models is proposed to identify local ozone-precursor models on the basis of the simulations of a photochemical modelling system (GAMES). The methodology has been performed for Lombardia region (Northern Italy); this area, characterized by a complex terrain, high urban and industrial emissions and a dense road network, is often affected by severe photochemical pollution episodes during summer.