Cascade feed forward neural network-based model for air pollutants evaluation of single monitoring stations in urban areas

Abstract

In this paper, air pollutants concentrations for N O2 , N O, N Ox and P M 10 in a single monitoring station are predicted using the data coming from other different monitoring stations located nearby. A cascade feed forward neural network based modeling is proposed. The main aim is to provide a methodology leading to the introduction of virtual monitoring station points consistent with the actual stations located in the city of Catania in Italy.