Authors: J C M Pires B Gonçalves F G Azevedo A P Carneiro N Rego A J B Assembleia J F B Lima P A Silva C Alves F G Martins
Publish Date: 2012/03/01
Volume: 19, Issue: 8, Pages: 3228-3234
Abstract
This study proposes three methodologies to define artificial neural network models through genetic algorithms GAs to predict the nextday hourly average surface ozone O3 concentrations GAs were applied to define the activation function in hidden layer and the number of hidden neuronsTwo of the methodologies define threshold models which assume that the behaviour of the dependent variable O3 concentrations changes when it enters in a different regime two and four regimes were considered in this study The change from one regime to another depends on a specific value threshold value of an explanatory variable threshold variable which is also defined by GAs The predictor variables were the hourly average concentrations of carbon monoxide CO nitrogen oxide nitrogen dioxide NO2 and O3 recorded in the previous day at an urban site with traffic influence and also meteorological data hourly averages of temperature solar radiation relative humidity and wind speed The study was performed for the period from May to August 2004Several models were achieved and only the best model of each methodology was analysed In threshold models the variables selected by GAs to define the O3 regimes were temperature CO and NO2 concentrations due to their importance in O3 chemistry in an urban atmosphereAuthors are grateful to Comissão de Coordenação da Direcção RegionalNorte and to Instituto Geofísico da Universidade do Porto for kindly providing the air quality and meteorological data This work was supported by Fundação para a Ciência e Tecnologia FCT JCM Pires also thank the FCT for the postDoctoral fellowship SFRH/BPD/66721/2009
Keywords: