Comparative assessment of neural networks and regression models for forecasting summertime ozone in Athens

Chaloulakou, A; Saisana, M; Spyrellis, N

dc.contributor.author	Chaloulakou, A	en
dc.contributor.author	Saisana, M	en
dc.contributor.author	Spyrellis, N	en
dc.date.accessioned	2014-03-01T01:18:46Z
dc.date.available	2014-03-01T01:18:46Z
dc.date.issued	2003	en
dc.identifier.issn	0048-9697	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/15187
dc.subject	Air quality forecasting	en
dc.subject	Model performance indices	en
dc.subject	Neural networks	en
dc.subject	Ozone	en
dc.subject.classification	Environmental Sciences	en
dc.subject.other	Estimation	en
dc.subject.other	Forecasting	en
dc.subject.other	Linear equations	en
dc.subject.other	Mathematical models	en
dc.subject.other	Neural networks	en
dc.subject.other	Regression analysis	en
dc.subject.other	Ozone concentration	en
dc.subject.other	Ozone	en
dc.subject.other	ozone	en
dc.subject.other	artificial neural network	en
dc.subject.other	atmospheric pollution	en
dc.subject.other	modeling	en
dc.subject.other	ozone	en
dc.subject.other	summer	en
dc.subject.other	air pollution	en
dc.subject.other	air quality	en
dc.subject.other	article	en
dc.subject.other	artificial neural network	en
dc.subject.other	comparative study	en
dc.subject.other	experimental model	en
dc.subject.other	forecasting	en
dc.subject.other	Greece	en
dc.subject.other	linear regression analysis	en
dc.subject.other	prediction	en
dc.subject.other	priority journal	en
dc.subject.other	summer	en
dc.subject.other	Greece	en
dc.title	Comparative assessment of neural networks and regression models for forecasting summertime ozone in Athens	en
heal.type	journalArticle	en
heal.identifier.primary	10.1016/S0048-9697(03)00335-8	en
heal.identifier.secondary	http://dx.doi.org/10.1016/S0048-9697(03)00335-8	en
heal.language	English	en
heal.publicationDate	2003	en
heal.abstract	A comparison study has been performed with neural networks (NNs) and multiple linear regression models to forecast the next day's maximum hourly ozone concentration in the Athens basin at four representative monitoring stations that show very different behavior. All models use 11 predictors (eight meteorological and three persistence variables) and are developed and validated between April and October from 1992 to 1999. Performance results based on a wide set of forecast quality measures indicate that the NNs provide better estimates of ozone concentrations at the monitoring sites, whilst the more often used linear models are less efficient at accurately forecasting high ozone concentrations. The violation of the European information threshold of 180 mug/m(3) is successfully predicted by the NN in 72% of the cases on average. Results at all stations are consistent with similar ozone forecast studies using NNs in other European cities. (C) 2003 Elsevier Science B.V. All rights reserved.	en
heal.publisher	ELSEVIER SCIENCE BV	en
heal.journalName	Science of the Total Environment	en
dc.identifier.doi	10.1016/S0048-9697(03)00335-8	en
dc.identifier.isi	ISI:000184929200001	en
dc.identifier.volume	313	en
dc.identifier.issue	1-3	en
dc.identifier.spage	1	en
dc.identifier.epage	13	en