Short-term forecast of urban ozone episodes using fuzzy neural networks

Hadjileontiadou, S; Stathopoulos, A

dc.contributor.author	Hadjileontiadou, S	en
dc.contributor.author	Stathopoulos, A	en
dc.date.accessioned	2014-03-01T02:44:11Z
dc.date.available	2014-03-01T02:44:11Z
dc.date.issued	2006	en
dc.identifier.issn	1018-4619	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/31741
dc.relation.uri	http://www.scopus.com/inward/record.url?eid=2-s2.0-33748990637&partnerID=40&md5=3935e14d7365f7b68a51d03e12fadf4a	en
dc.subject	Forecast of ozone pollution episodes	en
dc.subject	Fuzzy-neural networks and photochemical pollution	en
dc.subject	Modeling ozone	en
dc.subject	O3 forecast with fuzzy-neural networks	en
dc.subject	Real-time O3 forecast	en
dc.subject	Short-term urban O3 forecast	en
dc.subject.classification	Environmental Sciences	en
dc.subject.other	concentration (composition)	en
dc.subject.other	forecasting method	en
dc.subject.other	fuzzy mathematics	en
dc.subject.other	ozone	en
dc.subject.other	urban area	en
dc.subject.other	Athens [Attica]	en
dc.subject.other	Attica	en
dc.subject.other	Eurasia	en
dc.subject.other	Europe	en
dc.subject.other	Greece	en
dc.subject.other	Southern Europe	en
dc.title	Short-term forecast of urban ozone episodes using fuzzy neural networks	en
heal.type	conferenceItem	en
heal.language	English	en
heal.publicationDate	2006	en
heal.abstract	This paper presents a short-term forecasting prototype, O3-AFM (Ozone-Adaptive Fuzzy Model), of hourly urban ozone (O3) concentrations at two spatial points of interest, when presented with inputs of O3 source emissions measured at one of the above points. The structure of the O3-AFM, which combines characteristics from the Neural Networks and the Fuzzy Logic methodologies, allows for its adaptability and function upon real-time data. By means of the AFM 2.0 (Adaptive Fuzzy Modeller, of STMicroelectronics, 1998) software and real data from pollution monitoring stations in the city of Athens, Greece, two O3-AFM scenarios were developed, which performed over varying forecasting time periods. Considering the fact that, the O3-AFM functions only upon an indirect indicator of stagnating conditions (CO concentration), its performance was validated by means of specific performance indexes and found to be quite satisfactory and promising, yet leaving space for further refinement e.g., upon larger data records. The proposed approach can highly contribute to the support of a reliable, on time decision-making process for the initiation of tactics towards the control of the urban pollution episode. © by PSP 2006.	en
heal.publisher	PARLAR SCIENTIFIC PUBLICATIONS (P S P)	en
heal.journalName	Fresenius Environmental Bulletin	en
dc.identifier.isi	ISI:000240784900007	en
dc.identifier.volume	15	en
dc.identifier.issue	8 B	en
dc.identifier.spage	883	en
dc.identifier.epage	890	en