Forecasting ozone threshold exceedances in urban background areas using supervised classification and easy-access information

Classification models to forecast exceedance of the ozone (O3) threshold established by European legislation are rare in literature, as is the focus on background O3, with higher concentrations at city outskirts. This study evaluated the performance of nine classifiers to forecast this threshold exc...

Descripción completa

Detalles Bibliográficos
Autor: Gómez Losada, Álvaro
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2018
País:España
Institución:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/138159
Acceso en línea:https://hdl.handle.net/11441/138159
https://doi.org/10.1016/j.apr.2018.04.002
Access Level:acceso abierto
Palabra clave:Background ozone
Forecasting
Classification
Imbalanced learning
Ensembles
Cost of learning
id ES_f2a4e2e07b91c2c41449c5d2811476ed
oai_identifier_str oai:idus.us.es:11441/138159
network_acronym_str ES
network_name_str España
repository_id_str
spelling Forecasting ozone threshold exceedances in urban background areas using supervised classification and easy-access informationGómez Losada, ÁlvaroBackground ozoneForecastingClassificationImbalanced learningEnsemblesCost of learningClassification models to forecast exceedance of the ozone (O3) threshold established by European legislation are rare in literature, as is the focus on background O3, with higher concentrations at city outskirts. This study evaluated the performance of nine classifiers to forecast this threshold exceedance by background O3. Models used five large hourly background O3 data sets (2006–2015), and included temporal features describing the O3 formation dynamic. Bagging and stacking ensembles of such classifiers and their cost of learning were also evaluated. C5.0 and nnet classifiers achieved the best forecasting performance, even at imbalanced learning. Bagging ensembles outperformed stacking approaches, although with little accuracy improvement as compared to classifiers. The cost of learning evidenced similar performance results from reduced fractions of original data sets. The use of these models to forecast background O3 threshold exceedances are encouraged due to the performances obtained and to their easy reproducibilityElsevierEstadística e Investigación Operativa2018info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttps://hdl.handle.net/11441/138159https://doi.org/10.1016/j.apr.2018.04.002reponame:idUS. Depósito de Investigación de la Universidad de Sevillainstname:Universidad de Sevilla (US)InglésAtmospheric Pollution Research, 9, 1052-1061.https://doi.org/10.1016/j.apr.2018.04.002info:eu-repo/semantics/openAccessoai:idus.us.es:11441/1381592026-06-17T12:51:07Z
dc.title.none.fl_str_mv Forecasting ozone threshold exceedances in urban background areas using supervised classification and easy-access information
title Forecasting ozone threshold exceedances in urban background areas using supervised classification and easy-access information
spellingShingle Forecasting ozone threshold exceedances in urban background areas using supervised classification and easy-access information
Gómez Losada, Álvaro
Background ozone
Forecasting
Classification
Imbalanced learning
Ensembles
Cost of learning
title_short Forecasting ozone threshold exceedances in urban background areas using supervised classification and easy-access information
title_full Forecasting ozone threshold exceedances in urban background areas using supervised classification and easy-access information
title_fullStr Forecasting ozone threshold exceedances in urban background areas using supervised classification and easy-access information
title_full_unstemmed Forecasting ozone threshold exceedances in urban background areas using supervised classification and easy-access information
title_sort Forecasting ozone threshold exceedances in urban background areas using supervised classification and easy-access information
dc.creator.none.fl_str_mv Gómez Losada, Álvaro
author Gómez Losada, Álvaro
author_facet Gómez Losada, Álvaro
author_role author
dc.contributor.none.fl_str_mv Estadística e Investigación Operativa
dc.subject.none.fl_str_mv Background ozone
Forecasting
Classification
Imbalanced learning
Ensembles
Cost of learning
topic Background ozone
Forecasting
Classification
Imbalanced learning
Ensembles
Cost of learning
description Classification models to forecast exceedance of the ozone (O3) threshold established by European legislation are rare in literature, as is the focus on background O3, with higher concentrations at city outskirts. This study evaluated the performance of nine classifiers to forecast this threshold exceedance by background O3. Models used five large hourly background O3 data sets (2006–2015), and included temporal features describing the O3 formation dynamic. Bagging and stacking ensembles of such classifiers and their cost of learning were also evaluated. C5.0 and nnet classifiers achieved the best forecasting performance, even at imbalanced learning. Bagging ensembles outperformed stacking approaches, although with little accuracy improvement as compared to classifiers. The cost of learning evidenced similar performance results from reduced fractions of original data sets. The use of these models to forecast background O3 threshold exceedances are encouraged due to the performances obtained and to their easy reproducibility
publishDate 2018
dc.date.none.fl_str_mv 2018
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/11441/138159
https://doi.org/10.1016/j.apr.2018.04.002
url https://hdl.handle.net/11441/138159
https://doi.org/10.1016/j.apr.2018.04.002
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Atmospheric Pollution Research, 9, 1052-1061.
https://doi.org/10.1016/j.apr.2018.04.002
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:idUS. Depósito de Investigación de la Universidad de Sevilla
instname:Universidad de Sevilla (US)
instname_str Universidad de Sevilla (US)
reponame_str idUS. Depósito de Investigación de la Universidad de Sevilla
collection idUS. Depósito de Investigación de la Universidad de Sevilla
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869424300839141376
score 15.300719

Similares en LA Referencia