Logo do repositório
 
Publicação

Modeling PM2.5 Urban Pollution Using Machine Learning and Selected Meteorological Parameters

2017Artigo científico Acesso aberto
Ver registo simples
dc.contributor.authorKleine Deters, Jan
dc.contributor.authorZalakeviciute, Rasa
dc.contributor.authorGonzalez, Mario
dc.contributor.authorRybarczyk, Yves
dc.contributor.institutionDEE2010-C2 Robótica e Manufactura Integrada por Computador
dc.contributor.institutionDEE - Departamento de Engenharia Electrotécnica e de Computadores
dc.contributor.institutionCTS - Centro de Tecnologia e Sistemas
dc.contributor.pblInstitute of Electrical and Electronics Engineers (IEEE)
dc.date.accessioned2023-01-05T22:09:45Z
dc.date.available2023-01-05T22:09:45Z
dc.date.issued2017
dc.description.abstractOutdoor air pollution costs millions of premature deaths annually, mostly due to anthropogenic fine particulate matter (or PM2.5). Quito, the capital city of Ecuador, is no exception in exceeding the healthy levels of pollution. In addition to the impact of urbanization, motorization, and rapid population growth, particulate pollution is modulated by meteorological factors and geophysical characteristics, which complicate the implementation of the most advanced models of weather forecast. Thus, this paper proposes a machine learning approach based on six years of meteorological and pollution data analyses to predict the concentrations of PM2.5 from wind (speed and direction) and precipitation levels. The results of the classification model show a high reliability in the classification of low (<10 μg/m3) versus high (>25 μg/m3) and low (<10 μg/m3) versus moderate (10-25 μg/m3) concentrations of PM2.5. A regression analysis suggests a better prediction of PM2.5 when the climatic conditions are getting more extreme (strong winds or high levels of precipitation). The high correlation between estimated and real data for a time series analysis during the wet season confirms this finding. The study demonstrates that the use of statistical models based on machine learning is relevant to predict PM2.5 concentrations from meteorological data.en
dc.description.versionpublishersversion
dc.description.versionpublished
dc.format.extent4044324
dc.identifier.doi10.1155/2017/5106045
dc.identifier.issn2090-0147
dc.identifier.otherPURE: 3820152
dc.identifier.otherPURE UUID: 9d6d31ad-9654-4778-ab24-da761f80e3ee
dc.identifier.otherScopus: 85022062861
dc.identifier.otherWOS: 000403645600001
dc.identifier.urihttp://hdl.handle.net/10362/147005
dc.identifier.urlhttps://www.scopus.com/pages/publications/85022062861
dc.language.isoeng
dc.peerreviewedyes
dc.subjectNEURAL-NETWORKS
dc.subjectAIR-POLLUTION
dc.subjectSURFACE WIND
dc.subjectWRF MODEL
dc.subjectPREDICTION
dc.subjectSCALE
dc.subjectSignal Processing
dc.subjectGeneral Computer Science
dc.subjectElectrical and Electronic Engineering
dc.subjectSDG 11 - Sustainable Cities and Communities
dc.titleModeling PM2.5 Urban Pollution Using Machine Learning and Selected Meteorological Parametersen
dc.typejournal article
degois.publication.titleJournal of Electrical and Computer Engineering
degois.publication.volume2017
dspace.entity.typePublication
rcaap.rightsopenAccess

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
Modeling_PM2.5_Urban_Pollution_Using_Machine.pdf
Tamanho:
3.86 MB
Formato:
Adobe Portable Document Format
Ver/Abrir

Coleções

Home collection (FCT)