001014687 001__ 1014687
001014687 005__ 20240116084318.0
001014687 0247_ $$2doi$$a10.1021/acs.est.3c05104
001014687 0247_ $$2ISSN$$a0013-936X
001014687 0247_ $$2ISSN$$a1520-5851
001014687 0247_ $$2datacite_doi$$a10.34734/FZJ-2023-03392
001014687 0247_ $$2pmid$$a37661931
001014687 0247_ $$2WOS$$aWOS:001061743500001
001014687 037__ $$aFZJ-2023-03392
001014687 041__ $$aEnglish
001014687 082__ $$a333.7
001014687 1001_ $$0P:(DE-Juel1)171435$$aBetancourt, Clara$$b0
001014687 245__ $$aGraph Machine Learning for Improved Imputation of Missing Tropospheric Ozone Data
001014687 260__ $$aColumbus, Ohio$$bAmerican Chemical Society$$c2023
001014687 3367_ $$2DRIVER$$aarticle
001014687 3367_ $$2DataCite$$aOutput Types/Journal article
001014687 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1702460602_490
001014687 3367_ $$2BibTeX$$aARTICLE
001014687 3367_ $$2ORCID$$aJOURNAL_ARTICLE
001014687 3367_ $$00$$2EndNote$$aJournal Article
001014687 520__ $$aGaps in the measurement series of atmospheric pollutants can impede the reliable assessment of their impacts and trends. We propose a new method for missing data imputation of the air pollutant tropospheric ozone by using the graph machine learning algorithm “correct and smooth”. This algorithm uses auxiliary data that characterize the measurement location and, in addition, ozone observations at neighboring sites to improve the imputations of simple statistical and machine learning models. We apply our method to data from 278 stations of the year 2011 of the German Environment Agency (Umweltbundesamt – UBA) monitoring network. The preliminary version of these data exhibits three gap patterns: shorter gaps in the range of hours, longer gaps of up to several months in length, and gaps occurring at multiple stations at once. For short gaps of up to 5 h, linear interpolation is most accurate. Longer gaps at single stations are most effectively imputed by a random forest in connection with the correct and smooth. For longer gaps at multiple stations, the correct and smooth algorithm improved the random forest despite a lack of data in the neighborhood of the missing values. We therefore suggest a hybrid of linear interpolation and graph machine learning for the imputation of tropospheric ozone time series.
001014687 536__ $$0G:(DE-HGF)POF4-5111$$a5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
001014687 536__ $$0G:(EU-Grant)787576$$aIntelliAQ - Artificial Intelligence for Air Quality (787576)$$c787576$$fERC-2017-ADG$$x1
001014687 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
001014687 7001_ $$0P:(DE-HGF)0$$aLi, Cathy W. Y.$$b1
001014687 7001_ $$0P:(DE-Juel1)176602$$aKleinert, Felix$$b2
001014687 7001_ $$0P:(DE-Juel1)6952$$aSchultz, Martin G.$$b3$$eCorresponding author
001014687 770__ $$aData Science for Advancing Environmental Science, Engineering and Technology
001014687 773__ $$0PERI:(DE-600)1465132-4$$a10.1021/acs.est.3c05104$$gp. acs.est.3c05104$$p18246-18258$$tEnvironmental science & technology$$v57$$x0013-936X$$y2023
001014687 8564_ $$uhttps://juser.fz-juelich.de/record/1014687/files/betancourt_graphml_2023.pdf$$yOpenAccess
001014687 8564_ $$uhttps://juser.fz-juelich.de/record/1014687/files/betancourt_graphml_2023.gif?subformat=icon$$xicon$$yOpenAccess
001014687 8564_ $$uhttps://juser.fz-juelich.de/record/1014687/files/betancourt_graphml_2023.jpg?subformat=icon-1440$$xicon-1440$$yOpenAccess
001014687 8564_ $$uhttps://juser.fz-juelich.de/record/1014687/files/betancourt_graphml_2023.jpg?subformat=icon-180$$xicon-180$$yOpenAccess
001014687 8564_ $$uhttps://juser.fz-juelich.de/record/1014687/files/betancourt_graphml_2023.jpg?subformat=icon-640$$xicon-640$$yOpenAccess
001014687 8767_ $$d2023-09-06$$eHybrid-OA$$jPublish and Read
001014687 909CO $$ooai:juser.fz-juelich.de:1014687$$pdnbdelivery$$popenCost$$pec_fundedresources$$pVDB$$pdriver$$popen_access$$popenaire
001014687 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)171435$$aForschungszentrum Jülich$$b0$$kFZJ
001014687 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)6952$$aForschungszentrum Jülich$$b3$$kFZJ
001014687 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5111$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vEnabling Computational- & Data-Intensive Science and Engineering$$x0
001014687 9141_ $$y2023
001014687 915pc $$0PC:(DE-HGF)0000$$2APC$$aAPC keys set
001014687 915pc $$0PC:(DE-HGF)0122$$2APC$$aHelmholtz: American Chemical Society 01/01/2023
001014687 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2022-11-22
001014687 915__ $$0StatID:(DE-HGF)1190$$2StatID$$aDBCoverage$$bBiological Abstracts$$d2022-11-22
001014687 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2022-11-22
001014687 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001014687 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
001014687 915__ $$0StatID:(DE-HGF)0420$$2StatID$$aNationallizenz$$d2023-08-29$$wger
001014687 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2023-08-29
001014687 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2023-08-29
001014687 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2023-08-29
001014687 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews$$d2023-08-29
001014687 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2023-08-29
001014687 915__ $$0StatID:(DE-HGF)1060$$2StatID$$aDBCoverage$$bCurrent Contents - Agriculture, Biology and Environmental Sciences$$d2023-08-29
001014687 915__ $$0StatID:(DE-HGF)1040$$2StatID$$aDBCoverage$$bZoological Record$$d2023-08-29
001014687 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bENVIRON SCI TECHNOL : 2022$$d2023-08-29
001014687 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2023-08-29
001014687 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2023-08-29
001014687 915__ $$0StatID:(DE-HGF)9910$$2StatID$$aIF >= 10$$bENVIRON SCI TECHNOL : 2022$$d2023-08-29
001014687 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
001014687 980__ $$ajournal
001014687 980__ $$aVDB
001014687 980__ $$aUNRESTRICTED
001014687 980__ $$aI:(DE-Juel1)JSC-20090406
001014687 980__ $$aAPC
001014687 9801_ $$aAPC
001014687 9801_ $$aFullTexts