000890956 001__ 890956
000890956 005__ 20230127125338.0
000890956 0247_ $$2doi$$a10.5194/egusphere-egu21-7596
000890956 0247_ $$2ISSN$$a0022-7722
000890956 0247_ $$2ISSN$$a1447-073X
000890956 0247_ $$2ISSN$$a1447-6959
000890956 0247_ $$2Handle$$a2128/27286
000890956 037__ $$aFZJ-2021-01272
000890956 041__ $$aEnglish
000890956 082__ $$a610
000890956 1001_ $$0P:(DE-Juel1)171435$$aBetancourt, Clara$$b0$$eCorresponding author
000890956 1112_ $$aEGU General Assembly 2021$$cOnline$$d2021-04-19 - 2021-04-30$$gvEGU21$$wOnline
000890956 245__ $$aGlobal fine resolution mapping of ozone metrics through explainable machine learning
000890956 260__ $$c2021
000890956 3367_ $$0PUB:(DE-HGF)1$$2PUB:(DE-HGF)$$aAbstract$$babstract$$mabstract$$s1614863314_1630
000890956 3367_ $$033$$2EndNote$$aConference Paper
000890956 3367_ $$2BibTeX$$aINPROCEEDINGS
000890956 3367_ $$2DRIVER$$aconferenceObject
000890956 3367_ $$2DataCite$$aOutput Types/Conference Abstract
000890956 3367_ $$2ORCID$$aOTHER
000890956 520__ $$aThrough the availability of multi-year ground based ozone observations on a global scale, substantial geospatial meta data, and high performance computing capacities, it is now possible to use machine learning for a global data-driven ozone assessment. In this presentation, we will show a novel, completely data-driven approach to map tropospheric ozone globally.</p><p>Our goal is to interpolate ozone metrics and aggregated statistics from the database of the Tropospheric Ozone Assessment Report (TOAR) onto a global 0.1&#176; x 0.1&#176; resolution grid. &#160;It is challenging to interpolate ozone, a toxic greenhouse gas because its formation depends on many interconnected environmental factors on small scales. We conduct the interpolation with various machine learning methods trained on aggregated hourly ozone data from five years at more than 5500 locations worldwide. We use several geospatial datasets as training inputs to provide proxy input for environmental factors controlling ozone formation, such as precursor emissions and climate. The resulting maps contain different ozone metrics, i.e. statistical aggregations which are widely used to assess air pollution impacts on health, vegetation, and climate.</p><p>The key aspects of this contribution are twofold: First, we apply explainable machine learning methods to the data-driven ozone assessment. Second, we discuss dominant uncertainties relevant to the ozone mapping and quantify their impact whenever possible. Our methods include a thorough a-priori uncertainty estimation of the various data and methods, assessment of scientific consistency, finding critical model parameters, using ensemble methods, and performing error modeling.</p><p>Our work aims to increase the reliability and integrity of the derived ozone maps through the provision of scientific robustness to a data-centric machine learning task. This study hence represents a blueprint for how to formulate an environmental machine learning task scientifically, gather the necessary data, and develop a data-driven workflow that focuses on optimizing transparency and applicability of its product to maximize its scientific knowledge return.</p>
000890956 536__ $$0G:(DE-HGF)POF4-511$$a511 - Enabling Computational- & Data-Intensive Science and Engineering (POF4-511)$$cPOF4-511$$fPOF IV$$x0
000890956 536__ $$0G:(EU-Grant)787576$$aIntelliAQ - Artificial Intelligence for Air Quality (787576)$$c787576$$fERC-2017-ADG$$x1
000890956 536__ $$0G:(DE-Juel1)kiste_20200501$$aAI Strategy for Earth system data (kiste_20200501)$$ckiste_20200501$$fAI Strategy for Earth system data$$x2
000890956 536__ $$0G:(DE-Juel-1)ESDE$$aEarth System Data Exploration (ESDE)$$cESDE$$x3
000890956 588__ $$aDataset connected to CrossRef
000890956 7001_ $$0P:(DE-Juel1)180752$$aStadtler, Scarlet$$b1$$ufzj
000890956 7001_ $$0P:(DE-HGF)0$$aStomberg, Timo$$b2
000890956 7001_ $$0P:(DE-HGF)0$$aEdrich, Ann-Kathrin$$b3
000890956 7001_ $$0P:(DE-Juel1)186635$$aPatnala, Ankit$$b4$$ufzj
000890956 7001_ $$0P:(DE-HGF)0$$aRoscher, Ribana$$b5
000890956 7001_ $$0P:(DE-HGF)0$$aKowalski, Julia$$b6
000890956 7001_ $$0P:(DE-Juel1)6952$$aSchultz, Martin G.$$b7
000890956 773__ $$a10.5194/egusphere-egu21-7596
000890956 8564_ $$uhttps://juser.fz-juelich.de/record/890956/files/20210113_betancourt_egu_abstract.pdf$$yOpenAccess
000890956 909CO $$ooai:juser.fz-juelich.de:890956$$pec_fundedresources$$pdriver$$pVDB$$popen_access$$popenaire
000890956 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)171435$$aForschungszentrum Jülich$$b0$$kFZJ
000890956 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)180752$$aForschungszentrum Jülich$$b1$$kFZJ
000890956 9101_ $$0I:(DE-HGF)0$$6P:(DE-HGF)0$$a Universität Bonn$$b2
000890956 9101_ $$0I:(DE-588b)36225-6$$6P:(DE-HGF)0$$aRWTH Aachen$$b3$$kRWTH
000890956 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)186635$$aForschungszentrum Jülich$$b4$$kFZJ
000890956 9101_ $$0I:(DE-HGF)0$$6P:(DE-HGF)0$$a Universität Bonn$$b5
000890956 9101_ $$0I:(DE-588b)36225-6$$6P:(DE-HGF)0$$aRWTH Aachen$$b6$$kRWTH
000890956 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)6952$$aForschungszentrum Jülich$$b7$$kFZJ
000890956 9130_ $$0G:(DE-HGF)POF3-512$$1G:(DE-HGF)POF3-510$$2G:(DE-HGF)POF3-500$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bKey Technologies$$lSupercomputing & Big Data$$vData-Intensive Science and Federated Computing$$x0
000890956 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$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
000890956 9141_ $$y2021
000890956 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS
000890956 915__ $$0StatID:(DE-HGF)1030$$2StatID$$aDBCoverage$$bCurrent Contents - Life Sciences
000890956 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000890956 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search
000890956 915__ $$0StatID:(DE-HGF)1040$$2StatID$$aDBCoverage$$bZoological Record
000890956 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bANAT SCI INT : 2015
000890956 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection
000890956 915__ $$0StatID:(DE-HGF)0111$$2StatID$$aWoS$$bScience Citation Index Expanded
000890956 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5
000890956 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000890956 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC
000890956 915__ $$0StatID:(DE-HGF)0310$$2StatID$$aDBCoverage$$bNCBI Molecular Biology Database
000890956 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews
000890956 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline
000890956 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bThomson Reuters Master Journal List
000890956 920__ $$lyes
000890956 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
000890956 980__ $$aabstract
000890956 980__ $$aVDB
000890956 980__ $$aUNRESTRICTED
000890956 980__ $$aI:(DE-Juel1)JSC-20090406
000890956 9801_ $$aFullTexts