000892258 001__ 892258
000892258 005__ 20230127125339.0
000892258 0247_ $$2doi$$a10.13140/RG.2.2.17134.13123
000892258 0247_ $$2Handle$$a2128/27722
000892258 037__ $$aFZJ-2021-01988
000892258 041__ $$aEnglish
000892258 1001_ $$0P:(DE-Juel1)171435$$aBetancourt, Clara$$b0$$eCorresponding author$$ufzj
000892258 1112_ $$aEGU General Assembly 2021$$cOnline$$d2021-04-19 - 2021-04-30$$gvEGU21$$wOnline
000892258 245__ $$aGlobal fine resolution mapping of ozone metrics through explainable machine learning
000892258 260__ $$c2021
000892258 3367_ $$033$$2EndNote$$aConference Paper
000892258 3367_ $$2DataCite$$aOther
000892258 3367_ $$2BibTeX$$aINPROCEEDINGS
000892258 3367_ $$2DRIVER$$aconferenceObject
000892258 3367_ $$2ORCID$$aLECTURE_SPEECH
000892258 3367_ $$0PUB:(DE-HGF)6$$2PUB:(DE-HGF)$$aConference Presentation$$bconf$$mconf$$s1620111872_3737$$xOther
000892258 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.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° x 0.1° resolution grid.  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.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.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.
000892258 536__ $$0G:(DE-HGF)POF4-511$$a511 - Enabling Computational- & Data-Intensive Science and Engineering (POF4-511)$$cPOF4-511$$fPOF IV$$x0
000892258 536__ $$0G:(EU-Grant)787576$$aIntelliAQ - Artificial Intelligence for Air Quality (787576)$$c787576$$fERC-2017-ADG$$x1
000892258 536__ $$0G:(DE-Juel-1)ESDE$$aEarth System Data Exploration (ESDE)$$cESDE$$x2
000892258 588__ $$aDataset connected to DataCite
000892258 7001_ $$0P:(DE-Juel1)180752$$aStadtler, Scarlet$$b1$$ufzj
000892258 7001_ $$0P:(DE-HGF)0$$aStomberg, Timo$$b2
000892258 7001_ $$0P:(DE-HGF)0$$aEdrich, Ann-Kathrin$$b3
000892258 7001_ $$0P:(DE-Juel1)186635$$aPatnala, Ankit$$b4$$ufzj
000892258 7001_ $$0P:(DE-HGF)0$$aRoscher, Ribana$$b5
000892258 7001_ $$0P:(DE-HGF)0$$aKowalski, Julia$$b6
000892258 7001_ $$0P:(DE-Juel1)6952$$aSchultz, Martin$$b7$$ufzj
000892258 773__ $$a10.13140/RG.2.2.17134.13123
000892258 8564_ $$uhttps://juser.fz-juelich.de/record/892258/files/20210430_betancourt_vegu21_display.pdf$$yOpenAccess
000892258 909CO $$ooai:juser.fz-juelich.de:892258$$pec_fundedresources$$pdriver$$pVDB$$popen_access$$popenaire
000892258 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)171435$$aForschungszentrum Jülich$$b0$$kFZJ
000892258 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)180752$$aForschungszentrum Jülich$$b1$$kFZJ
000892258 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)186635$$aForschungszentrum Jülich$$b4$$kFZJ
000892258 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)6952$$aForschungszentrum Jülich$$b7$$kFZJ
000892258 9130_ $$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$$x0
000892258 9131_ $$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$$x0
000892258 9141_ $$y2021
000892258 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000892258 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000892258 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
000892258 980__ $$aconf
000892258 980__ $$aVDB
000892258 980__ $$aUNRESTRICTED
000892258 980__ $$aI:(DE-Juel1)JSC-20090406
000892258 9801_ $$aFullTexts