000916411 001__ 916411
000916411 005__ 20230309201804.0
000916411 0247_ $$2doi$$a10.5194/gmd-15-8913-2022
000916411 0247_ $$2ISSN$$a1991-959X
000916411 0247_ $$2ISSN$$a1991-9603
000916411 0247_ $$2Handle$$a2128/33319
000916411 0247_ $$2WOS$$aWOS:000898538800001
000916411 037__ $$aFZJ-2022-06211
000916411 082__ $$a550
000916411 1001_ $$0P:(DE-Juel1)176602$$aKleinert, Felix$$b0$$eCorresponding author
000916411 245__ $$aRepresenting chemical history in ozone time-series predictions – a model experiment study building on the MLAir (v1.5) deep learning framework
000916411 260__ $$aKatlenburg-Lindau$$bCopernicus$$c2022
000916411 3367_ $$2DRIVER$$aarticle
000916411 3367_ $$2DataCite$$aOutput Types/Journal article
000916411 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1671714043_12005
000916411 3367_ $$2BibTeX$$aARTICLE
000916411 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000916411 3367_ $$00$$2EndNote$$aJournal Article
000916411 520__ $$aTropospheric ozone is a secondary air pollutant that is harmful to living beings and crops. Predicting ozone concentrations at specific locations is thus important to initiate protection measures, i.e. emission reductions or warnings to the population. Ozone levels at specific locations result from emission and sink processes, mixing and chemical transformation along an air parcel's trajectory. Current ozone forecasting systems generally rely on computationally expensive chemistry transport models (CTMs). However, recently several studies have demonstrated the potential of deep learning for this task. While a few of these studies were trained on gridded model data, most efforts focus on forecasting time series from individual measurement locations. In this study, we present a hybrid approach which is based on time-series forecasting (up to 4 d) but uses spatially aggregated meteorological and chemical data from upstream wind sectors to represent some aspects of the chemical history of air parcels arriving at the measurement location. To demonstrate the value of this additional information, we extracted pseudo-observation data for Germany from a CTM to avoid extra complications with irregularly spaced and missing data. However, our method can be extended so that it can be applied to observational time series. Using one upstream sector alone improves the forecasts by 10 % during all 4 d, while the use of three sectors improves the mean squared error (MSE) skill score by 14 % during the first 2 d of the prediction but depends on the upstream wind direction. Our method shows its best performance in the northern half of Germany for the first 2 prediction days. Based on the data's seasonality and simulation period, we shed some light on our models' open challenges with (i) spatial structures in terms of decreasing skill scores from the northern German plain to the mountainous south and (ii) concept drifts related to an unusually cold winter season. Here we expect that the inclusion of explainable artificial intelligence methods could reveal additional insights in future versions of our model.
000916411 536__ $$0G:(DE-HGF)POF4-5111$$a5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
000916411 536__ $$0G:(EU-Grant)787576$$aIntelliAQ - Artificial Intelligence for Air Quality (787576)$$c787576$$fERC-2017-ADG$$x1
000916411 536__ $$0G:(GEPRIS)491111487$$aOpen-Access-Publikationskosten Forschungszentrum Jülich (OAPKFZJ) (491111487)$$c491111487$$x2
000916411 536__ $$0G:(DE-Juel-1)ESDE$$aEarth System Data Exploration (ESDE)$$cESDE$$x3
000916411 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
000916411 7001_ $$0P:(DE-Juel1)177004$$aLeufen, Lukas H.$$b1
000916411 7001_ $$00000-0002-1055-9727$$aLupascu, Aurelia$$b2
000916411 7001_ $$00000-0002-2219-4657$$aButler, Tim$$b3
000916411 7001_ $$0P:(DE-Juel1)6952$$aSchultz, Martin G.$$b4
000916411 770__ $$aBenchmark datasets and machine learning algorithms for Earth system science data
000916411 773__ $$0PERI:(DE-600)2456725-5$$a10.5194/gmd-15-8913-2022$$gVol. 15, no. 23, p. 8913 - 8930$$n23$$p8913 - 8930$$tGeoscientific model development$$v15$$x1991-959X$$y2022
000916411 8564_ $$uhttps://juser.fz-juelich.de/record/916411/files/gmd-15-8913-2022.pdf$$yOpenAccess
000916411 8767_ $$d2023-03-09$$eAPC$$jZahlung erfolgt
000916411 909CO $$ooai:juser.fz-juelich.de:916411$$pec_fundedresources$$pVDB$$pdriver$$pOpenAPC$$popen_access$$popenaire$$popenCost$$pdnbdelivery
000916411 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)176602$$aForschungszentrum Jülich$$b0$$kFZJ
000916411 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)177004$$aForschungszentrum Jülich$$b1$$kFZJ
000916411 9101_ $$0I:(DE-HGF)0$$60000-0002-1055-9727$$a IASS: Institute for Advanced Sustainability Studies$$b2
000916411 9101_ $$0I:(DE-HGF)0$$60000-0002-2219-4657$$a IASS: Institute for Advanced Sustainability Studies$$b3
000916411 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)6952$$aForschungszentrum Jülich$$b4$$kFZJ
000916411 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$$x0
000916411 9141_ $$y2022
000916411 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2022-11-25
000916411 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2022-11-25
000916411 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000916411 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2022-11-25
000916411 915__ $$0StatID:(DE-HGF)1150$$2StatID$$aDBCoverage$$bCurrent Contents - Physical, Chemical and Earth Sciences$$d2022-11-25
000916411 915__ $$0StatID:(DE-HGF)9905$$2StatID$$aIF >= 5$$bGEOSCI MODEL DEV : 2021$$d2022-11-25
000916411 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2021-01-16T18:00:10Z
000916411 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2021-01-16T18:00:10Z
000916411 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2022-11-25
000916411 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2022-11-25
000916411 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000916411 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2022-11-25
000916411 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2022-11-25
000916411 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bGEOSCI MODEL DEV : 2021$$d2022-11-25
000916411 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2022-11-25
000916411 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2022-11-25
000916411 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2022-11-25
000916411 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Peer review$$d2021-01-16T18:00:10Z
000916411 915pc $$0PC:(DE-HGF)0000$$2APC$$aAPC keys set
000916411 915pc $$0PC:(DE-HGF)0001$$2APC$$aLocal Funding
000916411 915pc $$0PC:(DE-HGF)0002$$2APC$$aDFG OA Publikationskosten
000916411 915pc $$0PC:(DE-HGF)0003$$2APC$$aDOAJ Journal
000916411 920__ $$lyes
000916411 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
000916411 9801_ $$aFullTexts
000916411 980__ $$ajournal
000916411 980__ $$aVDB
000916411 980__ $$aUNRESTRICTED
000916411 980__ $$aI:(DE-Juel1)JSC-20090406
000916411 980__ $$aAPC