000889193 001__ 889193
000889193 005__ 20230127125338.0
000889193 0247_ $$2doi$$a10.5194/gmd-14-1-2021
000889193 0247_ $$2ISSN$$a1991-959X
000889193 0247_ $$2ISSN$$a1991-9603
000889193 0247_ $$2Handle$$a2128/26697
000889193 0247_ $$2altmetric$$aaltmetric:97074776
000889193 0247_ $$2WOS$$aWOS:000606577700001
000889193 037__ $$aFZJ-2021-00103
000889193 041__ $$aEnglish
000889193 082__ $$a550
000889193 1001_ $$0P:(DE-Juel1)176602$$aKleinert, Felix$$b0$$eCorresponding author
000889193 245__ $$aIntelliO3-ts v1.0: a neural network approach to predict near-surface ozone concentrations in Germany
000889193 260__ $$aKatlenburg-Lindau$$bCopernicus$$c2021
000889193 3367_ $$2DRIVER$$aarticle
000889193 3367_ $$2DataCite$$aOutput Types/Journal article
000889193 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1634739649_19753
000889193 3367_ $$2BibTeX$$aARTICLE
000889193 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000889193 3367_ $$00$$2EndNote$$aJournal Article
000889193 520__ $$aThe prediction of near-surface ozone concentrations is important for supporting regulatory procedures for the protection of humans from high exposure to air pollution. In this study, we introduce a data-driven forecasting model named “IntelliO3-ts”, which consists of multiple convolutional neural network (CNN) layers, grouped together as inception blocks. The model is trained with measured multi-year ozone and nitrogen oxide concentrations of more than 300 German measurement stations in rural environments and six meteorological variables from the meteorological COSMO reanalysis. This is by far the most extensive dataset used for time series predictions based on neural networks so far. IntelliO3-ts allows the prediction of daily maximum 8 h average (dma8eu) ozone concentrations for a lead time of up to 4 d, and we show that the model outperforms standard reference models like persistence models. Moreover, we demonstrate that IntelliO3-ts outperforms climatological reference models for the first 2 d, while it does not add any genuine value for longer lead times. We attribute this to the limited deterministic information that is contained in the single-station time series training data. We applied a bootstrapping technique to analyse the influence of different input variables and found that the previous-day ozone concentrations are of major importance, followed by 2 m temperature. As we did not use any geographic information to train IntelliO3-ts in its current version and included no relation between stations, the influence of the horizontal wind components on the model performance is minimal. We expect that the inclusion of advection–diffusion terms in the model could improve results in future versions of our model.
000889193 536__ $$0G:(DE-HGF)POF4-5111$$a5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
000889193 536__ $$0G:(EU-Grant)787576$$aIntelliAQ - Artificial Intelligence for Air Quality (787576)$$c787576$$fERC-2017-ADG$$x1
000889193 536__ $$0G:(DE-Juel1)PHD-NO-GRANT-20170405$$aPhD no Grant - Doktorand ohne besondere Förderung (PHD-NO-GRANT-20170405)$$cPHD-NO-GRANT-20170405$$x2
000889193 536__ $$0G:(DE-Juel1)deepacf_20191101$$aDeep Learning for Air Quality and Climate Forecasts (deepacf_20191101)$$cdeepacf_20191101$$fDeep Learning for Air Quality and Climate Forecasts$$x3
000889193 536__ $$0G:(DE-Juel-1)ESDE$$aEarth System Data Exploration (ESDE)$$cESDE$$x4
000889193 588__ $$aDataset connected to CrossRef
000889193 7001_ $$0P:(DE-Juel1)177004$$aLeufen, Lukas H.$$b1
000889193 7001_ $$0P:(DE-Juel1)6952$$aSchultz, Martin G.$$b2
000889193 773__ $$0PERI:(DE-600)2456725-5$$a10.5194/gmd-14-1-2021$$gVol. 14, no. 1, p. 1 - 25$$n1$$p1 - 25$$tGeoscientific model development$$v14$$x1991-9603$$y2021
000889193 8564_ $$uhttps://juser.fz-juelich.de/record/889193/files/IntelliO3-ts.pdf$$yOpenAccess
000889193 8767_ $$8Helmholtz-PUC-2021-21$$92021-04-01$$d2021-04-12$$eAPC$$jZahlung erfolgt$$pgmd-2020-169$$zBelegnr.  1200165527 / 2021
000889193 909CO $$ooai:juser.fz-juelich.de:889193$$pdnbdelivery$$popenCost$$pec_fundedresources$$pVDB$$pdriver$$pOpenAPC$$popen_access$$popenaire
000889193 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)176602$$aForschungszentrum Jülich$$b0$$kFZJ
000889193 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)177004$$aForschungszentrum Jülich$$b1$$kFZJ
000889193 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)6952$$aForschungszentrum Jülich$$b2$$kFZJ
000889193 9131_ $$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
000889193 9141_ $$y2021
000889193 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2020-08-31
000889193 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2020-08-31
000889193 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000889193 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2020-08-31
000889193 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bGEOSCI MODEL DEV : 2018$$d2020-08-31
000889193 915__ $$0StatID:(DE-HGF)9905$$2StatID$$aIF >= 5$$bGEOSCI MODEL DEV : 2018$$d2020-08-31
000889193 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2020-08-31
000889193 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2020-08-31
000889193 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2020-08-31
000889193 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2020-08-31
000889193 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2020-08-31
000889193 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000889193 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2020-08-31
000889193 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2020-08-31
000889193 915__ $$0StatID:(DE-HGF)1150$$2StatID$$aDBCoverage$$bCurrent Contents - Physical, Chemical and Earth Sciences$$d2020-08-31
000889193 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2020-08-31
000889193 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2020-08-31
000889193 920__ $$lyes
000889193 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
000889193 9201_ $$0I:(DE-Juel1)NIC-20090406$$kNIC$$lJohn von Neumann - Institut für Computing$$x1
000889193 980__ $$ajournal
000889193 980__ $$aVDB
000889193 980__ $$aI:(DE-Juel1)JSC-20090406
000889193 980__ $$aI:(DE-Juel1)NIC-20090406
000889193 980__ $$aAPC
000889193 980__ $$aUNRESTRICTED
000889193 9801_ $$aAPC
000889193 9801_ $$aFullTexts