001007047 001__ 1007047
001007047 005__ 20231208201858.0
001007047 0247_ $$2doi$$a10.1175/AIES-D-22-0085.1
001007047 0247_ $$2datacite_doi$$a10.34734/FZJ-2023-01952
001007047 037__ $$aFZJ-2023-01952
001007047 1001_ $$0P:(DE-Juel1)177004$$aLeufen, Lukas Hubert$$b0$$eCorresponding author$$ufzj
001007047 245__ $$aO3ResNet: A Deep Learning–Based Forecast System to Predict Local Ground-Level Daily Maximum 8-Hour Average Ozone in Rural and Suburban Environments
001007047 260__ $$aBoston$$b[Verlag nicht ermittelbar]$$c2023
001007047 3367_ $$2DRIVER$$aarticle
001007047 3367_ $$2DataCite$$aOutput Types/Journal article
001007047 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1702014408_21791
001007047 3367_ $$2BibTeX$$aARTICLE
001007047 3367_ $$2ORCID$$aJOURNAL_ARTICLE
001007047 3367_ $$00$$2EndNote$$aJournal Article
001007047 520__ $$aWith the impact of tropospheric ozone pollution on humankind, there is a compelling need for robust air quality forecasts. Here, we introduce a novel deep learning (DL) forecasting system called O3ResNet that produces a four-day forecast for ground-level ozone. O3ResNet is based on a convolutional neural network with residual blocks. The model has been trained on 22 years of ozone and nitrogen oxides in-situ measurements and ERA5 reanalysis data from 2000 to 2021 at 328 stations in Central Europe located in rural and suburban environment. Our model outperforms the state-of-the-art Copernicus Atmosphere Monitoring Service regional forecast model ensemble for ground-level ozone with respect to the mean square error and mean absolute error of the daily maximum 8-hour running average ozone, thus marking a major milestone for DL-based ozone prediction. O3ResNet has a very small bias without requiring additional post-processing, and it generalizes well so that new stations can be added with no need to re-train the neural network. As the model works on hourly data, it can be easily adapted to output other air quality metrics. We conclude that O3ResNet is sufficiently advanced and robust to become a test application for operational air quality forecasting with DL.
001007047 536__ $$0G:(DE-HGF)POF4-5111$$a5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
001007047 536__ $$0G:(EU-Grant)787576$$aIntelliAQ - Artificial Intelligence for Air Quality (787576)$$c787576$$fERC-2017-ADG$$x1
001007047 536__ $$0G:(DE-Juel-1)ESDE$$aEarth System Data Exploration (ESDE)$$cESDE$$x2
001007047 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
001007047 7001_ $$0P:(DE-Juel1)176602$$aKleinert, Felix$$b1$$ufzj
001007047 7001_ $$0P:(DE-Juel1)6952$$aSchultz, Martin G.$$b2$$ufzj
001007047 773__ $$0PERI:(DE-600)3172988-5$$a10.1175/AIES-D-22-0085.1$$gp. 1 - 42$$n3$$p1 - 16$$tArtificial Intelligence for the Earth Systems$$v2$$x2769-7525$$y2023
001007047 8564_ $$uhttps://juser.fz-juelich.de/record/1007047/files/Invoice_INV002339.pdf
001007047 8564_ $$uhttps://juser.fz-juelich.de/record/1007047/files/aies-AIES-D-22-0085.1.pdf$$yOpenAccess
001007047 8564_ $$uhttps://juser.fz-juelich.de/record/1007047/files/aies-AIES-D-22-0085.gif?subformat=icon$$xicon$$yOpenAccess
001007047 8564_ $$uhttps://juser.fz-juelich.de/record/1007047/files/aies-AIES-D-22-0085.jpg?subformat=icon-1440$$xicon-1440$$yOpenAccess
001007047 8564_ $$uhttps://juser.fz-juelich.de/record/1007047/files/aies-AIES-D-22-0085.jpg?subformat=icon-180$$xicon-180$$yOpenAccess
001007047 8564_ $$uhttps://juser.fz-juelich.de/record/1007047/files/aies-AIES-D-22-0085.jpg?subformat=icon-640$$xicon-640$$yOpenAccess
001007047 8767_ $$8INV002339$$92023-04-19$$a1200193107$$d2023-05-17$$eAPC$$jZahlung erfolgt$$zUSD 2200,-
001007047 909CO $$ooai:juser.fz-juelich.de:1007047$$pdnbdelivery$$popenaire$$popenCost$$pec_fundedresources$$pVDB$$pdriver$$pOpenAPC$$popen_access
001007047 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)177004$$aForschungszentrum Jülich$$b0$$kFZJ
001007047 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)176602$$aForschungszentrum Jülich$$b1$$kFZJ
001007047 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)6952$$aForschungszentrum Jülich$$b2$$kFZJ
001007047 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$$x0
001007047 9141_ $$y2023
001007047 915pc $$0PC:(DE-HGF)0000$$2APC$$aAPC keys set
001007047 915pc $$0PC:(DE-HGF)0001$$2APC$$aLocal Funding
001007047 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001007047 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
001007047 980__ $$ajournal
001007047 980__ $$aVDB
001007047 980__ $$aUNRESTRICTED
001007047 980__ $$aI:(DE-Juel1)JSC-20090406
001007047 980__ $$aAPC
001007047 9801_ $$aAPC
001007047 9801_ $$aFullTexts