000890961 001__ 890961
000890961 005__ 20230127125338.0
000890961 0247_ $$2doi$$a10.5194/egusphere-egu21-12146
000890961 0247_ $$2ISSN$$a0022-7722
000890961 0247_ $$2ISSN$$a1447-073X
000890961 0247_ $$2ISSN$$a1447-6959
000890961 0247_ $$2Handle$$a2128/29874
000890961 037__ $$aFZJ-2021-01277
000890961 082__ $$a610
000890961 1001_ $$0P:(DE-Juel1)176602$$aKleinert, Felix$$b0$$eCorresponding author
000890961 1112_ $$aEGU General Assembly 2021$$cVienna (online)$$d2021-04-19 - 2021-04-30$$gvEGU2021$$wAustria
000890961 245__ $$aRepresenting chemical history for ozone time-series predictions - a method development study for deep learning models
000890961 260__ $$c2021
000890961 3367_ $$0PUB:(DE-HGF)1$$2PUB:(DE-HGF)$$aAbstract$$babstract$$mabstract$$s1641379342_2751
000890961 3367_ $$033$$2EndNote$$aConference Paper
000890961 3367_ $$2BibTeX$$aINPROCEEDINGS
000890961 3367_ $$2DRIVER$$aconferenceObject
000890961 3367_ $$2DataCite$$aOutput Types/Conference Abstract
000890961 3367_ $$2ORCID$$aOTHER
000890961 520__ $$a<p>Machine learning techniques like deep learning gained enormous momentum in recent years. This was mainly caused by the success story of the main drivers like image and speech recognition, video prediction and autonomous driving, to name just a few.<br>Air pollutant forecasting models are an example, where earth system scientists start picking up deep learning models to enhance the forecast quality of time series. Almost all previous air pollution forecasts with machine learning rely solely on analysing temporal features in the observed time series of the target compound(s) and additional variables describing precursor concentrations and meteorological conditions. These studies, therefore, neglect the 'chemical history' of air masses, i.e. the fact that air pollutant concentrations at a given observation site are a result of emission and sink processes, mixing and chemical transformations along the transport pathways of air.<br>This study develops a concept of how such factors can be represented in the recently published deep learning model IntelliO3. The concept is demonstrated with numerical model data from the WRF-Chem model because the gridded model data provides an internally consistent dataset with complete spatial coverage and no missing values.<br>Furthermore, using model data allows for attributing changes of the forecasting performance to specific conceptual aspects. For example, we use the 8 wind sectors (N, NE, E, SE, etc.) and circles with predefined radii around our target locations to aggregate meteorological and chemical data from the intersections. Afterwards, we feed this aggregated data into a deep neural network while using the ozone concentration of the central point's next timesteps as targets. By analysing the change of forecast quality when moving from 4-dimensional (x, y, z, t) to 3-dimensional (x, y, t or r, &#966;, t) sectors and thinning out the underlying model data, we can deliver first estimates of expected performance gains or losses when applying our concept to station based surface observations in future studies.</p>
000890961 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
000890961 536__ $$0G:(EU-Grant)787576$$aIntelliAQ - Artificial Intelligence for Air Quality (787576)$$c787576$$fERC-2017-ADG$$x1
000890961 536__ $$0G:(DE-Juel-1)ESDE$$aEarth System Data Exploration (ESDE)$$cESDE$$x2
000890961 588__ $$aDataset connected to CrossRef
000890961 7001_ $$0P:(DE-Juel1)177004$$aLeufen, Lukas H.$$b1
000890961 7001_ $$0P:(DE-HGF)0$$aLupascu, Aurelia$$b2
000890961 7001_ $$00000-0002-2219-4657$$aButler, Tim$$b3
000890961 7001_ $$0P:(DE-Juel1)6952$$aSchultz, Martin G.$$b4
000890961 773__ $$a10.5194/egusphere-egu21-12146
000890961 8564_ $$uhttps://juser.fz-juelich.de/record/890961/files/Abstract.pdf$$yOpenAccess
000890961 909CO $$ooai:juser.fz-juelich.de:890961$$pec_fundedresources$$pdriver$$pVDB$$popen_access$$popenaire
000890961 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)176602$$aForschungszentrum Jülich$$b0$$kFZJ
000890961 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)177004$$aForschungszentrum Jülich$$b1$$kFZJ
000890961 9101_ $$0I:(DE-HGF)0$$6P:(DE-HGF)0$$a Institute for Advanced Sustainability Studies, Potsdam$$b2
000890961 9101_ $$0I:(DE-HGF)0$$60000-0002-2219-4657$$a Institute for Advanced Sustainability Studies, Potsdam$$b3
000890961 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)6952$$aForschungszentrum Jülich$$b4$$kFZJ
000890961 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$$x0
000890961 9141_ $$y2021
000890961 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS
000890961 915__ $$0StatID:(DE-HGF)1030$$2StatID$$aDBCoverage$$bCurrent Contents - Life Sciences
000890961 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000890961 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search
000890961 915__ $$0StatID:(DE-HGF)1040$$2StatID$$aDBCoverage$$bZoological Record
000890961 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bANAT SCI INT : 2015
000890961 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection
000890961 915__ $$0StatID:(DE-HGF)0111$$2StatID$$aWoS$$bScience Citation Index Expanded
000890961 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5
000890961 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000890961 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC
000890961 915__ $$0StatID:(DE-HGF)0310$$2StatID$$aDBCoverage$$bNCBI Molecular Biology Database
000890961 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews
000890961 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline
000890961 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bThomson Reuters Master Journal List
000890961 920__ $$lyes
000890961 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
000890961 980__ $$aabstract
000890961 980__ $$aVDB
000890961 980__ $$aUNRESTRICTED
000890961 980__ $$aI:(DE-Juel1)JSC-20090406
000890961 9801_ $$aFullTexts