000908456 001__ 908456
000908456 005__ 20240624104534.0
000908456 0247_ $$2doi$$a10.1017/eds.2022.9
000908456 0247_ $$2Handle$$a2128/31431
000908456 0247_ $$2altmetric$$aaltmetric:130514046
000908456 0247_ $$2WOS$$aWOS:001223640200010
000908456 037__ $$aFZJ-2022-02615
000908456 041__ $$aEnglish
000908456 082__ $$a333.7
000908456 1001_ $$0P:(DE-Juel1)177004$$aLeufen, Lukas Hubert$$b0$$eCorresponding author
000908456 245__ $$aExploring decomposition of temporal patterns to facilitate learning of neural networks for ground-level daily maximum 8-hour average ozone prediction
000908456 260__ $$aCambridge$$bCambridge University Press$$c2022
000908456 3367_ $$2DRIVER$$aarticle
000908456 3367_ $$2DataCite$$aOutput Types/Journal article
000908456 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1657094102_11695
000908456 3367_ $$2BibTeX$$aARTICLE
000908456 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000908456 3367_ $$00$$2EndNote$$aJournal Article
000908456 520__ $$aExposure to ground-level ozone is a concern for both humans and vegetation, so accurate prediction of ozone time series is of great importance. However, conventional as well as emerging methods have deficiencies in predicting time series when a superposition of differently pronounced oscillations on various time scales is present. In this paper, we propose a meteorologically motivated filtering method of time series data, which can separate oscillation patterns, in combination with different multibranch neural networks. To avoid phase shifts introduced by using a causal filter, we combine past observation data with a climatological estimate about the future to be able to apply a noncausal filter in a forecast setting. In addition, the forecast in the form of the expected climatology provides some a priori information that can support the neural network to focus not merely on learning a climatological statistic. We apply this method to hourly data obtained from over 50 different monitoring stations in northern Germany situated in rural or suburban surroundings to generate a prediction for the daily maximum 8-hr average values of ground-level ozone 4 days into the future. The data preprocessing with time filters enables simpler neural networks such as fully connected networks as well as more sophisticated approaches such as convolutional and recurrent neural networks to better recognize long-term and short-term oscillation patterns like the seasonal cycle and thus leads to an improvement in the forecast skill, especially for a lead time of more than 48 hr, compared to persistence, climatological reference, and other reference models.
000908456 536__ $$0G:(DE-HGF)POF4-5111$$a5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
000908456 536__ $$0G:(EU-Grant)787576$$aIntelliAQ - Artificial Intelligence for Air Quality (787576)$$c787576$$fERC-2017-ADG$$x1
000908456 536__ $$0G:(DE-Juel1)PHD-NO-GRANT-20170405$$aPhD no Grant - Doktorand ohne besondere Förderung (PHD-NO-GRANT-20170405)$$cPHD-NO-GRANT-20170405$$x2
000908456 536__ $$0G:(DE-Juel-1)ESDE$$aEarth System Data Exploration (ESDE)$$cESDE$$x3
000908456 588__ $$aDataset connected to DataCite
000908456 7001_ $$0P:(DE-Juel1)176602$$aKleinert, Felix$$b1
000908456 7001_ $$0P:(DE-Juel1)6952$$aSchultz, Martin G.$$b2
000908456 773__ $$0PERI:(DE-600)3116427-4$$a10.1017/eds.2022.9$$gVol. 1, p. e10$$pe10$$tEnvironmental data science$$v1$$x2634-4602$$y2022
000908456 8564_ $$uhttps://juser.fz-juelich.de/record/908456/files/exploring-decomposition-of-temporal-patterns-to-facilitate-learning-of-neural-networks-for-ground-level-daily-maximum-8-hour-average-ozone-prediction.pdf$$yOpenAccess
000908456 909CO $$ooai:juser.fz-juelich.de:908456$$pdnbdelivery$$pec_fundedresources$$pVDB$$pdriver$$popen_access$$popenaire
000908456 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)177004$$aForschungszentrum Jülich$$b0$$kFZJ
000908456 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)176602$$aForschungszentrum Jülich$$b1$$kFZJ
000908456 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)6952$$aForschungszentrum Jülich$$b2$$kFZJ
000908456 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$$x0
000908456 9141_ $$y2022
000908456 915__ $$0StatID:(DE-HGF)0430$$2StatID$$aNational-Konsortium
000908456 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000908456 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000908456 920__ $$lyes
000908456 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
000908456 980__ $$ajournal
000908456 980__ $$aVDB
000908456 980__ $$aUNRESTRICTED
000908456 980__ $$aI:(DE-Juel1)JSC-20090406
000908456 9801_ $$aFullTexts