000872741 001__ 872741
000872741 005__ 20230127125337.0
000872741 0247_ $$2Handle$$a2128/23877
000872741 037__ $$aFZJ-2020-00219
000872741 1001_ $$0P:(DE-Juel1)176602$$aKleinert, Felix$$b0$$eCorresponding author
000872741 1112_ $$aEGU General Assembly 2019$$cWien$$d2019-04-07 - 2019-04-12$$gEGU2019$$wAustria
000872741 245__ $$aNear Surface Ozone Predictions Based on Multiple Artificial Neural Network Architectures
000872741 260__ $$c2019
000872741 3367_ $$0PUB:(DE-HGF)1$$2PUB:(DE-HGF)$$aAbstract$$babstract$$mabstract$$s1579155711_7154
000872741 3367_ $$033$$2EndNote$$aConference Paper
000872741 3367_ $$2BibTeX$$aINPROCEEDINGS
000872741 3367_ $$2DRIVER$$aconferenceObject
000872741 3367_ $$2DataCite$$aOutput Types/Conference Abstract
000872741 3367_ $$2ORCID$$aOTHER
000872741 520__ $$aArtificial neural networks (ANNs) are well suited to solve complex and highly non-linear problems. Various ma-chine learning architectures like convolutional neural networks (CNNs) and Long Short-Term Memory networks (LSTMs), both subclasses of ANNs, are applied to the prediction of near surface ozone concentrations (dma8eu) for a lead time of up to four days at 51 measurement sites in southern Germany. Only stations with at least 3500 days of valid data between 1997 and 2015 were used, while the first 80% of the data were used for training and the remaining 20% for testing and validation. Forecasts were evaluated with respect to other continuous predictions from climatological, persistence and ordinary least square (ols) models. Furthermore, the quality of threshold exceedance predictions for varying thresholds was analysed based on the joint distribution of forecasts and ob-ervations. Finally, it was examined which input variables are most important to generate skilful predictions. The results of all three analyses will be presented for all network architectures. For example, experiments with a CNN architecture show that those networks outperform ols and persistence pre-dictions on all four days. The climatological predictions, however, are outperformed at the first two days, only. On day three and four the CNN’s skill score with respect to multivalued climatological forecasts decreased with time,indicating no added value on those days as the scores no longer differ substantially. The CNNs performed best for continuous ozone predictions between the 20% and the 80% percentile, but cannot generate skilful predictions for higher or lower concentrations due to imbalanced training data. The quality of forecasts was determined primarily by the previous day’s ozone concentration. Of all other input variables, which were selected based on their importance for ozone formation and air mass transport, only temperature and the wind’s v-component had a small impact on forecast quality.
000872741 536__ $$0G:(DE-HGF)POF3-512$$a512 - Data-Intensive Science and Federated Computing (POF3-512)$$cPOF3-512$$fPOF III$$x0
000872741 536__ $$0G:(DE-Juel1)PHD-NO-GRANT-20170405$$aPhD no Grant - Doktorand ohne besondere Förderung (PHD-NO-GRANT-20170405)$$cPHD-NO-GRANT-20170405$$x1
000872741 536__ $$0G:(DE-Juel-1)ESDE$$aEarth System Data Exploration (ESDE)$$cESDE$$x2
000872741 7001_ $$0P:(DE-Juel1)177767$$aGong, Bing$$b1
000872741 7001_ $$0P:(DE-Juel1)162390$$aGötz, Markus$$b2
000872741 7001_ $$0P:(DE-Juel1)6952$$aSchultz, Martin$$b3
000872741 8564_ $$uhttps://juser.fz-juelich.de/record/872741/files/Abstract.pdf$$yOpenAccess
000872741 8564_ $$uhttps://juser.fz-juelich.de/record/872741/files/Abstract.pdf?subformat=pdfa$$xpdfa$$yOpenAccess
000872741 909CO $$ooai:juser.fz-juelich.de:872741$$pdriver$$pVDB$$popen_access$$popenaire
000872741 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)176602$$aForschungszentrum Jülich$$b0$$kFZJ
000872741 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)177767$$aForschungszentrum Jülich$$b1$$kFZJ
000872741 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)6952$$aForschungszentrum Jülich$$b3$$kFZJ
000872741 9131_ $$0G:(DE-HGF)POF3-512$$1G:(DE-HGF)POF3-510$$2G:(DE-HGF)POF3-500$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bKey Technologies$$lSupercomputing & Big Data$$vData-Intensive Science and Federated Computing$$x0
000872741 9141_ $$y2019
000872741 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000872741 920__ $$lyes
000872741 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
000872741 9801_ $$aFullTexts
000872741 980__ $$aabstract
000872741 980__ $$aVDB
000872741 980__ $$aUNRESTRICTED
000872741 980__ $$aI:(DE-Juel1)JSC-20090406