000908083 001__ 908083
000908083 005__ 20220628190225.0
000908083 0247_ $$2Handle$$a2128/31393
000908083 037__ $$aFZJ-2022-02362
000908083 041__ $$aEnglish
000908083 1001_ $$0P:(DE-Juel1)180790$$aLangguth, Michael$$b0$$eCorresponding author$$ufzj
000908083 1112_ $$aLiving Planet Symposium 2022$$cBonn$$d2022-05-23 - 2022-05-27$$gLPS2022$$wGermany
000908083 245__ $$aStochastic downscaling of meteorological fields with deep neural networks
000908083 260__ $$c2022
000908083 3367_ $$033$$2EndNote$$aConference Paper
000908083 3367_ $$2BibTeX$$aINPROCEEDINGS
000908083 3367_ $$2DRIVER$$aconferenceObject
000908083 3367_ $$2ORCID$$aCONFERENCE_POSTER
000908083 3367_ $$2DataCite$$aOutput Types/Conference Poster
000908083 3367_ $$0PUB:(DE-HGF)24$$2PUB:(DE-HGF)$$aPoster$$bposter$$mposter$$s1656419890_30066$$xOther
000908083 520__ $$aWeather forecasts at high spatio-temporal resolution are of great relevance for industry and society. However, contemporary global NWP models deploy grids with a spacing of about 10 km which is too coarse to capture relevant variability in the presence of complex topography. To overcome the limitations of coarse-grained model output, statistical downscaling with deep neural networks is attaining increasing attention.<br>In this study, a powerful generative adversarial network (GAN) for downscaling the 2m temperature is presented. The generator of the GAN model is built upon a U-net architecture and furthermore equipped with a recurrent layer to obtain a temporarily coherent downscaling product. As an exemplary case study, coarsened 2m temperature fields from the ERA5 reanalysis dataset are downscaled to the same horizontal resolution (0.1°) as the Integrated Forecasting System (IFS) model which runs operationally at the European Centre for Medium-Range Weather Forecasts (ECMWF). We choose Central Europe including the Alps as a proper target region for our downscaling experiment.Our GAN model is evaluated in terms of several evaluation metrics which measure the error on grid point-level as well as the goodness of the downscaled product in terms of the spatial variability and the produced probability distribution function. Furthermore, we demonstrate how different input quantities help the model to create an improved downscaling product. These quantities comprise dynamic variables such as wind and temperature on different pressure levels, but also static fields such as the surface elevation and the land-sea mask. Incorporating the selected input variables ensures that our neural network for downscaling is capable of capturing challenging situations with the presence of temperature inversions over complex terrain.<br>The results motivate further development of the deep neural network including a further increase in the spatial resolution of the target product as well as applications to other meteorological variables such as wind or precipitation.
000908083 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
000908083 536__ $$0G:(EU-Grant)955513$$aMAELSTROM - MAchinE Learning for Scalable meTeoROlogy and cliMate (955513)$$c955513$$fH2020-JTI-EuroHPC-2019-1$$x1
000908083 536__ $$0G:(DE-Juel-1)ESDE$$aEarth System Data Exploration (ESDE)$$cESDE$$x2
000908083 65027 $$0V:(DE-MLZ)SciArea-140$$2V:(DE-HGF)$$aGeosciences$$x0
000908083 7001_ $$0P:(DE-Juel1)177767$$aGong, Bing$$b1$$ufzj
000908083 7001_ $$0P:(DE-Juel1)187069$$aJi, Yan$$b2$$ufzj
000908083 7001_ $$0P:(DE-Juel1)166264$$aMozaffari, Amirpasha$$b3$$ufzj
000908083 7001_ $$0P:(DE-Juel1)6952$$aSchultz, Martin$$b4$$ufzj
000908083 8564_ $$uhttps://juser.fz-juelich.de/record/908083/files/LSP20220526-downscaling_maelstrom_Langguth.pdf$$yOpenAccess
000908083 909CO $$ooai:juser.fz-juelich.de:908083$$popenaire$$popen_access$$pVDB$$pdriver$$pec_fundedresources
000908083 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)180790$$aForschungszentrum Jülich$$b0$$kFZJ
000908083 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)177767$$aForschungszentrum Jülich$$b1$$kFZJ
000908083 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)187069$$aForschungszentrum Jülich$$b2$$kFZJ
000908083 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)166264$$aForschungszentrum Jülich$$b3$$kFZJ
000908083 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)6952$$aForschungszentrum Jülich$$b4$$kFZJ
000908083 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$$x0
000908083 9141_ $$y2022
000908083 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000908083 920__ $$lyes
000908083 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
000908083 980__ $$aposter
000908083 980__ $$aVDB
000908083 980__ $$aUNRESTRICTED
000908083 980__ $$aI:(DE-Juel1)JSC-20090406
000908083 9801_ $$aFullTexts