000908363 001__ 908363
000908363 005__ 20230127125340.0
000908363 0247_ $$2Handle$$a2128/31419
000908363 037__ $$aFZJ-2022-02565
000908363 041__ $$aEnglish
000908363 1001_ $$0P:(DE-Juel1)177767$$aGong, Bing$$b0$$eCorresponding author$$ufzj
000908363 1112_ $$aPlatform for Advanced Scientific Computing Conference 2022$$cBasel$$d2022-06-27 - 2022-06-30$$gPASC2022$$wSwitzerland
000908363 245__ $$aStatistical Downscaling of Surface Temperature and Precipitation with Deep Neural Networks
000908363 260__ $$c2022
000908363 3367_ $$033$$2EndNote$$aConference Paper
000908363 3367_ $$2DataCite$$aOther
000908363 3367_ $$2BibTeX$$aINPROCEEDINGS
000908363 3367_ $$2DRIVER$$aconferenceObject
000908363 3367_ $$2ORCID$$aLECTURE_SPEECH
000908363 3367_ $$0PUB:(DE-HGF)6$$2PUB:(DE-HGF)$$aConference Presentation$$bconf$$mconf$$s1656674930_12168$$xOther
000908363 520__ $$aIn light of the success of superresolution (SR) applications in computer vision, recent studies have started to develop statistical downscaling methods for meteorological data based on deep neural networks (DNNs). DNNs are attractive, because they are computationally cheap, once they are trained.In this study, deep neural networks are developed to downscale hourly 2 meter temperature and precipitation over the complex terrain of Central Europe. Our approach is based on advanced generative adversarial networks (GANs) and transformer networks. The merit of this choice is that GANs encourage the generator to preserve the strong spatial variability from the data, while the transformer can capture the temporal dependencies. The experiments are designed to generate high-resolution temperature (0.1°) from low resolution (0.8°), and time-evolving high-resolution precipitation (1 km) from low resolution (4 km/8 km). The DNNs are fed with several relevant static and dynamic predictors and comprehensively evaluated by grid point-level errors, and error metrics for spatial variability and the generated probability distribution. Our results motivate the further development of DNNs that can be potentially leveraged to downscale other challenging Earth system data such as cloud cover or wind in operational workflows.
000908363 536__ $$0G:(DE-HGF)POF4-5111$$a5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
000908363 536__ $$0G:(EU-Grant)955513$$aMAELSTROM - MAchinE Learning for Scalable meTeoROlogy and cliMate (955513)$$c955513$$fH2020-JTI-EuroHPC-2019-1$$x1
000908363 536__ $$0G:(DE-Juel-1)ESDE$$aEarth System Data Exploration (ESDE)$$cESDE$$x2
000908363 536__ $$0G:(DE-Juel-1)ESDE$$aEarth System Data Exploration (ESDE)$$cESDE$$x3
000908363 7001_ $$0P:(DE-Juel1)180790$$aLangguth, Michael$$b1$$eCorresponding author$$ufzj
000908363 7001_ $$0P:(DE-Juel1)187069$$aJi, Yan$$b2$$ufzj
000908363 7001_ $$0P:(DE-Juel1)166264$$aMozaffari, Amirpasha$$b3$$ufzj
000908363 7001_ $$0P:(DE-Juel1)187076$$aMache, Karim$$b4$$ufzj
000908363 7001_ $$0P:(DE-Juel1)6952$$aSchultz, Martin$$b5$$ufzj
000908363 8564_ $$uhttps://pasc22.pasc-conference.org/program/schedule/presentation/?id=msa221&sess=sess127
000908363 8564_ $$uhttps://juser.fz-juelich.de/record/908363/files/2022-06-26_PASC_downscaling_Gong%2BLangguth.pptx$$yOpenAccess
000908363 909CO $$ooai:juser.fz-juelich.de:908363$$pec_fundedresources$$pdriver$$pVDB$$popen_access$$popenaire
000908363 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)177767$$aForschungszentrum Jülich$$b0$$kFZJ
000908363 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)180790$$aForschungszentrum Jülich$$b1$$kFZJ
000908363 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)187069$$aForschungszentrum Jülich$$b2$$kFZJ
000908363 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)166264$$aForschungszentrum Jülich$$b3$$kFZJ
000908363 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)187076$$aForschungszentrum Jülich$$b4$$kFZJ
000908363 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)6952$$aForschungszentrum Jülich$$b5$$kFZJ
000908363 9131_ $$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
000908363 9141_ $$y2022
000908363 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000908363 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
000908363 980__ $$aconf
000908363 980__ $$aVDB
000908363 980__ $$aUNRESTRICTED
000908363 980__ $$aI:(DE-Juel1)JSC-20090406
000908363 9801_ $$aFullTexts