000890172 001__ 890172
000890172 005__ 20230127125338.0
000890172 037__ $$aFZJ-2021-00761
000890172 041__ $$aEnglish
000890172 1001_ $$0P:(DE-Juel1)177767$$aGong, Bing$$b0$$eCorresponding author$$ufzj
000890172 1112_ $$aEuropean Geosciences Union 2020$$cVirtual$$d2020-05-04 - 2020-05-08$$gEGU2020$$wAustria
000890172 245__ $$aDeep learning for short-term temperature forecasts with video prediction methods
000890172 260__ $$c2020
000890172 3367_ $$0PUB:(DE-HGF)1$$2PUB:(DE-HGF)$$aAbstract$$babstract$$mabstract$$s1611580296_25895
000890172 3367_ $$033$$2EndNote$$aConference Paper
000890172 3367_ $$2BibTeX$$aINPROCEEDINGS
000890172 3367_ $$2DRIVER$$aconferenceObject
000890172 3367_ $$2DataCite$$aOutput Types/Conference Abstract
000890172 3367_ $$2ORCID$$aOTHER
000890172 520__ $$aThis study explores the adaptation of state-of-the-art deep learning architectures for video frame prediction in the context of weather and climate applications. A proof-of-concept case study was performed to predict surface temperature fields over Europe for up to 20 hours based on ERA5 reanalyses weather data. Initial results have been achieved with a PredNet and a GAN-based architecture by using various combinations of temperature, surface pressure, and 500 hPa geopotential as inputs. The results show that the GAN-based architecture outperforms the PredNet. To facilitate the massive data processing and testing of various deep learning architectures, we have developed a containerized parallel workflow for the full life-cycle of the application, which consists of data extraction, data pre-processing, training, post-processing and visualisation of results. The training for PredNet was parallelized on JUWELS supercomputer at JSC, and the training scalability performance was also evaluated.
000890172 536__ $$0G:(DE-HGF)POF3-512$$a512 - Data-Intensive Science and Federated Computing (POF3-512)$$cPOF3-512$$fPOF III$$x0
000890172 536__ $$0G:(EU-Grant)787576$$aIntelliAQ - Artificial Intelligence for Air Quality (787576)$$c787576$$fERC-2017-ADG$$x1
000890172 536__ $$0G:(DE-Juel-1)ESDE$$aEarth System Data Exploration (ESDE)$$cESDE$$x2
000890172 7001_ $$0P:(DE-Juel1)180752$$aStadtler, Scarlet$$b1$$ufzj
000890172 7001_ $$0P:(DE-Juel1)180790$$aLangguth, Michael$$b2$$ufzj
000890172 7001_ $$0P:(DE-Juel1)166264$$aMozaffari, Amirpasha$$b3$$ufzj
000890172 7001_ $$0P:(DE-Juel1)173676$$aVogelsang, Jan$$b4$$ufzj
000890172 7001_ $$0P:(DE-Juel1)6952$$aSchultz, Martin$$b5$$ufzj
000890172 909CO $$ooai:juser.fz-juelich.de:890172$$pec_fundedresources$$pVDB$$popenaire
000890172 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)177767$$aForschungszentrum Jülich$$b0$$kFZJ
000890172 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)180752$$aForschungszentrum Jülich$$b1$$kFZJ
000890172 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)180790$$aForschungszentrum Jülich$$b2$$kFZJ
000890172 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)166264$$aForschungszentrum Jülich$$b3$$kFZJ
000890172 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)173676$$aForschungszentrum Jülich$$b4$$kFZJ
000890172 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)6952$$aForschungszentrum Jülich$$b5$$kFZJ
000890172 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
000890172 9141_ $$y2020
000890172 920__ $$lyes
000890172 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
000890172 980__ $$aabstract
000890172 980__ $$aVDB
000890172 980__ $$aI:(DE-Juel1)JSC-20090406
000890172 980__ $$aUNRESTRICTED