001041713 001__ 1041713
001041713 005__ 20250509202317.0
001041713 0247_ $$2datacite_doi$$a10.34734/FZJ-2025-02398
001041713 037__ $$aFZJ-2025-02398
001041713 041__ $$aEnglish
001041713 1001_ $$0P:(DE-Juel1)186635$$aPatnala, Ankit$$b0$$eCorresponding author
001041713 1112_ $$aThe 12th John von Neumann Institute for Computing (NIC) Symposium$$cJülich$$d2025-03-06 - 2025-03-07$$wGermany
001041713 245__ $$aApplying AtmoRep for Diverse Weather Applications
001041713 260__ $$c2025
001041713 29510 $$aNIC Symposium 2025 Proceedings
001041713 300__ $$a301-  311
001041713 3367_ $$2ORCID$$aCONFERENCE_PAPER
001041713 3367_ $$033$$2EndNote$$aConference Paper
001041713 3367_ $$2BibTeX$$aINPROCEEDINGS
001041713 3367_ $$2DRIVER$$aconferenceObject
001041713 3367_ $$2DataCite$$aOutput Types/Conference Paper
001041713 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1746791755_2942
001041713 3367_ $$0PUB:(DE-HGF)7$$2PUB:(DE-HGF)$$aContribution to a book$$mcontb
001041713 500__ $$aProceedings: https://doi.org/10.34734/FZJ-2025-01965  ISBN: 978-3-95806-793-6
001041713 520__ $$aMachine learning has recently seen a rapid wide-spread adoption across various fields of science including atmospheric and weather research. The emergence of foundation models has marked a transformation in the science of machine learning. These foundation models are general-purpose models trained on huge amounts of data using self-supervised methods, eliminating the need for labeled data. Once trained, the parameters of these models can be utilized as a starting point for a range of domain-specific tasks. This approach is advantageous in terms of both cost and performance, as it minimizes the reliance on annotated data compared to models trained from scratch. Motivated by this, our study explores the foundational capabilities of AtmoRep, a stochastic atmospheric foundation model, for two distinct weather-related applications, data compression and statistical downscaling. The training of the 3.5 billion parameter AtmoRep model consumed about a few weeks of compute time on 32 JUWELS Booster nodes.
001041713 536__ $$0G:(DE-HGF)POF4-5111$$a5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
001041713 536__ $$0G:(DE-Juel-1)ESDE$$aEarth System Data Exploration (ESDE)$$cESDE$$x1
001041713 7001_ $$0P:(DE-Juel1)203330$$aSemcheddine, Asma$$b1
001041713 7001_ $$0P:(DE-Juel1)180790$$aLangguth, Michael$$b2
001041713 7001_ $$0P:(DE-Juel1)6952$$aSchultz, Martin$$b3
001041713 7001_ $$0P:(DE-HGF)0$$aLessig, Christian$$b4
001041713 7001_ $$0P:(DE-HGF)0$$aLuise, Ilaria$$b5
001041713 770__ $$z978-3-95806-793-6
001041713 773__ $$v52
001041713 8564_ $$uhttps://juser.fz-juelich.de/record/1041713/files/poster.png$$yRestricted
001041713 8564_ $$uhttps://juser.fz-juelich.de/record/1041713/files/pre-print%20of%20the%20paper.pdf$$yOpenAccess
001041713 8564_ $$uhttps://juser.fz-juelich.de/record/1041713/files/poster.gif?subformat=icon$$xicon$$yRestricted
001041713 8564_ $$uhttps://juser.fz-juelich.de/record/1041713/files/poster.jpg?subformat=icon-1440$$xicon-1440$$yRestricted
001041713 8564_ $$uhttps://juser.fz-juelich.de/record/1041713/files/poster.jpg?subformat=icon-180$$xicon-180$$yRestricted
001041713 8564_ $$uhttps://juser.fz-juelich.de/record/1041713/files/poster.jpg?subformat=icon-640$$xicon-640$$yRestricted
001041713 909CO $$ooai:juser.fz-juelich.de:1041713$$popenaire$$popen_access$$pVDB$$pdriver$$pdnbdelivery
001041713 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)186635$$aForschungszentrum Jülich$$b0$$kFZJ
001041713 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)203330$$aForschungszentrum Jülich$$b1$$kFZJ
001041713 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)180790$$aForschungszentrum Jülich$$b2$$kFZJ
001041713 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)6952$$aForschungszentrum Jülich$$b3$$kFZJ
001041713 9131_ $$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
001041713 9141_ $$y2025
001041713 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001041713 920__ $$lyes
001041713 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
001041713 980__ $$acontrib
001041713 980__ $$aVDB
001041713 980__ $$acontb
001041713 980__ $$aI:(DE-Juel1)JSC-20090406
001041713 980__ $$aUNRESTRICTED
001041713 9801_ $$aFullTexts