001045001 001__ 1045001
001045001 005__ 20251104202045.0
001045001 0247_ $$2datacite_doi$$a10.34734/FZJ-2025-03483
001045001 037__ $$aFZJ-2025-03483
001045001 1001_ $$0P:(DE-Juel1)203330$$aSemcheddine, Asma$$b0$$eCorresponding author
001045001 1112_ $$aDynamics Days Europe 2025$$cThessaloniki$$d2025-06-23 - 2025-06-27$$gDDE2025$$wGreece
001045001 245__ $$aThe Effect of BERT Training on Atmospheric Data Interpolation
001045001 260__ $$c2025
001045001 3367_ $$033$$2EndNote$$aConference Paper
001045001 3367_ $$2BibTeX$$aINPROCEEDINGS
001045001 3367_ $$2DRIVER$$aconferenceObject
001045001 3367_ $$2ORCID$$aCONFERENCE_POSTER
001045001 3367_ $$2DataCite$$aOutput Types/Conference Poster
001045001 3367_ $$0PUB:(DE-HGF)24$$2PUB:(DE-HGF)$$aPoster$$bposter$$mposter$$s1762259233_12766$$xAfter Call
001045001 520__ $$aAtmospheric science has witnessed a breakthrough in recent years by harnessing deep learning models to understand and replicate  the complex relationships within and between different atmospheric variables. Atmorep [1], a foundational model of atmospheric dynamics, was developed as a task-agnostic model, trained on 40 years of hourly data in a BERT-style manner, with up to 90% of the data being masked, in order to provide a plethora of  downstream applications. To further assess the model's ability to learn a comprehensive abstract representation of atmospheric data, we tested several systematic token-masking strategies (geographical masking, temporal masking, a hybrid pattern combining both, and masking along model levels) and examined their effects on its data interpolation performance. Our preliminary results indicate that the coupled-fields transformer slightly outperforms the single-field transformer, reinforcing the correlation between different atmospheric fields. At a 75% compression ratio, AtmoRep achieves good reconstruction for the temperature field and all three wind components. Additionally, AtmoRep appears to benefit from the hybrid masking pattern, offering further insights into large-scale representation learning and enhancing our understanding of data-driven atmospheric modeling.
001045001 536__ $$0G:(DE-HGF)POF4-5111$$a5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
001045001 536__ $$0G:(DE-Juel-1)ESDE$$aEarth System Data Exploration (ESDE)$$cESDE$$x1
001045001 536__ $$0G:(BMFTR)-01LK2316A$$aBMFTR 01LK2316A - Warmworld Smarter (IconRep) (-01LK2316A)$$c-01LK2316A$$x2
001045001 7001_ $$0P:(DE-HGF)0$$aLuise, Ilaria$$b1
001045001 7001_ $$0P:(DE-HGF)0$$aLessig, Christian$$b2
001045001 7001_ $$0P:(DE-Juel1)6952$$aSchultz, Martin$$b3
001045001 7001_ $$0P:(DE-Juel1)180790$$aLangguth, Michael$$b4
001045001 7001_ $$0P:(DE-Juel1)207675$$aMelidonis, Savvas$$b5
001045001 8564_ $$uhttps://juser.fz-juelich.de/record/1045001/files/DDE2025_poster_asma-final3%20%281%29.pdf$$yOpenAccess
001045001 909CO $$ooai:juser.fz-juelich.de:1045001$$popenaire$$popen_access$$pVDB$$pdriver
001045001 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)203330$$aForschungszentrum Jülich$$b0$$kFZJ
001045001 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)6952$$aForschungszentrum Jülich$$b3$$kFZJ
001045001 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)180790$$aForschungszentrum Jülich$$b4$$kFZJ
001045001 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)207675$$aForschungszentrum Jülich$$b5$$kFZJ
001045001 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$$x0
001045001 9141_ $$y2025
001045001 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001045001 920__ $$lyes
001045001 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
001045001 9801_ $$aFullTexts
001045001 980__ $$aposter
001045001 980__ $$aVDB
001045001 980__ $$aUNRESTRICTED
001045001 980__ $$aI:(DE-Juel1)JSC-20090406