001051601 001__ 1051601
001051601 005__ 20260120203621.0
001051601 0247_ $$2datacite_doi$$a10.34734/FZJ-2026-00524
001051601 037__ $$aFZJ-2026-00524
001051601 041__ $$aEnglish
001051601 1001_ $$0P:(DE-Juel1)208670$$aEffen, Moritz$$b0$$eCorresponding author
001051601 245__ $$aAn Investigation of a Multimodal Variational Autoencoder Framework for Physics Data$$f - 2025-09-29
001051601 260__ $$c2025
001051601 300__ $$a75p
001051601 3367_ $$2DataCite$$aOutput Types/Supervised Student Publication
001051601 3367_ $$02$$2EndNote$$aThesis
001051601 3367_ $$2BibTeX$$aMASTERSTHESIS
001051601 3367_ $$2DRIVER$$amasterThesis
001051601 3367_ $$0PUB:(DE-HGF)19$$2PUB:(DE-HGF)$$aMaster Thesis$$bmaster$$mmaster$$s1768898710_22093
001051601 3367_ $$2ORCID$$aSUPERVISED_STUDENT_PUBLICATION
001051601 502__ $$aMasterarbeit, RWTH Aachen, 2025$$bMasterarbeit$$cRWTH Aachen$$d2025$$o2025-09-29
001051601 520__ $$aMany scientific domains, such as physics, provide multimodal data when observing complex phenomena or when doing experiments. Understanding individual contributions of each modality can help to optimise experimental setups and sensors, thereby potentially increasing accuracy on domain-specific tasks that rely on such data. This thesis examines the role of multimodal data in (downstream) prediction tasks, with a focus on the unique and shared contributions of the respective modalities. Disentangled representation learning is a paradigm that aims to extract the independent, underlying factors from data. We employ this approach for multimodal data, proposing an extension to the disentangled multimodal variational autoencoder (DMVAE) by incorporating an additional optimisation objective to enforce minimal redundancy between shared and unique latent representations extracted by the DMVAE. Based on these representations, we train and evaluate several downstream tasks to study their contributions to the task. We compare this method to the traditional DMVAE and VAE across multimodal and single-modal configurations and also compare it directly to regression models. In our experiments, this approach is applied to the Multimodal Universe (MMU) astronomical dataset, which includes both imagery and spectral data. We also evaluate the impact of a physical-model-based differentiable image decoder model for extracting meaningful parameters into the latent space. Addi-tionally, the setup is applied to HyPlant hyperspectral remote sensing data, which consists of airborne measurements of Earth’s surface, to study it as a source of multimodal data to test how much information images and spectra contain about hyperspectral data.
001051601 536__ $$0G:(DE-HGF)POF4-5112$$a5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
001051601 8564_ $$uhttps://juser.fz-juelich.de/record/1051601/files/Master%20Thesis%20Moritz%20Effen.pdf$$yOpenAccess
001051601 909CO $$ooai:juser.fz-juelich.de:1051601$$popenaire$$popen_access$$pVDB$$pdriver$$pdnbdelivery
001051601 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)208670$$aForschungszentrum Jülich$$b0$$kFZJ
001051601 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5112$$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
001051601 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001051601 920__ $$lyes
001051601 9201_ $$0I:(DE-Juel1)IAS-8-20210421$$kIAS-8$$lDatenanalyse und Maschinenlernen$$x0
001051601 980__ $$amaster
001051601 980__ $$aVDB
001051601 980__ $$aUNRESTRICTED
001051601 980__ $$aI:(DE-Juel1)IAS-8-20210421
001051601 9801_ $$aFullTexts