% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@MASTERSTHESIS{Effen:1051601,
      author       = {Effen, Moritz},
      title        = {{A}n {I}nvestigation of a {M}ultimodal {V}ariational
                      {A}utoencoder {F}ramework for {P}hysics {D}ata},
      school       = {RWTH Aachen},
      type         = {Masterarbeit},
      reportid     = {FZJ-2026-00524},
      pages        = {75p},
      year         = {2025},
      note         = {Masterarbeit, RWTH Aachen, 2025},
      abstract     = {Many 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.},
      cin          = {IAS-8},
      cid          = {I:(DE-Juel1)IAS-8-20210421},
      pnm          = {5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs)
                      and Research Groups (POF4-511)},
      pid          = {G:(DE-HGF)POF4-5112},
      typ          = {PUB:(DE-HGF)19},
      doi          = {10.34734/FZJ-2026-00524},
      url          = {https://juser.fz-juelich.de/record/1051601},
}