% 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”.

@ARTICLE{Kelling:1053125,
      author       = {Kelling, Jeffrey and Bolea, Vicente and Bussmann, Michael
                      and Checkervarty, Ankush and Debus, Alexander and Ebert, Jan
                      and Eisenhauer, Greg and Gutta, Vineeth and Kesselheim,
                      Stefan and Klasky, Scott and Pandit, Vedhas and Pausch,
                      Richard and Podhorszki, Norbert and Poschel, Franz and
                      Rogers, David and Rustamov, Jeyhun and Schmerler, Steve and
                      Schramm, Ulrich and Steiniger, Klaus and Widera, Rene and
                      Willmann, Anna and Chandrasekaran, Sunita},
      title        = {{T}he {A}rtificial {S}cientist -- in-transit {M}achine
                      {L}earning of {P}lasma {S}imulations},
      publisher    = {arXiv},
      reportid     = {FZJ-2026-01458},
      year         = {2025},
      abstract     = {Increasing HPC cluster sizes and large-scale simulations
                      that produce petabytes of data per run, create massive IO
                      and storage challenges for analysis. Deep learning-based
                      techniques, in particular, make use of these amounts of
                      domain data to extract patterns that help build scientific
                      understanding. Here, we demonstrate a streaming workflow in
                      which simulation data is streamed directly to a
                      machine-learning (ML) framework, circumventing the file
                      system bottleneck. Data is transformed in transit,
                      asynchronously to the simulation and the training of the
                      model. With the presented workflow, data operations can be
                      performed in common and easy-to-use programming languages,
                      freeing the application user from adapting the application
                      output routines. As a proof-of-concept we consider a GPU
                      accelerated particle-in-cell (PIConGPU) simulation of the
                      Kelvin- Helmholtz instability (KHI). We employ experience
                      replay to avoid catastrophic forgetting in learning from
                      this non-steady process in a continual manner. We detail
                      challenges addressed while porting and scaling to Frontier
                      exascale system.},
      keywords     = {Computational Physics (physics.comp-ph) (Other) /
                      Distributed, Parallel, and Cluster Computing (cs.DC) (Other)
                      / Machine Learning (cs.LG) (Other) / FOS: Physical sciences
                      (Other) / FOS: Computer and information sciences (Other)},
      pnm          = {5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs)
                      and Research Groups (POF4-511) / Helmholtz AI Consultant
                      Team FB Information (E54.303.11)},
      pid          = {G:(DE-HGF)POF4-5112 / G:(DE-Juel-1)E54.303.11},
      typ          = {PUB:(DE-HGF)25},
      doi          = {10.48550/ARXIV.2501.03383},
      url          = {https://juser.fz-juelich.de/record/1053125},
}