In Situ Framework for Coupling Simulation and Machine Learning with Application to CFD

doi:doi:10.57702/h0jq94vp

In Situ Framework for Coupling Simulation and Machine Learning with Application to CFD

Recent years have seen many successful applications of machine learning (ML) to facilitate fluid dynamic computations. As simulations grow, generating new training datasets for traditional offline learning creates I/O and storage bottlenecks. Additionally, performing inference at runtime requires non-trivial coupling of ML framework libraries with simulation codes.

BibTex:

@dataset{Riccardo_Balin_and_Andrew_Shao_and_Stephen_Becker_and_Filippo_Simini_and_Alessandro_Rigazzi_and_Alireza_Doostan_and_Kenneth_E_Jansen_and_Cooper_Simpson_and_Matthew_Ellis_and_John_A_Evans_2024,
    abstract = {Recent years have seen many successful applications of machine learning (ML) to facilitate fluid dynamic computations. As simulations grow, generating new training datasets for traditional offline learning creates I/O and storage bottlenecks. Additionally, performing inference at runtime requires non-trivial coupling of ML framework libraries with simulation codes.},
    author = {Riccardo Balin and Andrew Shao and Stephen Becker and Filippo Simini and Alessandro Rigazzi and Alireza Doostan and Kenneth E. Jansen and Cooper Simpson and Matthew Ellis and John A. Evans},
    doi = {10.57702/h0jq94vp},
    institution = {No Organization},
    keyword = {'CFD', 'HPC', 'In situ training', 'Inference', 'ML'},
    month = {dec},
    publisher = {TIB},
    title = {In Situ Framework for Coupling Simulation and Machine Learning with Application to CFD},
    url = {https://service.tib.eu/ldmservice/dataset/in-situ-framework-for-coupling-simulation-and-machine-learning-with-application-to-cfd},
    year = {2024}
}