An adaptive model hierarchy for data-augmented training of kernel models for reactive flow
Haasdonk B, Ohlberger M, Schindler F
Research article in edited proceedings (conference) | Peer reviewedAbstract
We consider machine-learning of time-dependent quantities of interest derived from solution trajectories of parabolic partial differential equations. For large-scale or long-time integration scenarios, where using a full order model (FOM) to generate sufficient training data is computationally prohibitive, we propose an adaptive hierarchy of intermediate Reduced Basis reduced order models (ROM) to augment the FOM training data by certified ROM training data required to fit a kernel model.
Details about the publication
Editors: Breitenecker, Felix; Kemmetmüller, Wolfgang; Körner, Andreas; Kugi, Andreas; Troch, Inge
Book title: MATHMOD 2022 Discussion Contribution Volume (Volume ARGESIM Report)
Page range: 67-68
Publisher: ARGESIM Verlag
Place of publication: Vienna
Edition: 17
Status: Published
Release year: 2022
Language in which the publication is written: English
Conference: 10th Vienna Conference on Mathematical Modelling, Vienna, Austria
ISBN: 978-3-901608-95-7
Link to the full text: https://arxiv.org/abs/2110.12388
Keywords: Model Order Reduction; Machine Learning; Parabolic PDEs
Authors from the University of Münster
| Ohlberger, Mario | Professorship of Applied Mathematics, especially Numerics (Prof. Ohlberger) |
| Schindler, Felix Tobias | Professorship of Applied Mathematics, especially Numerics (Prof. Ohlberger) |
Projects the publication originates from
Duration: 01/04/2020 - 31/12/2023 Funded by: Federal Ministry of Research, Technology and Space Type of project: Participation in federally funded joint project | |
Duration: 01/01/2019 - 31/12/2025 | 1st Funding period Funded by: DFG - Cluster of Excellence Type of project: Subproject in DFG-joint project hosted at University of Münster |