Login
- Title:
Benchmarking Autoregressive Conditional Diffusion Models for Turbulent Flow Simulation
- Document type:
- Forschungsdaten
- Publication date:
- 12.02.2024
- Responsible:
- Kohl, Georg
- Authors:
- Kohl, Georg; Chen, Li-Wei; Thuerey, Nils
- Author affiliation:
- TUM
- Publisher:
- TUM
- Identifier:
- doi:10.14459/2024mp1734798.001
- Concept DOI:
- doi:10.14459/2024mp1734798
- End date of data production:
- 01.02.2024
- Subject area:
- DAT Datenverarbeitung, Informatik; PHY Physik
- Resource type:
- Simulationen / simulations
- Data type:
- mehrdimensionale Visualisierungen oder Modelle / models; Datenbanken / data bases
- Other data type:
- Compressed numpy arrays of dense spatial fields (like velocity, density, or pressure) and pretrained neural network model weights that can be loaded with pytorch
- Description:
- This archive contains spatio-temporal data from simulations of the Navier-Stokes equations: First, simulations of an incompressible wake flow at different Reynolds numbers simulated with PhiFlow. Second, a transonic cylinder flow simulated with SU2 at different Mach numbers. Finally, a curation of data from the Johns Hopkins Turbulence Database (JHTDB) is included, that features an isotropic turbulence flow simulated with a direct numerical simulation.
The isotropic turbulence data is made available under the Open Data Commons Attribution License (ODC-By) ( http://opendatacommons.org/licenses/by/). This means the data is open to use, but requires attribution to the original creators from the JHTDB (see https://turbulence.pha.jhu.edu/citing.aspx).
Furthermore, pretrained neural network model weights for flow prediction on each data set are provided, that can be used as described in more detail in our source code. - Links:
Project: https://ge.in.tum.de/publications/2023-acdm-kohl
Publication: https://arxiv.org/abs/2309.01745
Source Code: https://github.com/tum-pbs/autoreg-pde-diffusion- Key words:
- flow prediction; turbulent flow; PDEs; numerical simulation; diffusion models; autoregressive models
- Technical remarks:
- View and download (219 GB total, 8 Files)
The data server also offers downloads with FTP
The data server also offers downloads with rsync (password m1734798.001):
rsync rsync://m1734798.001@dataserv.ub.tum.de/m1734798.001/ - Language:
- en
- Other rights:
- Isotropic turbulence data set (128_iso.zip): Open Data Commons Attribution License (ODC-By) http://opendatacommons.org/licenses/by/
Remaining data sets and models (all other archives): Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/ - Horizon 2020:
- ERC Consolidator Grant SpaTe (CoG-2019-863850)
BibTeX