Persistent Identifier
|
doi:10.18419/darus-2987 |
Publication Date
|
2022-06-21 |
Title
| PDEBench Pretrained Models |
Subtitle
| Pretrained models for "PDEBench: An Extensive Benchmark for Scientific Machine Learning" |
Author
| Takamoto, Makoto (NEC Labs Europe) - ORCID: 0000-0001-7192-1956
Praditia, Timothy (Universität Stuttgart) - ORCID: 0000-0003-3619-9122
Leiteritz, Raphael (Universität Stuttgart) - ORCID: 0000-0001-8070-2384
MacKinlay, Dan (CSIRO's Data61) - ORCID: 0000-0001-6077-2684
Alesiani, Francesco (NEC Labs Europe) - ORCID: 0000-0003-4413-7247
Pflüger, Dirk (Universität Stuttgart) - ORCID: 0000-0002-4360-0212
Niepert, Mathias (Universität Stuttgart) - ORCID: 0000-0002-8401-3751 |
Point of Contact
|
Use email button above to contact.
Leiteritz, Raphael (Universität Stuttgart)
Takamoto, Makoto (NEC Labs Europe)
Takamoto, Makoto (NEC Labs Europe)
MacKinlay, Dan (CSIRO's Data61)
Praditia, Timothy (Universität Stuttgart)
Alesiani, Francesco (NEC Labs Europe) |
Description
| This dataset contains the pretrained baseline models, namely FNO, U-Net, and PINN. These models are trained on different PDEs, such as 1D advection, 1D Burgers', 1D and 2D diffusion-reaction, 1D diffusion-sorption, 1D, 2D, and 3D compressible Navier-Stokes, 2D Darcy flow, and 2D shallow water equation. In addition the dataset contains the pre-trained model for the 1D Inverse problem for FNO and U-Net. These models are stored using the same structure as the dataset they trained on. All the files are saved in .pt files, the default file type for the PyTorch library.
More detailed information are also provided in our Github repository (https://github.com/pdebench/PDEBench) and our submitting paper to NeurIPS 2022 Benchmark track. |
Subject
| Computer and Information Science; Earth and Environmental Sciences; Physics |
Keyword
| Benchmark (Wikidata) https://www.wikidata.org/wiki/Q816747
Scientific Machine Learning
Physics-Informed Machine Learning
Machine Learning (Wikidata) https://www.wikidata.org/wiki/Q2539
Partial Differential Equation (Wikidata) https://www.wikidata.org/wiki/Q271977 |
Related Publication
| Takamoto, M., Praditia, T., Leiteritz, R., MacKinlay, D., Alesiani, F., Pflüger, D. and Niepert, M.: PDEBench: An Extensive Benchmark for Scientific Machine Learning. submitted to the 36th Conference on Neural Information Processing Systems (NeurIPS 2022) Track on Datasets and Benchmarks. |
Contributor
| Project Leader : Takamoto, Makoto
Researcher : Praditia, Timothy
Researcher : Leiteritz, Raphael
Researcher : MacKinlay, Dan
Researcher : Alesiani, Francesco
Supervisor : Pflüger, Dirk
Supervisor : Niepert, Mathias |
Funding Information
| DFG: EXC-2075 - 390740016 |
Project
| PDEBench |
Depositor
| Leiteritz, Raphael |
Deposit Date
| 2022-06-09 |
Related Material
| Takamoto, M., Praditia, T., Leiteritz, R., MacKinlay, D., Alesiani, F., Pflüger, D. and Niepert, M.: PDEBench. Github repository. 2022 |
Related Dataset
| Makoto, T., Praditia, T., Leiteritz, R., MacKinlay, D., Alesiani, F., Pflüger, D. and Niepert, M. (2022): PDEBench Datasets, doi: 10.18419/darus-2986, DaRUS. |