PDEBench Pretrained Models (doi:10.18419/darus-2987)

View:

Part 1: Document Description
Part 2: Study Description
Part 5: Other Study-Related Materials
Entire Codebook

Document Description

Citation

Title:

PDEBench Pretrained Models

Identification Number:

doi:10.18419/darus-2987

Distributor:

DaRUS

Date of Distribution:

2022-06-21

Version:

2

Bibliographic Citation:

Takamoto, Makoto; Praditia, Timothy; Leiteritz, Raphael; MacKinlay, Dan; Alesiani, Francesco; Pflüger, Dirk; Niepert, Mathias, 2022, "PDEBench Pretrained Models", https://doi.org/10.18419/darus-2987, DaRUS, V2

Study Description

Citation

Title:

PDEBench Pretrained Models

Subtitle:

Pretrained models for "PDEBench: An Extensive Benchmark for Scientific Machine Learning"

Identification Number:

doi:10.18419/darus-2987

Authoring Entity:

Takamoto, Makoto (NEC Labs Europe)

Praditia, Timothy (Universität Stuttgart)

Leiteritz, Raphael (Universität Stuttgart)

MacKinlay, Dan (CSIRO's Data61)

Alesiani, Francesco (NEC Labs Europe)

Pflüger, Dirk (Universität Stuttgart)

Niepert, Mathias (Universität Stuttgart)

Other identifications and acknowledgements:

Takamoto, Makoto

Other identifications and acknowledgements:

Praditia, Timothy

Other identifications and acknowledgements:

Leiteritz, Raphael

Other identifications and acknowledgements:

MacKinlay, Dan

Other identifications and acknowledgements:

Alesiani, Francesco

Other identifications and acknowledgements:

Pflüger, Dirk

Other identifications and acknowledgements:

Niepert, Mathias

Grant Number:

EXC-2075 - 390740016

Distributor:

DaRUS

Access Authority:

Leiteritz, Raphael

Access Authority:

Takamoto, Makoto

Access Authority:

Takamoto, Makoto

Access Authority:

MacKinlay, Dan

Access Authority:

Praditia, Timothy

Access Authority:

Alesiani, Francesco

Depositor:

Leiteritz, Raphael

Date of Deposit:

2022-06-09

Holdings Information:

https://doi.org/10.18419/darus-2987

Study Scope

Keywords:

Computer and Information Science, Earth and Environmental Sciences, Physics, Benchmark, Scientific Machine Learning, Physics-Informed Machine Learning, Machine Learning, Partial Differential Equation

Abstract:

<p>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. <br/> All the files are saved in .pt files, the default file type for the PyTorch library.</p> <p>More detailed information are also provided in our Github repository (<a href="https://github.com/pdebench/PDEBench">https://github.com/pdebench/PDEBench</a>) and our submitting paper to NeurIPS 2022 Benchmark track.</p>

Notes:

This version includes the pretrained model weights trained using the latest Advection and Burgers equation data.

Methodology and Processing

Sources Statement

Data Access

Other Study Description Materials

Related Materials

Takamoto, M., Praditia, T., Leiteritz, R., MacKinlay, D., Alesiani, F., Pflüger, D. and Niepert, M.: <a href="https://github.com/pdebench/PDEBench">PDEBench</a>. Github repository. 2022

Related Studies

Makoto, T., Praditia, T., Leiteritz, R., MacKinlay, D., Alesiani, F., Pflüger, D. and Niepert, M. (2022): PDEBench Datasets, <a href="https://doi.org/10.18419/darus-2986">doi: 10.18419/darus-2986</a>, DaRUS.

Related Publications

Citation

Title:

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.

Bibliographic Citation:

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.

Other Study-Related Materials

Label:

1D_Advection_Sols_beta4.0_FNO.pt

Text:

Advection pre-trained model (FNO) (1D)

Notes:

application/octet-stream

Other Study-Related Materials

Label:

1D_Advection_Sols_beta4.0_Unet.pt

Text:

Advection pre-trained model (Unet) (1D)

Notes:

application/octet-stream

Other Study-Related Materials

Label:

1D_Burgers_Sols_Nu1.0_FNO.pt

Text:

Burgers pre-trained model (FNO) (1D)

Notes:

application/octet-stream

Other Study-Related Materials

Label:

1D_Burgers_Sols_Nu1.0_Unet.pt

Text:

Burgers pre-trained model (Unet) (1D)

Notes:

application/octet-stream

Other Study-Related Materials

Label:

1D_CFD_Shock_trans_Train_FNO.pt

Text:

CFD pre-trained model (FNO) (1D)

Notes:

application/octet-stream

Other Study-Related Materials

Label:

1D_CFD_Shock_trans_Train_Unet.pt

Text:

CFD pre-trained model (Unet) (1D)

Notes:

application/octet-stream

Other Study-Related Materials

Label:

ReacDiff_Nu1.0_Rho2.0_FNO.pt

Text:

ReactionDiffusion pre-trained model (FNO) (1D)

Notes:

application/octet-stream

Other Study-Related Materials

Label:

ReacDiff_Nu1.0_Rho2.0_Unet.pt

Text:

ReactionDiffusion pre-trained model (Unet) (1D)

Notes:

application/octet-stream

Other Study-Related Materials

Label:

1DCFD_FNO.tar

Text:

1D compressible NS eq pretrained model for FNO

Notes:

application/x-tar

Other Study-Related Materials

Label:

1DReacDiff_FNO.tar

Text:

1D Reaction-Diffusion eq pretrained model for FNO

Notes:

application/x-tar

Other Study-Related Materials

Label:

1D_diff-sorp_NA_NA_FNO.pt

Notes:

application/octet-stream

Other Study-Related Materials

Label:

2DCFD_FNO.tar

Text:

2D compressible NS eq pretrained model for FNO

Notes:

application/x-tar

Other Study-Related Materials

Label:

2D_diff-react_NA_NA_FNO.pt

Notes:

application/octet-stream

Other Study-Related Materials

Label:

2D_rdb_NA_NA_FNO.pt

Notes:

application/octet-stream

Other Study-Related Materials

Label:

3DCFD_FNO.tar

Text:

3D compressible NS eq pretrained model for FNO

Notes:

application/x-tar

Other Study-Related Materials

Label:

advection_FNO-1.tar

Text:

Notes:

text/plain

Other Study-Related Materials

Label:

advection_FNO.tar

Text:

1D Advection eq pretrained model for FNO

Notes:

application/x-tar

Other Study-Related Materials

Label:

burgers_FNO-1.tar

Text:

Notes:

text/plain

Other Study-Related Materials

Label:

burgers_FNO.tar

Text:

1D Burgers eq pretrained model for FNO

Notes:

application/x-tar

Other Study-Related Materials

Label:

DarcyFlow_FNO.tar

Text:

2D DarcyFlow pretrained model for FNO

Notes:

application/x-tar

Other Study-Related Materials

Label:

1DCFD_PINN.tar

Text:

1D compressible NS eq pretrained model for PINN

Notes:

application/x-tar

Other Study-Related Materials

Label:

1DReacDiff_PINN.tar

Text:

1D Reaction-Diffusion eq pretrained model for PINN

Notes:

application/x-tar

Other Study-Related Materials

Label:

1D_diff-sorp_NA_NA_0001.h5_PINN.pt-15000.pt

Notes:

application/vnd.snesdev-page-table

Other Study-Related Materials

Label:

2D_diff-react_NA_NA_0000.h5_PINN.pt-15000.pt

Notes:

application/vnd.snesdev-page-table

Other Study-Related Materials

Label:

2D_rdb_NA_NA_0000.h5_PINN.pt-15000.pt

Notes:

application/vnd.snesdev-page-table

Other Study-Related Materials

Label:

advection_PINN-1.tar

Text:

Notes:

text/plain

Other Study-Related Materials

Label:

advection_PINN.tar

Text:

1D Advection eq pretrained model for PINN

Notes:

application/x-tar

Other Study-Related Materials

Label:

burgers_PINN-1.tar

Text:

Notes:

text/plain

Other Study-Related Materials

Label:

burgers_PINN.tar

Text:

1D Burgers eq pretrained model for PINN

Notes:

application/x-tar

Other Study-Related Materials

Label:

1DCFD_Unet.tar

Text:

1D compressible NS eq pretrained model for Unet

Notes:

application/x-tar

Other Study-Related Materials

Label:

1DReacDiff_Unet.tar

Text:

1D Reaction-Diffusion eq pretrained model for Unet

Notes:

application/x-tar

Other Study-Related Materials

Label:

1D_diff-sorp_NA_NA_Unet-1-step.pt

Notes:

application/octet-stream

Other Study-Related Materials

Label:

1D_diff-sorp_NA_NA_Unet-AR.pt

Notes:

application/octet-stream

Other Study-Related Materials

Label:

1D_diff-sorp_NA_NA_Unet-PF-20.pt

Notes:

application/octet-stream

Other Study-Related Materials

Label:

2DCFD_Unet.tar

Text:

2D compressible NS eq pretrained model for Unet

Notes:

application/x-tar

Other Study-Related Materials

Label:

2D_diff-react_NA_NA_Unet-1-step.pt

Notes:

application/octet-stream

Other Study-Related Materials

Label:

2D_diff-react_NA_NA_Unet-AR.pt

Notes:

application/octet-stream

Other Study-Related Materials

Label:

2D_diff-react_NA_NA_Unet-PF-20.pt

Notes:

application/octet-stream

Other Study-Related Materials

Label:

2D_rdb_NA_NA_Unet-1-step.pt

Notes:

application/octet-stream

Other Study-Related Materials

Label:

2D_rdb_NA_NA_Unet-AR.pt

Notes:

application/octet-stream

Other Study-Related Materials

Label:

2D_rdb_NA_NA_Unet-PF-20.pt

Notes:

application/octet-stream

Other Study-Related Materials

Label:

3DCFD_Unet.tar

Text:

3D compressible NS eq pretrained model for Unet

Notes:

application/x-tar

Other Study-Related Materials

Label:

advection_Unet-1.tar

Text:

Notes:

text/plain

Other Study-Related Materials

Label:

advection_Unet.tar

Text:

1D Advection eq pretrained model for Unet

Notes:

application/x-tar

Other Study-Related Materials

Label:

burgers_Unet-1.tar

Text:

Notes:

text/plain

Other Study-Related Materials

Label:

burgers_Unet.tar

Text:

1D Burgers eq pretrained model for Unet

Notes:

application/x-tar

Other Study-Related Materials

Label:

DarcyFlow_Unet.tar

Text:

2D DarcyFlow pretrained model for Unet

Notes:

application/x-tar