https://github.com/amazon-science/boon
Datasets and code for results presented in the BOON paper
Science Score: 36.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
✓Academic publication links
Links to: scholar.google -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (9.5%) to scientific vocabulary
Keywords
Repository
Datasets and code for results presented in the BOON paper
Basic Info
Statistics
- Stars: 43
- Watchers: 7
- Forks: 7
- Open Issues: 1
- Releases: 0
Topics
Metadata Files
README.md
BOON: Boundary correction for neural operators
Nadim Saad*, Gaurav Gupta*, Shima Alizadeh, Danielle C. Maddix\ Guiding continuous operator learning through Physics-based boundary constraints,\ International Conference on Learning Representations, 2023\ (*equal contribution authors)
Setup
Requirements
The code package is developed using Python 3.8 and Pytorch 1.11 with cuda 11.6. The code could be executed on CPU/GPU but GPU is preferred. All experiments were conducted on Tesla V100 16GB.
Experiments
Data
Generate the data using the scripts provided in the 'Data' directory. The scripts use Matlab 2018+. A sample generated dataset for all the experiments is available below.
Scripts
Detailed notebooks for reproducing all the experiments in the paper are provided. The cases of 1D, 1D time-varying, 2D time-varying are shown in the respective notebooks for all the three boundary conditions of Dirichlet, Neumann, and Periodic.
1D Heat equation motivating example
As an example, a complete pipeline is shown for the 1D single-step PDE with Neumann boundary condition in the attached examples_1d_single_step.ipynb notebook.
\
Non-physical solution: Nonzero flux suggests heat flow through an insulator.
1D Stokes' second problem
As an example, a complete pipeline is shown for the 1D time-varying PDE with Dirichlet boundary condition in the attached examples_1d_multi_step.ipynb notebook.
2D Navier-Stokes lid-driven cavity flow
A complete pipeline is shown for the 2D time-varying PDE with Dirichlet boundary condition in the attached examples_3d_multi_step.ipynb notebook.
https://user-images.githubusercontent.com/19197210/217733438-211a4499-d2b3-4830-8bba-2d3d7ad5dfb3.mp4
https://user-images.githubusercontent.com/19197210/217733831-9d9336a3-6709-40f3-b326-716ab98a6d30.mp4
Citation
If you use this code, or our work, please cite:
@inproceedings{saad2022BOON,
author = {Saad, Nadim and Gupta, Gaurav and Alizadeh, Shima and Maddix, Danielle C.},
title = {Guiding continuous operator learning through Physics-based boundary constraints},
booktitle={International Conference on Learning Representations},
year={2023},
}
Owner
- Name: Amazon Science
- Login: amazon-science
- Kind: organization
- Website: https://amazon.science
- Twitter: AmazonScience
- Repositories: 80
- Profile: https://github.com/amazon-science
GitHub Events
Total
- Watch event: 3
Last Year
- Watch event: 3
Issues and Pull Requests
Last synced: over 1 year ago
All Time
- Total issues: 4
- Total pull requests: 0
- Average time to close issues: about 8 hours
- Average time to close pull requests: N/A
- Total issue authors: 3
- Total pull request authors: 0
- Average comments per issue: 0.75
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 3
- Pull requests: 0
- Average time to close issues: about 6 hours
- Average time to close pull requests: N/A
- Issue authors: 2
- Pull request authors: 0
- Average comments per issue: 0.67
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
- Fangwq (1)
- liu-ziyuan-math (1)
- afrah (1)