ippqw5/PINNLearning

Implement PINN with high level APIs of TF2.0, including a solution of coupled PDEs with PINN

29
/ 100
Experimental

This project offers tools to help engineers and scientists model complex physical systems using machine learning, even when traditional methods struggle. It takes in partial observations or known physical laws for systems described by coupled partial differential equations (PDEs), like fluid flow or heat transfer. The output is a highly accurate prediction of the system's behavior across its entire domain, even in areas with no data, which is useful for design, analysis, or understanding system dynamics.

No commits in the last 6 months.

Use this if you need to solve complex systems of coupled partial differential equations (PDEs) and want to leverage machine learning, especially when you have limited observation data or are dealing with inverse problems like parameter or domain identification.

Not ideal if you are looking for a general-purpose machine learning library for tasks unrelated to scientific computing or if you require solutions that strictly adhere to traditional numerical PDE methods without neural network components.

computational-physics fluid-dynamics heat-transfer inverse-problems scientific-modeling
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

29

Forks

5

Language

Jupyter Notebook

License

Last pushed

Apr 14, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ippqw5/PINNLearning"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.