HiPerSimLab/PECANN

PECANNs: Physics and Equality Constrained Artificial Neural Networks

39
/ 100
Emerging

This method helps researchers and engineers solve complex physics-based problems described by partial differential equations (PDEs), even with limited or varied data. It takes in observational data and the mathematical equations governing a system, then accurately predicts unknown system behaviors or identifies hidden parameters. Scientists, computational fluid dynamics engineers, and material scientists would find this particularly useful.

No commits in the last 6 months.

Use this if you need highly accurate solutions for forward or inverse problems involving multi-dimensional PDEs, especially when you have multi-fidelity data and need to strictly enforce physical laws and boundary conditions.

Not ideal if your problem doesn't involve physics-based differential equations or if you are looking for a simple, out-of-the-box solution without needing to understand constrained optimization.

computational-physics scientific-modeling inverse-problems engineering-simulation data-assimilation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

24

Forks

8

Language

Jupyter Notebook

License

MIT

Last pushed

Jun 05, 2023

Commits (30d)

0

Get this data via API

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

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