Peiyannn/MM-PDE

[ICLR24] Better Neural PDE Solvers Through Data-Free Mesh Movers

19
/ 100
Experimental

This project helps researchers and engineers solve complex Partial Differential Equations (PDEs) more accurately and efficiently using neural networks. It takes a PDE description and outputs an optimized mesh (computational grid) that adapts to the problem, leading to more precise solutions for simulations in fields like fluid dynamics or physics. This is ideal for computational scientists or engineers who need to model physical phenomena.

No commits in the last 6 months.

Use this if you are working with complex simulations involving Partial Differential Equations and need a way to improve the accuracy and efficiency of your neural network-based solvers.

Not ideal if you are looking for a traditional numerical PDE solver or if your problems do not require adaptive meshing for improved accuracy.

computational-physics fluid-dynamics scientific-simulation numerical-analysis engineering-modeling
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 5 / 25

How are scores calculated?

Stars

17

Forks

1

Language

Python

License

Last pushed

Mar 20, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Peiyannn/MM-PDE"

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