jaggbow/magnet

This repository contains code for the paper "MAgNet: Mesh-Agnostic Neural PDE Solver" https://arxiv.org/abs/2210.05495

25
/ 100
Experimental

This project helps researchers and engineers quickly predict solutions to complex Partial Differential Equations (PDEs). You provide existing simulation data on various computational grids, and it outputs predictions for the PDE's behavior at any point within the problem domain, even on new, previously unseen grids or resolutions. This is for computational scientists, physicists, or engineers who work with simulations and need to generalize their models without retraining.

No commits in the last 6 months.

Use this if you need to predict the outcomes of physical or engineering simulations (governed by PDEs) on diverse computational grids without having to regenerate or retrain models for each new grid resolution or structure.

Not ideal if your problems are not described by Partial Differential Equations or if you always work with fixed, regular simulation grids.

computational-physics fluid-dynamics structural-mechanics numerical-simulation materials-science
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 10 / 25

How are scores calculated?

Stars

38

Forks

4

Language

Python

License

Last pushed

Jun 21, 2023

Commits (30d)

0

Get this data via API

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

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