MJfadeaway/DAS

DAS: A deep adaptive sampling method for solving high-dimensional partial differential equations

40
/ 100
Emerging

This helps researchers and engineers solve complex physics equations without needing extensive pre-calculated data. You input the structure of a high-dimensional partial differential equation, and it outputs a highly accurate numerical solution. It's designed for computational scientists and engineers working with challenging physical models.

No commits in the last 6 months.

Use this if you need to find accurate solutions for complex, high-dimensional partial differential equations (PDEs) and want to avoid the sparsity problems of traditional uniform sampling methods.

Not ideal if your problems are low-dimensional or you prefer working with pre-labeled datasets for surrogate modeling, as a separate, PyTorch-based project handles that specific use case.

computational-physics numerical-methods fluid-dynamics-modeling material-science-simulation engineering-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

39

Forks

8

Language

Python

License

MIT

Last pushed

Nov 20, 2024

Commits (30d)

0

Get this data via API

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

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