snap-stanford/le_pde

LE-PDE accelerates PDEs' forward simulation and inverse optimization via latent global evolution, achieving significant speedup with SOTA accuracy

37
/ 100
Emerging

This project helps scientists and engineers quickly simulate complex physical systems and optimize designs. It takes in real-world data about a physical system, like weather patterns or material properties, and outputs rapid predictions for how that system will evolve over time, or suggests optimal configurations. Users include those working in weather forecasting, material science, and engine design who need to run many simulations quickly.

No commits in the last 6 months.

Use this if you need to significantly accelerate the forward simulation or inverse optimization of partial differential equations (PDEs) in scientific or engineering applications, achieving faster results with competitive accuracy compared to other deep learning models.

Not ideal if your work doesn't involve partial differential equations or if you require direct interpretability of every step of a classical physics-based simulation.

scientific-simulation engineering-design weather-forecasting material-science fluid-dynamics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

29

Forks

5

Language

Jupyter Notebook

License

MIT

Last pushed

Jan 30, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/snap-stanford/le_pde"

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