ml-jku/neural-gyrokinetics

Machine learning tools to accelerate high-dimensional plasma turbulence simulations.

43
/ 100
Emerging

This project offers tools for plasma physicists to accelerate high-dimensional simulations of plasma turbulence. It takes initial plasma state data and conditioning parameters as input and quickly outputs predictions for turbulent transport (df, phi, flux). This helps researchers working on scientific machine learning and plasma physics to study complex plasma dynamics more efficiently.

Use this if you are a plasma physicist or researcher who needs to run high-dimensional plasma turbulence simulations significantly faster than traditional methods, or if you need to compress large plasma datasets while preserving critical physical properties.

Not ideal if your primary interest is in low-dimensional or non-plasma related simulations, or if you require an off-the-shelf, easy-to-use software without any machine learning research involvement.

plasma-physics fusion-research turbulence-simulation scientific-computing data-compression
No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 15 / 25
Community 11 / 25

How are scores calculated?

Stars

33

Forks

4

Language

Jupyter Notebook

License

MIT

Last pushed

Mar 10, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ml-jku/neural-gyrokinetics"

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