tum-pbs/PhiFlow

A differentiable PDE solving framework for machine learning

69
/ 100
Established

PhiFlow helps engineers and researchers design and optimize systems involving fluid dynamics, heat transfer, and other physical phenomena. It takes in descriptions of physical setups and outputs simulations that can be directly used with machine learning models. This is ideal for those developing AI-driven solutions for real-world physics problems, like optimizing aerodynamic designs or understanding complex material behaviors.

1,835 stars. Actively maintained with 1 commit in the last 30 days. Available on PyPI.

Use this if you need to integrate physics simulations directly into machine learning models to optimize designs or control systems.

Not ideal if you only need standard physics simulations without any machine learning integration or gradient-based optimization.

fluid-dynamics computational-physics physics-based-AI engineering-design materials-science
Maintenance 13 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 21 / 25

How are scores calculated?

Stars

1,835

Forks

222

Language

Python

License

MIT

Last pushed

Mar 06, 2026

Commits (30d)

1

Dependencies

3

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/tum-pbs/PhiFlow"

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