tum-pbs/PhiFlow
A differentiable PDE solving framework for machine learning
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.
Stars
1,835
Forks
222
Language
Python
License
MIT
Category
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.
Compare
Related frameworks
pdebench/PDEBench
PDEBench: An Extensive Benchmark for Scientific Machine Learning
ArnauMiro/pyLowOrder
High performance parallel reduced order Modelling library
lettucecfd/lettuce
Computational Fluid Dynamics based on PyTorch and the Lattice Boltzmann Method
peterdsharpe/NeuralFoil
NeuralFoil is a practical airfoil aerodynamics analysis tool using physics-informed machine...
OFDataCommittee/OFMLHackathon
OpenFOAM and Machine Learning Hackathon