PhiFlow and SmartFlow
These are complements: PhiFlow provides differentiable PDE solving primitives that SmartFlow could leverage as a physics engine within its reinforcement learning framework for CFD optimization.
About PhiFlow
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.
About SmartFlow
SmartFlow-AI4CFD/SmartFlow
CFD-solver-agnostic deep reinforcement learning framework for computational fluid dynamics on HPC platforms
This framework helps researchers in computational fluid dynamics (CFD) develop and test advanced turbulence models, flow control strategies, and numerical algorithms. It takes outputs from traditional CFD simulations (like flow fields or pressures) and feeds them to deep reinforcement learning (DRL) models, which then generate control actions or model parameters to improve the simulation. It's designed for scientists and engineers working on complex fluid dynamics problems on high-performance computing platforms.
Scores updated daily from GitHub, PyPI, and npm data. How scores work