JAX-CFD

License: Apache-2.0 · Updated 2026-02-08

JAX-CFD implements incompressible Navier-Stokes solvers in JAX, making the whole time-stepping loop differentiable and JIT-compilable on accelerators.

Use cases: Hybrid neural-CFD models where a learned correction is trained through the solver; gradient-based closure modeling; turbulence model discovery.

Tags: JAXDifferentiable PhysicsCFDGoogleHybrid Modeling
Related entries