What symmetry buys a learned turbulence model
July 6, 2026
Research project
What symmetry buys a learned closure
Building the symmetries of the Navier–Stokes equations into a neural turbulence closure is standard advice — and rarely tested. We compared three architectures, from unconstrained to exactly equivariant, and found they all saturate at the same accuracy floor: the optimal one-point closure, measurable directly from data. The constraints buy the trip to that floor with 25× fewer parameters, and a filter-scale Reynolds number input matters more for generalization than the architecture itself.
Paper
Interactive explainer