TIDE

License: MIT License · Updated 2026-03-20

TIDE provides direct numerical simulation (DNS) data for 3D turbulence, with 5 evaluation tasks and controlled generalization splits that help researchers rigorously test model extrapolation beyond the training distribution. It is a key 2026 benchmark in turbulence ML.

Use cases: Evaluating the generalization of turbulence surrogates / baselines; comparing architectures on 3D turbulence.

Tags: TurbulenceDNS3DBenchmark
Related entries
  • PDEBench · Large-scale PDE benchmark covering heat, advection-diffusion and fluid dynamics
  • TU Delft Turbulent Wake Dataset · Classic experimental & simulation dataset of turbulent wakes/cavity flows from T
  • PDEArena · Microsoft Research's open-source PDE benchmark suite with differentiable solvers
  • The Well · Unified benchmark spanning 16 physical domains, dubbed the 'ImageNet moment of p
  • CFDBench · Multiphysics benchmark for computational fluid dynamics covering internal/extern