DrivAerNet++
DrivAerNet++ extends the classic DrivAer benchmark to 8,000 diverse parametric car geometries, each paired with high-fidelity CFD results: 3D flow fields, surface fields, meshes and drag/lift coefficients.
Use cases: Training geometry-to-field surrogate models; aerodynamic coefficient regression; generative design and shape optimization.
The accompanying paper documents dataset construction, mesh generation and baseline benchmarks for common surrogate architectures.
Tags: AutomotiveAeroCFDSurrogateMIT
Related entries
- CFDBench · Multiphysics benchmark for computational fluid dynamics covering internal/extern
- PDEBench · Large-scale PDE benchmark covering heat, advection-diffusion and fluid dynamics
- AirfRANS · Parametric airfoil RANS flow-field dataset - compact and ML-pipeline friendly, t
- TU Delft Turbulent Wake Dataset · Classic experimental & simulation dataset of turbulent wakes/cavity flows from T
- U-bend Thermal-Fluid Dataset · 10,000 parametric 90 degree bend fluid-thermal coupling simulations across curva