Automotive Ahmed body
AhmedML
AhmedML provides 500 parametric Ahmed-body CFD cases and official train, validation and test splits for data-efficiency and out-of-distribution evaluation.
- Scale
- 500 geometries
- Method
- Hybrid RANS–LES
- Size
- About 2 TB
Automotive Windsor body
WindsorML
WindsorML provides 355 Windsor-body WMLES cases and official train, validation and test splits for data-efficiency and out-of-distribution evaluation.
- Scale
- 355 geometries
- Method
- WMLES
- Size
- About 8 TB
Automotive DrivAer notchback
DrivAerML
DrivAerML is a 500-geometry road-car CFD dataset with official train, validation and test partitions for data-efficiency and out-of-distribution evaluation.
- Scale
- 500-geometry design space
- Method
- Scale-resolving CFD
- Size
- About 31 TB
Aerospace NASA CRM-HL
HiLiftAeroML
HiLiftAeroML comprises 1,800 WMLES cases of NASA CRM-HL aircraft variants for aerodynamic machine-learning research.
- Scale
- 1,800 cases
- Method
- Explicit WMLES
- Size
- About 66.9 TB stored
Technical comparison
Dataset scope and data volume
Stored sizes are approximate and may change with repository revisions. Transfer estimates should be checked before field data are retrieved.
| Dataset | Domain | Scale | Method | Resolution | Stored size | Licence |
|---|---|---|---|---|---|---|
| AhmedMLAhmed body | Automotive | 500 geometries | Hybrid RANS–LES | About 20 million cells per case | About 2 TB | CC BY-SA 4.0 |
| WindsorMLWindsor body | Automotive | 355 geometries | WMLES | About 300 million cells per case | About 8 TB | CC BY-SA 4.0 |
| DrivAerMLDrivAer notchback | Automotive | 500-geometry design space | Scale-resolving CFD | Industrial-scale unstructured meshes | About 31 TB | CC BY-SA 4.0 |
| HiLiftAeroMLNASA CRM-HL | Aerospace | 1,800 cases | Explicit WMLES | 300–500 million cells per case | About 66.9 TB stored | CC BY 4.0 |