This page is for AI assistant context only. To use this package, visit community.ntop.com.
Summary
12,000 LES CFD runs across 2,400 drone planform geometries, generated with nTop Fluids on CoreWeave GPU infrastructure for NASA’s CFD Vision 2030 Grand Challenge.Package Details
A large-eddy simulation (LES) CFD dataset generated with nTop Fluids — nTop’s GPU-native LBM-LES solver — in collaboration with CoreWeave, produced in the context of NASA’s CFD Vision 2030 Grand Challenge for large-scale ensemble simulation.
Orbit render of a sample planform geometry
What’s in it
- 12,000 CFD runs across 2,400 distinct fixed-wing UAS planform geometries (Latin Hypercube sampled) at 5 angles of attack each
- 10,000 runs completed in 32.2 hours; 11,950 of 12,000 completed overall
- Fixed cruise conditions: Mach 0.21, ISA standard day at 30,000 ft
- Per-run outputs: aerodynamic scalars (C_L, C_D, L/D, moments), surface pressure/force distributions, and full 3D flow fields (instantaneous + time-averaged)
- ~1.1 GB per run, ~13-14 TB total
- Simulated on CoreWeave’s GPU cloud infrastructure
Intended use
Design space characterization and surrogate-model / MDO (multidisciplinary design optimization) training over parametric planform geometry. Read more:- nTop + CoreWeave: NASA 2030 Grand Challenge in CFD
- 10,000 LES Simulations in 32 Hours: nTop and CoreWeave Hit NASA’s CFD 2030 Target