HiLiftAeroML: A High-Fidelity Computational Fluid Dynamics Dataset for High-Lift Aircraft Aerodynamics
Abstract
HiLiftAeroML is, to our knowledge, the first open high-fidelity computational fluid dynamics dataset dedicated to high-lift aircraft aerodynamics. It contains 1,800 simulations spanning 180 variants of the NASA Common Research Model high-lift configuration and ten angles of attack from 4∘ to 22∘. Each case was generated with a GPU-accelerated explicit wall-modeled large-eddy simulation approach on solution-adapted grids of 300--500 million cells, covering attached, separated, and post-stall flow conditions. Comparisons with wind-tunnel measurements for reference landing configurations show good agreement in integrated loads and sectional pressures, with grid adaptation substantially improving drag and pitching-moment predictions. The CC-BY-4.0 release includes geometries, time-averaged surface and volume fields, integrated loads, validation material, and deterministic benchmark splits. Initial GeoTransolver and Transolver baselines, evaluated on the complete native surface and volume support of every held-out case rather than on a sampled subset, reconstruct the fields well for several interpolation and held-out-geometry tests, while high-angle separated flow, limited-data training, and out-of-distribution flow-regime shifts remain substantially harder. The dataset and baselines provide a common resource for developing and assessing data-driven models for realistic high-lift aerodynamics.
Related
- SHIFT-Truck: A High-Fidelity Aerodynamics Dataset and Benchmark for Pickup Trucks
- TripNet: Learning large-scale high-fidelity three-dimensional car aerodynamics with triplane networks
- Swarmlet: a GPU-resident reformulated vortex particle method for coupled multirotor aerodynamics and flight dynamics
- Quantitative T2* Fidelity in Accelerated Radial Ultrashort-Echo-Time MRI of the Lumbar Cartilage Endplate: A Synthetic Computational Validation Study
- Dynamical protection of quantum steering and fidelity dynamics in the double Jaynes-Cummings model
BibTeX
@misc{ashton2026hiliftaeroml,
title = {{HiLiftAeroML: A High-Fidelity Computational Fluid Dynamics Dataset for High-Lift Aircraft Aerodynamics}},
author = {Neil Ashton and Adam Clark and Konrad Goc and Liam Heidt and Christopher Ivey and Rahul Agrawal and Sanjeeb T Bose and Corey Adams and Peter Sharpe and Daniel Leibovici and Semih Akkurt and Sheel Nidhan and Rishi Ranade and Jean Kossaifi},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2605.19565},
eprint = {2605.19565},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.19565},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - HiLiftAeroML: A High-Fidelity Computational Fluid Dynamics Dataset for High-Lift Aircraft Aerodynamics
AU - Neil Ashton
AU - Adam Clark
AU - Konrad Goc
AU - Liam Heidt
AU - Christopher Ivey
AU - Rahul Agrawal
AU - Sanjeeb T Bose
AU - Corey Adams
AU - Peter Sharpe
AU - Daniel Leibovici
AU - Semih Akkurt
AU - Sheel Nidhan
AU - Rishi Ranade
AU - Jean Kossaifi
PY - 2026
DA - 2026/09/25
PB - arXiv
DO - 10.48550/arxiv.2605.19565
UR - https://arxiv.org/abs/2605.19565
AB - HiLiftAeroML is, to our knowledge, the first open high-fidelity computational fluid dynamics dataset dedicated to high-lift aircraft aerodynamics. It contains 1,800 simulations spanning 180 variants of the NASA Common Research Model high-lift configuration and ten angles of attack from 4^∘ to 22^∘. Each case was generated with a GPU-accelerated explicit wall-modeled large-eddy simulation approach on solution-adapted grids of 300--500 million cells, covering attached, separated, and post-stall flow conditions. Comparisons with wind-tunnel measurements for reference landing configurations show good agreement in integrated loads and sectional pressures, with grid adaptation substantially improving drag and pitching-moment predictions. The CC-BY-4.0 release includes geometries, time-averaged surface and volume fields, integrated loads, validation material, and deterministic benchmark splits. Initial GeoTransolver and Transolver baselines, evaluated on the complete native surface and volume support of every held-out case rather than on a sampled subset, reconstruct the fields well for several interpolation and held-out-geometry tests, while high-angle separated flow, limited-data training, and out-of-distribution flow-regime shifts remain substantially harder. The dataset and baselines provide a common resource for developing and assessing data-driven models for realistic high-lift aerodynamics.
ER -