pith. sign in

arxiv: 2605.19565 · v1 · pith:HSHUH3LBnew · submitted 2026-05-19 · ⚛️ physics.flu-dyn · cs.LG

HiLiftAeroML: High-Fidelity Computational Fluid Dynamics Dataset for High-Lift Aircraft Aerodynamics

Neil Ashton , Adam Clark , Liam Heidt , Christopher Ivey , Sanjeeb Bose , Rahul Agrawal , Konrad Goc , Rishi Ranade
show 6 more authors
Corey Adams Peter Sharpe Sheel Nidhan Semit Akkurt Daniel Leibovici Jean Kossaifi
This is my paper

Pith reviewed 2026-05-20 02:48 UTC · model grok-4.3

classification ⚛️ physics.flu-dyn cs.LG
keywords high-lift aerodynamicsCFD datasetwall-modeled LESNASA CRMAI surrogate modelingopen-source dataaircraft aerodynamicshigh-fidelity simulation
0
0 comments X p. Extension
pith:HSHUH3LB Add to your LaTeX paper What is a Pith Number? 
\usepackage{pith}
\pithnumber{HSHUH3LB}

Prints a linked pith:HSHUH3LB badge after your title and writes the identifier into PDF metadata. Compiles on arXiv with no extra files. Learn more

The pith

The first open-source high-fidelity CFD dataset for high-lift aircraft has been released to support AI surrogate model development.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This paper presents a dataset of 1800 high-fidelity computational fluid dynamics simulations covering 180 geometry variants and 10 angles of attack for the high-lift NASA Common Research Model. Each simulation uses GPU-accelerated explicit wall-modeled large eddy simulation on solution-adapted grids with 300 to 500 million cells. The authors position this approach as more accurate than steady-state Reynolds-averaged Navier-Stokes methods for the high-lift flight regime. The full set of geometries, time-averaged flow variables, and integral forces is made available under a permissive license to speed up research on AI-based predictions of aircraft performance.

Core claim

The paper establishes the first open-source high-fidelity CFD dataset for high-lift aircraft aerodynamics, consisting of 1800 samples from 180 geometry variants and 10 angles of attack of the NASA CRM high-lift configuration, each computed with GPU-accelerated explicit wall-modeled LES on 300M-500M cell grids, with all geometries, volume and surface data, and forces released under CC-BY-4.0.

What carries the argument

The dataset of 1800 wall-modeled LES simulations on large solution-adapted grids that supplies time-averaged flow fields and forces for AI surrogate training.

If this is right

  • AI surrogate models trained on this data can predict high-lift forces and flow fields for new configurations without running full CFD each time.
  • The open release removes the need for each research group to generate its own expensive high-fidelity data.
  • Design studies can now explore more geometry variations and angles of attack than was previously practical with RANS alone.
  • Time-averaged volume and surface variables in the dataset enable training of models that output full flow-field predictions rather than only integral quantities.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The dataset's geometry variants could be used to quantify sensitivity of high-lift performance to small changes in flap or slat settings.
  • Similar high-fidelity datasets for other aircraft classes or flow regimes could be generated using the same workflow to expand the range of AI surrogates.
  • Integration of this data with optimization loops might allow rapid exploration of high-lift configurations that minimize drag while meeting lift requirements.

Load-bearing premise

The wall-modeled large eddy simulation results on 300M-500M cell grids are accurate enough to serve as reliable ground truth for training AI models of high-lift flows.

What would settle it

A direct comparison of the dataset's predicted lift, drag, and pitching moment coefficients against experimental data from the AIAA High-Lift Prediction Workshop at the same conditions would show whether the simulations match physical measurements within acceptable error.

Figures

Figures reproduced from arXiv: 2605.19565 by Adam Clark, Christopher Ivey, Corey Adams, Daniel Leibovici, Jean Kossaifi, Konrad Goc, Liam Heidt, Neil Ashton, Peter Sharpe, Rahul Agrawal, Rishi Ranade, Sanjeeb Bose, Semit Akkurt, Sheel Nidhan.

Figure 1
Figure 1. Figure 1: CRM-HL Geometry shown in the Reference Landing Configuration a manner that encompasses the set of already defined reference positions. The leading-edge high-lift system features a slat, whose deployment relative to the main wing is defined by its deflection angle, gap, and height as shown in [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 3
Figure 3. Figure 3: Schematic of the baseline case setup showing the inflow, outflow regions and the symmetry plane along which the semi-span aircraft model is mounted. ongoing work relating to the impact of slat-transition, and also minimize its aerodynamic impacts [PITH_FULL_IMAGE:figures/full_fig_p004_3.png] view at source ↗
Figure 2
Figure 2. Figure 2: Sectional views of Leading and Trailing Edge Device Positioning Parameters At the trailing edge, single slotted flaps are employed, and their geometric settings are characterized by deflection an￾gle, gap, and overlap relative to the main wing element. Similar to the slat, the flap deflection is the most dominant variable, and is allowed a range of 10o through 45o . This range fully captures the most shall… view at source ↗
Figure 4
Figure 4. Figure 4: Grid distribution (from a side-view) on the airframe, with specific details of the three-element airfoil slice (taken at mid-span of the main wing element), around the fuselage and the nacelle, the vertical tail and the horizontal stabilizers respectively. Note that these images represent a grid four times coarser than the baseline grid for visual clarity. conserve kinetic energy. The numerical discretizat… view at source ↗
Figure 5
Figure 5. Figure 5: Comparison of predicted integrated loads across the angle-of-attack sweep with experiments (Mouton et al., 2024) for the with-tail and with-stabilizer configuration at ReMAC = 1.6 × 106 [PITH_FULL_IMAGE:figures/full_fig_p006_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: presents a qualitative comparison of the near-surface flow patterns at the α = 18◦ angle of attack. On the adapted grid, both the simulation and the experiments show outboard wedge-shaped separation patterns near the wing tip, in con￾junction with an otherwise attached inboard flow. Both the simulations and experiment also show some evidence of flow separation on the flap near the Yehudi break. Appendix C … view at source ↗
Figure 7
Figure 7. Figure 7: Lift Coefficient vs IB (inboard) flap deflection angle for all angles of attack [PITH_FULL_IMAGE:figures/full_fig_p007_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Comparison of integrated forces (lift, pitching moment, and drag) across the angle of attack sweeps for the two configurations (LHC029 and LHC013). Metric LHC013 LHC029 IB Flap Deflection 10.97 39.34 OB Flap Deflection 17.09 18.65 IB Flap Gap Multiplier 1.33 0.74 OB Flap Gap Multiplier 1.46 1.06 IB Slat Deflection 14.97 28.69 OB Slat Deflection 10.48 29.61 IB Slat Gap Multiplier 1.11 1.50 OB Slat Gap Multi… view at source ↗
Figure 9
Figure 9. Figure 9: Comparison of absolute value of the skin-friction on the wing-surfaces, |Cf |, at two specific AoA, α = 8◦ and 18◦ , for the two configurations (LHC029 and LHC013), illustrating two different flow characteristics. The white isosurface denotes the ux/U∞ ≈ 0 region where x denotes the streamwise flow direction and U∞ denotes the freestream flow velocity. to 22◦ . Provided under a permissive license HiLiftAer… view at source ↗
Figure 10
Figure 10. Figure 10: Grid distribution (from a side-view) on the airframe, with specific details of the three-element airfoil slice (taken at mid-span of the main wing element), around the fuselage and the nacelle, the vertical tail and the horizontal stabilizers respectively. Note that these images represent a grid four times coarser than the baseline grid for visual clarity. Variable Value Units Description cref 275.80 inch… view at source ↗
Figure 11
Figure 11. Figure 11: Example statistical convergence plots for Lift (CL), Drag (CD), and Pitching Moment (CM) coefficients for geometry LHC001 at 10◦ AoA (left column) and 22◦ AoA (right column). The plots display the instantaneous signal (scatter), the running mean (solid line), and the running 95% confidence interval (shaded/dashed lines) plotted against Convective Time Units. 15 [PITH_FULL_IMAGE:figures/full_fig_p015_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: Standard deviation of Lift (CL), Drag (CD), and Pitching Moment (CM) coefficients plotted against Geometry ID for various Angles of Attack. 17 [PITH_FULL_IMAGE:figures/full_fig_p017_12.png] view at source ↗
Figure 13
Figure 13. Figure 13: Comparison of predicted integrated loads across the angle-of-attack sweep with experiments (Mouton et al., 2024) for the LDG-HV configuration at ReMAC = 1.6 × 106 [PITH_FULL_IMAGE:figures/full_fig_p021_13.png] view at source ↗
Figure 14
Figure 14. Figure 14: Contours of near-wall resolution from the adaptation approach (Agrawal et al., 2024a) at α = 18◦ . It is apparent that the leading edges of the wing element necessitate more grid refinement than the rest of the wing. Similarly, finer grids are dynamically allocated to the slat element where the strong inviscid acceleration of the flow imposes strict pressure-gradient based resolution requirements. This ta… view at source ↗
Figure 15
Figure 15. Figure 15: Comparisons of surface pressure belts from current wall-modeled LES (adapted grid) with experiments (Mouton et al., 2024) at α = 18◦ for the LDG configuration. 22 [PITH_FULL_IMAGE:figures/full_fig_p022_15.png] view at source ↗
Figure 16
Figure 16. Figure 16: Comparison of oil-film visualization from experiments (Mouton et al., 2024) with averaged wall-stress contours on the suction side at α = 18◦ . Finally, [PITH_FULL_IMAGE:figures/full_fig_p023_16.png] view at source ↗
Figure 17
Figure 17. Figure 17: Sectional views of Leading and Trailing Edge Device Positioning Parameters At the trailing edge, single slotted flaps are employed, and their geometric settings are characterized by deflection angle, gap, and overlap relative to the main wing element. Similar to the slat, the flap deflection is the most dominant variable, and is allowed a range of 10o through 45o . This range fully captures the most shall… view at source ↗
Figure 18
Figure 18. Figure 18: Drag, Lift and Moment Coefficient vs Geo ID number for 4 degrees AoA To further illustrate the dependencies between geometric parameters and aerodynamic performance, Fig. ?? and Fig. ?? plot the Lift Coefficient (CL) against key deflection parameters. Several clear trends emerge. First, there is a primary positive correlation between the inboard flap deflection and CL, which is consistent with the increas… view at source ↗
Figure 19
Figure 19. Figure 19: Drag, Lift and Moment Coefficient vs Geo ID number for 12 degrees AoA flap ≈ 11◦ ), whereas LHC029 features significantly more aggressive settings (inboard flap ≈ 39◦ ). As shown in [PITH_FULL_IMAGE:figures/full_fig_p033_19.png] view at source ↗
Figure 20
Figure 20. Figure 20: Drag, Lift and Moment Coefficient vs Geo ID number for 22 degrees AoA 34 [PITH_FULL_IMAGE:figures/full_fig_p034_20.png] view at source ↗
Figure 21
Figure 21. Figure 21: Variation of force coefficients with selected geometry parameters over all samples and AoA in the dataset. The top-left inset in each quadrant visualises the geometry parameter being varied. 35 [PITH_FULL_IMAGE:figures/full_fig_p035_21.png] view at source ↗
Figure 22
Figure 22. Figure 22: Variation of force coefficients with selected geometry parameters (2x2 layout). The top-left inset in each quadrant indicates the highlighted geometry component. 36 [PITH_FULL_IMAGE:figures/full_fig_p036_22.png] view at source ↗
Figure 23
Figure 23. Figure 23: Variation of force coefficients with selected geometry parameters over all samples and 12 degrees AoA in the dataset. The top-left inset visualises the geometry configuration reference. 37 [PITH_FULL_IMAGE:figures/full_fig_p037_23.png] view at source ↗
Figure 24
Figure 24. Figure 24: Variation of force coefficients with selected geometry parameters over all samples and 22 degrees AoA in the dataset. The top-left inset visualises the geometry configuration reference. 38 [PITH_FULL_IMAGE:figures/full_fig_p038_24.png] view at source ↗
Figure 25
Figure 25. Figure 25: Comparison of integrated forces (lift, pitching moment, and drag) across the angle of attack sweeps for the two configurations (LHC029 and LHC013) [PITH_FULL_IMAGE:figures/full_fig_p039_25.png] view at source ↗
Figure 26
Figure 26. Figure 26: Comparison of absolute value of the skin-friction on the wing-surfaces, |Cf |, at two specific AoA, α = 8◦ and 18◦ , for the two configurations (LHC029 and LHC013), illustrating two different flow characteristics. The white isosurface denotes the ux/U∞ ≈ 0 region where x denotes the streamwise flow direction and U∞ denotes the freestream flow velocity. 39 [PITH_FULL_IMAGE:figures/full_fig_p039_26.png] view at source ↗
Figure 27
Figure 27. Figure 27: Iso-surfaces of negative velocity (i.e flow separation) for runs 1 to 20 at 4 degrees AoA - top view 40 [PITH_FULL_IMAGE:figures/full_fig_p040_27.png] view at source ↗
Figure 28
Figure 28. Figure 28: Iso-surfaces of negative velocity (i.e flow separation) for runs 1 to 20 at 4 degrees AoA - side view 41 [PITH_FULL_IMAGE:figures/full_fig_p041_28.png] view at source ↗
Figure 29
Figure 29. Figure 29: Iso-surfaces of negative velocity (i.e flow separation) for runs 1 to 20 at 16 degrees AoA - side view 42 [PITH_FULL_IMAGE:figures/full_fig_p042_29.png] view at source ↗
Figure 30
Figure 30. Figure 30: Iso-surfaces of negative velocity (i.e flow separation) for runs 1 to 20 at 16 degrees AoA - top view 43 [PITH_FULL_IMAGE:figures/full_fig_p043_30.png] view at source ↗
Figure 31
Figure 31. Figure 31: Iso-surfaces of negative velocity (i.e flow separation) for runs 1 to 20 at 22 degrees AoA - side view 44 [PITH_FULL_IMAGE:figures/full_fig_p044_31.png] view at source ↗
Figure 32
Figure 32. Figure 32: Iso-surfaces of negative velocity (i.e flow separation) for runs 1 to 20 at 22 degrees AoA - top view 45 [PITH_FULL_IMAGE:figures/full_fig_p045_32.png] view at source ↗
read the original abstract

This paper describes the first-ever open-source high-fidelity CFD dataset of a high-lift aircraft for the purpose of AI surrogate model development. The dataset is composed of 1800 samples, arising from 180 geometry variants and 10 angles of attack for the high-lift NASA Common Research Model (CRM) geometry, used within the AIAA High-Lift Prediction Workshop series. One of the novelties of this dataset is the use of a GPU-accelerated high-fidelity explicit, wall-modeled LES approach for each simulation, using solution-adapted grids between 300M and 500M cells. This ensures the greatest possible accuracy given known challenges in steady-state RANS approaches for these portions of the flight envelope. The entire dataset (geometries, time-averaged volume and surface variables and integral forces) are available, free of charge with a permissive open-source license (CC-BY-4.0). By making this data publicly available, we aim to accelerate the research and development of AI surrogate modeling within the aerospace industry.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper introduces HiLiftAeroML, the first open-source high-fidelity CFD dataset for high-lift aircraft aerodynamics. It consists of 1800 samples from 180 geometry variants of the NASA CRM high-lift configuration at 10 angles of attack. Simulations are performed using GPU-accelerated explicit wall-modeled LES on solution-adapted grids with 300M to 500M cells. The dataset includes geometries, time-averaged volume and surface variables, and integral forces, released under the CC-BY-4.0 license to support the development of AI surrogate models in the aerospace industry.

Significance. If the WMLES simulations provide the claimed high accuracy for the high-lift regime, this dataset represents a significant contribution by providing large-scale, open data that can accelerate machine learning applications in aerodynamics. It directly addresses the scarcity of high-fidelity data for complex configurations where RANS methods are known to have limitations. The open-source release with a permissive license enhances its potential impact on the community.

major comments (2)
  1. Abstract: The statement that the WMLES approach 'ensures the greatest possible accuracy given known challenges in steady-state RANS approaches' lacks supporting evidence in the manuscript, such as grid-convergence studies, comparisons to experimental data from the AIAA High-Lift Prediction Workshop, or quantified error metrics for lift, drag, or surface pressure in separated flow regions. This is load-bearing for the dataset's designation as 'high-fidelity' and its suitability for training reliable AI surrogates.
  2. Dataset description section: No details are provided on verification that the solution-adapted grids of 300M-500M cells achieve adequate resolution for capturing key high-lift phenomena such as leading-edge vortices, flap separation, or wake interactions under the explicit WMLES formulation.
minor comments (2)
  1. The manuscript would benefit from a summary table listing the number of cells, time-averaging intervals, and computational resources used across the 1800 simulations to aid reproducibility.
  2. Consider including a short section on known limitations of the wall model employed and how they may affect predictions in the high-lift regime for users developing AI surrogates.

Simulated Author's Rebuttal

2 responses · 1 unresolved

We are grateful to the referee for their careful reading and valuable suggestions. We have carefully considered the major comments and provide our responses below, along with plans for revisions to the manuscript.

read point-by-point responses

  1. Referee: Abstract: The statement that the WMLES approach 'ensures the greatest possible accuracy given known challenges in steady-state RANS approaches' lacks supporting evidence in the manuscript, such as grid-convergence studies, comparisons to experimental data from the AIAA High-Lift Prediction Workshop, or quantified error metrics for lift, drag, or surface pressure in separated flow regions. This is load-bearing for the dataset's designation as 'high-fidelity' and its suitability for training reliable AI surrogates.

    Authors: We concur that the current wording in the abstract makes a strong claim without direct supporting evidence presented in the paper. This manuscript focuses on the generation and public release of the HiLiftAeroML dataset rather than on a detailed validation of the WMLES results against experiments. While the choice of explicit WMLES on large, adapted grids is motivated by the known deficiencies of RANS in predicting separated flows at high angles of attack, we will revise the abstract to avoid the phrase 'ensures the greatest possible accuracy' and instead describe the approach as providing high-fidelity data that mitigates some limitations of RANS. We will include citations to previous studies that have validated the WMLES methodology for high-lift configurations. We are unable to add new grid-convergence studies or error metrics at this stage without performing additional simulations and post-processing, which falls outside the intended scope of this work. revision: partial

  2. Referee: Dataset description section: No details are provided on verification that the solution-adapted grids of 300M-500M cells achieve adequate resolution for capturing key high-lift phenomena such as leading-edge vortices, flap separation, or wake interactions under the explicit WMLES formulation.

    Authors: We accept this observation and will enhance the dataset description section with additional information on the grid generation and adaptation process. Specifically, we will describe the criteria used for solution-based adaptation to ensure sufficient resolution in critical areas such as leading-edge regions, flap gaps, and wakes. This will include references to resolution requirements for WMLES in complex aerodynamic flows. However, we note that exhaustive verification for each of the 180 geometry variants was not conducted as part of this project; the grid sizes were selected based on established practices for achieving acceptable accuracy in WMLES for high-lift problems. revision: yes

standing simulated objections not resolved
  • Conducting comprehensive grid-convergence studies and providing quantified error metrics compared to experimental data for the entire dataset

Circularity Check

0 steps flagged

Dataset release paper with no derivations, predictions, or self-referential steps

full rationale

This is a dataset release paper whose central contribution is the public distribution of 1800 WMLES simulations on the high-lift NASA CRM. No equations are derived, no parameters are fitted to data, and no predictions are made that could reduce to internal quantities by construction. The accuracy claim for WMLES versus RANS is an external assertion based on known literature limitations rather than any self-citation chain or definitional loop within the paper. The work is therefore self-contained with respect to the circularity criteria.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The paper introduces no free parameters, axioms, or invented entities; it is a data publication that applies established CFD techniques to generate and release simulations.

pith-pipeline@v0.9.0 · 5763 in / 1171 out tokens · 46854 ms · 2026-05-20T02:48:15.577020+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

300 extracted references · 300 canonical work pages · 1 internal anchor

  1. [1]

    Clark and Christopher L

    Adam M. Clark and Christopher L. Rumsey and Jeffrey P. Slotnick and Li Wang , title =. AIAA SciTech Forum , doi =. https://arc.aiaa.org/doi/pdf/10.2514/6.2025-0045 , year=

    work page doi:10.2514/6.2025-0045 2025

  2. [2]

    Nielsen and Aaron Walden and Gabriel Nastac and Li Wang and William Jones and Mark Lohry and William K

    Eric J. Nielsen and Aaron Walden and Gabriel Nastac and Li Wang and William Jones and Mark Lohry and William K. Anderson and Boris Diskin and Yi Liu and Christopher L. Rumsey and Prahladh Iyer and Patrick Moran and Mohammad Zubair , title =. AIAA AVIATION FORUM AND ASCEND 2024 , chapter =. doi:10.2514/6.2024-3866 , URL =. https://arc.aiaa.org/doi/pdf/10.2...

    work page doi:10.2514/6.2024-3866 2024

  3. [3]

    AIAA SCITECH 2025 Forum , pages=

    Rapidus: Performance-Portable Parallel Flow Solver for Aerospace Applications , author=. AIAA SCITECH 2025 Forum , pages=

    work page 2025

  4. [4]

    2025 , eprint=

    GeoTransolver: Learning Physics on Irregular Domains Using Multi-scale Geometry Aware Physics Attention Transformer , author=. 2025 , eprint=

    work page 2025

  5. [5]

    2025 , eprint=

    SuperWing: a comprehensive transonic wing dataset for data-driven aerodynamic design , author=. 2025 , eprint=

    work page 2025

  6. [6]

    Development of the high lift common research model (

    Lacy, Doug S and Sclafani, Anthony J , booktitle =. Development of the high lift common research model (. 2016 , doi=

    work page 2016

  7. [7]

    Lacy and Adam M

    Doug S. Lacy and Adam M. Clark , title =. AIAA Aviation Forum , doi =. https://arc.aiaa.org/doi/pdf/10.2514/6.2020-2771 , year=

    work page doi:10.2514/6.2020-2771 2020

  8. [8]

    Evans and Doug S

    Ashley N. Evans and Doug S. Lacy and Ian Smith and Melissa B. Rivers , title =. AIAA Aviation Forum , doi =

    work page

  9. [9]

    2008 , booktitle =

    John Vassberg and Mark Dehaan and Melissa Rivers and Richard Wahls , title =. 2008 , booktitle =. doi:10.2514/6.2008-6919 , URL =

    work page doi:10.2514/6.2008-6919 2008

  10. [10]

    arXiv preprint arXiv:2502.04317 , year=

    Factorized Implicit Global Convolution for Automotive Computational Fluid Dynamics Prediction , author=. arXiv preprint arXiv:2502.04317 , year=

    work page arXiv

  11. [11]

    Advances in neural information processing systems , volume=

    Pointnet++: Deep hierarchical feature learning on point sets in a metric space , author=. Advances in neural information processing systems , volume=

    work page

  12. [12]

    Advances in neural information processing systems , volume=

    Pointnext: Revisiting pointnet++ with improved training and scaling strategies , author=. Advances in neural information processing systems , volume=

    work page

  13. [13]

    Transolver: A Fast Transformer Solver for PDEs on General Geometries

    Transolver: A fast transformer solver for pdes on general geometries , author=. arXiv preprint arXiv:2402.02366 , year=

    work page internal anchor Pith review Pith/arXiv arXiv

  14. [14]

    Advances in Neural Information Processing Systems , volume=

    Geometry-informed neural operator for large-scale 3d pdes , author=. Advances in Neural Information Processing Systems , volume=

    work page

  15. [15]

    arXiv preprint arXiv:2501.13350 , year=

    DoMINO: A Decomposable Multi-scale Iterative Neural Operator for Modeling Large Scale Engineering Simulations , author=. arXiv preprint arXiv:2501.13350 , year=

    work page arXiv

  16. [16]

    arXiv preprint arXiv:2502.09692 , year=

    NeuralCFD: Deep Learning on High-Fidelity Automotive Aerodynamics Simulations , author=. arXiv preprint arXiv:2502.09692 , year=

    work page arXiv

  17. [17]

    arXiv preprint arXiv:2411.17164 , year=

    X-meshgraphnet: Scalable multi-scale graph neural networks for physics simulation , author=. arXiv preprint arXiv:2411.17164 , year=

    work page arXiv

  18. [18]

    Nature machine intelligence , volume=

    Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators , author=. Nature machine intelligence , volume=. 2021 , publisher=

    work page 2021

  19. [19]

    arXiv preprint arXiv:2503.15766 , year=

    Accelerating Transient CFD through Machine Learning-Based Flow Initialization , author=. arXiv preprint arXiv:2503.15766 , year=

    work page arXiv

  20. [20]

    SAE transactions , pages=

    Some salient features of the time-averaged ground vehicle wake , author=. SAE transactions , pages=. 1984 , publisher=

    work page 1984

  21. [21]

    Angel and Aditya Ghate and Gaetan Kenway and Man Long Wong and Cetin C

    Neil Ashton and Jordan B. Angel and Aditya Ghate and Gaetan Kenway and Man Long Wong and Cetin C. Kiris and Astrid Walle and Danielle C. Maddix and Gary Page , booktitle=. Windsor. 2024 , url=

    work page 2024

  22. [22]

    2024 , journal=

    Data-Efficient Operator Learning via Unsupervised Pretraining and In-Context Learning , author=. 2024 , journal=

    work page 2024

  23. [23]

    1989 , institution=

    A strategy for optimum surveys of passenger-car flow fields , author=. 1989 , institution=

    work page 1989

  24. [24]

    Introduction of a new full-scale open cooling version of the

    Hupertz, Burkhard and Kr. Introduction of a new full-scale open cooling version of the. Progress in Vehicle Aerodynamics and Thermal Management: 11th FKFS Conference, Stuttgart, September 26-27, 2017 11 , pages=. 2018 , organization=

    work page 2017

  25. [25]

    arXiv preprint arXiv:2406.09624 , year=

    DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks , author=. arXiv preprint arXiv:2406.09624 , year=

    work page arXiv

  26. [26]

    and Mockett, C

    Fuchs, M. and Mockett, C. and Steger, M. and Thiele, F. , booktitle =. A novel

    work page

  27. [27]

    2024 , journal=

    Using Uncertainty Quantification to Characterize and Improve Out-of-Domain Learning for PDEs , author=. 2024 , journal=

    work page 2024

  28. [28]

    Nat Mach Intell , volume =

    Incorporating physics into data-driven computer vision , author=. Nat Mach Intell , volume =

    work page

  29. [29]

    2023 , journal=

    Learning skillful medium-range global weather forecasting , author=. 2023 , journal=

    work page 2023

  30. [30]

    2023 , author =

    Advances in. 2023 , author =

    work page 2023

  31. [31]

    and Cantwell, Chris D

    Lino, Mario and Fotiadis, Stathi and Bharath, Anil A. and Cantwell, Chris D. , number =. 2023 , booktitle =. doi:10.1098/rspa.2023.0058 , issn =

    work page doi:10.1098/rspa.2023.0058 2023

  32. [32]

    and Mockett, C

    Fuchs, M. and Mockett, C. and Sesterhenn, J. and Thiele, F. , publisher =. Assessment of novel. doi:10.2514/6.2015-3433 , year =

    work page doi:10.2514/6.2015-3433 2015

  33. [33]

    and Fischer D

    Fuchs, M. and Fischer D. and Mockett, C. and Kramer, F. and Knacke, T. and Sesterhenn, J. and Thiele, F. , booktitle =. Assessment of different meshing strategies for low. doi:https://doi.org/10.2514/6.2017-3020 , year =

    work page doi:10.2514/6.2017-3020 2017

  34. [34]

    and Mockett, C

    Fuchs, M. and Mockett, C. and Sesterhenn, J. and Thiele, F. , title =. Progress in Hybrid RANS-LES Modelling, Notes on Numerical Fluid Mechanics and Multidisciplinary Design , editor =. 2018 , publisher =

    work page 2018

  35. [35]

    and Fliessbach, L

    Fuchs, M. and Fliessbach, L. and Mockett, C. and Kramer, F. and Knacke, T. and Thiele, F. , booktitle =. Aeroacoustic prediction of a three-element high-lift airfoil using a grey-area enhanced. doi:https://doi.org/10.2514/6.2019-2462 , year =

    work page doi:10.2514/6.2019-2462 2019

  36. [36]

    and Mockett, C

    Fuchs, M. and Mockett, C. and Sesterhenn, J. and Thiele, F. , booktitle =. The grey-area improved -. 2020 , publisher =

    work page 2020

  37. [37]

    Proceedings of the 28th AIAA/CEAS Aeroacoustics Conference, Southampton, UK, AIAA 2022-2860 , doi =

    Two computational studies of a flatback airfoil using non-zonal and embedded scale-resolving turbulence modelling approaches , author =. Proceedings of the 28th AIAA/CEAS Aeroacoustics Conference, Southampton, UK, AIAA 2022-2860 , doi =

    work page 2022

  38. [38]

    2021 , journal =

    Hupertz, Burkhard and Chalupa, Karel and Krueger, Lothar and Howard, Kevin and Glueck, Hans-Dieter and Lewington, Neil and Chang, Jin-Hyuck and Shin, Yong-su , number =. 2021 , journal =

    work page 2021

  39. [39]

    arXiv preprint arXiv:2504.06699 , year =

    Benchmarking Convolutional Neural Network and Graph Neural Network based Surrogate Models on a Real-World Car External Aerodynamics Dataset , author =. arXiv preprint arXiv:2504.06699 , year =

    work page arXiv

  40. [40]

    , title =

    Knacke, T. , title =. Accurate and efficient aeroacoustic prediction approaches for airframe noise , series =

    work page

  41. [41]

    Proceedings of ETMM8, Marseille , year =

    Detection of initial transient and estimation of statistical error in time-resolved turbulent flow data , author =. Proceedings of ETMM8, Marseille , year =

    work page

  42. [42]

    and Fuchs, M

    Mockett, C. and Fuchs, M. and Garbaruk, A. and Shur, M. and Spalart, P. and Strelets, M. and Thiele, F. and Travin, A. , title =. Progress in Hybrid RANS-LES Modelling, Notes on Numerical Fluid Mechanics and Multidisciplinary Design , editor =. 2015 , publisher =

    work page 2015

  43. [43]

    and Fuchs, M

    Mockett, C. and Fuchs, M. and Knacke, T. and Kramer, F. and Michel, U. and Steger, M. and Thiele, F. , title =. Progress in Hybrid RANS-LES Modelling, Notes on Numerical Fluid Mechanics and Multidisciplinary Design , editor =. 2019 , publisher =

    work page 2019

  44. [44]

    and Knacke, T

    Mockett, C. and Knacke, T. and Sch\". A statistical approach for optimising. 3rd High-Fidelity Industrial LES/DNS Symposium , year =

    work page

  45. [45]

    and Brethouwer, G

    Montecchia, M. and Brethouwer, G. and Wallin, S. and Johansson, A. and Knacke, T. , journal =. Improving. 2019 , publisher =

    work page 2019

  46. [46]

    , title =

    Patankar, S. , title =. 1980 , address =

    work page 1980

  47. [47]

    AIAA Journal , volume =

    Numerical study of the turbulent flow past an airfoil with trailing edge separation , author =. AIAA Journal , volume =

    work page

  48. [48]

    International Journal of Heat and Fluid Flow , volume=

    Strategies for turbulence modelling and simulations , author=. International Journal of Heat and Fluid Flow , volume=. 2000 , publisher=

    work page 2000

  49. [49]

    Spalart, P. R. and Deck, S. and Shur, M. L. and Squires, K. D. and Strelets, M. Kh. and Travin, A. , number =. 2006 , journal =. doi:10.1007/s00162-006-0015-0 , issn =

    work page doi:10.1007/s00162-006-0015-0 2006

  50. [50]

    SAE International Journal of Advances and Current Practices in Mobility , volume =

    Pad correction estimation around 5 belt wind tunnel wheel belts using pressure tap measurement and mathematical pressure distribution model , author =. SAE International Journal of Advances and Current Practices in Mobility , volume =

    work page

  51. [51]

    G. Br\`. Large-eddy simulations of co-annular turbulent jet using a

    work page

  52. [52]

    Clark and Konrad Goc and Neil Ashton and Utkarsh Ayachit and Lukas Mosimann , title =

    Liam Heidt and Christopher Ivey and Sanjeeb Bose and Rahul Agrawal and Adam M. Clark and Konrad Goc and Neil Ashton and Utkarsh Ayachit and Lukas Mosimann , title =. Submitted to AIAA SciTech Forum , year=

    work page

  53. [53]

    2025 , eprint=

    BlendedNet++: A Large-Scale Blended Wing Body Aerodynamics Dataset and Benchmark , author=. 2025 , eprint=

    work page 2025

  54. [54]

    2025 , eprint=

    Fluid Intelligence: A Forward Look on AI Foundation Models in Computational Fluid Dynamics , author=. 2025 , eprint=

    work page 2025

  55. [55]

    2025 , eprint=

    ONERA's CRM WBPN database for machine learning activities, related regression challenge and first results , author=. 2025 , eprint=

    work page 2025

  56. [56]

    Brodersen and Stefan Keye and Kelly R

    Ed Tinoco and Olaf P. Brodersen and Stefan Keye and Kelly R. Laflin and John C. Vassberg and Ben Rider and Richard A. Wahls and Joseph H. Morrison and Brent. W. Pomeroy and David Hue and Mitsuhiro Murayama , title =. AIAA Aviation Forum , chapter =. 2023 , publisher =. doi:10.2514/6.2023-3492 , URL =

    work page doi:10.2514/6.2023-3492 2023

  57. [57]

    2025 , eprint=

    Geometry Aware Operator Transformer as an Efficient and Accurate Neural Surrogate for PDEs on Arbitrary Domains , author=. 2025 , eprint=

    work page 2025

  58. [58]

    2025 , eprint=

    AB-UPT for Automotive and Aerospace Applications , author=. 2025 , eprint=

    work page 2025

  59. [59]

    Wissink and Jason Cornelius , title =

    Philipp Bekemeyer and Nathan Hariharan and Andrew M. Wissink and Jason Cornelius , title =. AIAA SciTech Forum , chapter =. 2025 , doi =. https://arc.aiaa.org/doi/pdf/10.2514/6.2025-0036 , abstract =

    work page doi:10.2514/6.2025-0036 2025

  60. [60]

    Aagren and Darrell Nieves Lugo , title =

    Jason Cornelius and Nicholas Peters and Tove S. Aagren and Darrell Nieves Lugo , title =. AIAA SciTech Forum , chapter =. 2025 , doi =. https://arc.aiaa.org/doi/pdf/10.2514/6.2025-0038 , abstract =

    work page doi:10.2514/6.2025-0038 2025

  61. [61]

    Kaminsky and Alec M

    Andrew L. Kaminsky and Alec M. House and Louis Jensen and Matthew Liu and William Chapman and Alessandro P. Brown and Andrew M. Wissink and Nathan S. Hariharan and David McDaniel , title =. AIAA SciTech Forum , chapter =. 2025 , doi =

    work page 2025

  62. [62]

    Jude and Jay Sitaraman and Nathan S

    Jennifer Abras and Shirzad Hosseinverdi and Dylan P. Jude and Jay Sitaraman and Nathan S. Hariharan , title =. AIAA SciTech Forum , chapter =. 2025 , doi =

    work page 2025

  63. [63]

    AIAA SciTech Forum , chapter =

    Rahul Agrawal and Sanjeeb Bose and Parviz Moin , title =. AIAA SciTech Forum , chapter =. 2025 , doi =

    work page 2025

  64. [64]

    AIAA Aviation Forum and Ascend , pages=

    Testing the Full-Span High-Lift Common Research Model at the ONERA F1 Pressurized Low-Speed Wind Tunnel , author=. AIAA Aviation Forum and Ascend , pages=

    work page

  65. [65]

    Journal of Fluid Mechanics , volume=

    Weakly nonlinear behaviour of transonic buffet on airfoils , author=. Journal of Fluid Mechanics , volume=. 2024 , publisher=

    work page 2024

  66. [66]

    Global structure of buffeting flow on transonic airfoils , author=. IUTAM Symposium on Unsteady Separated Flows and their Control: Proceedings of the IUTAM Symposium “Unsteady Separated Flows and their Control “, Corfu, Greece, 18--22 June 2007 , pages=. 2009 , organization=

    work page 2007

  67. [67]

    and Haberland, Matt and Reddy, Tyler and Cournapeau, David and Burovski, Evgeni and Peterson, Pearu and Weckesser, Warren and Bright, Jonathan and

    Virtanen, Pauli and Gommers, Ralf and Oliphant, Travis E. and Haberland, Matt and Reddy, Tyler and Cournapeau, David and Burovski, Evgeni and Peterson, Pearu and Weckesser, Warren and Bright, Jonathan and. Nature Methods , year =

    work page

  68. [68]

    ONERA’s CRM WBPN database for machine learning activities, related regression challenge and first results , journal =

    Jacques Peter and Quentin Bennehard and Sébastien Heib and Jean-Luc Hantrais-Gervois and Frédéric Moëns , keywords =. ONERA’s CRM WBPN database for machine learning activities, related regression challenge and first results , journal =. 2025 , issn =. doi:https://doi.org/10.1016/j.compfluid.2025.106838 , url =

    work page doi:10.1016/j.compfluid.2025.106838 2025

  69. [69]

    SHIFT-Wing: High-Fidelity Computational Fluid Dynamics Dataset for Transonic Aerospace External Aerodynamics , year =

    Luminary Cloud. SHIFT-Wing: High-Fidelity Computational Fluid Dynamics Dataset for Transonic Aerospace External Aerodynamics , year =

    work page

  70. [70]

    AIAA Journal , volume=

    Reverse Flow Radius in Vortex Chambers , author=. AIAA Journal , volume=. 1986 , publisher=

    work page 1986

  71. [71]

    Aviation Week & Space Technology , volume=

    Planetary Flight Surge Faces Budget Realities , author=. Aviation Week & Space Technology , volume=

    work page

  72. [72]

    Space News , volume=

    NASA Considers Switch to Delta 2 , author=. Space News , volume=

    work page

  73. [73]

    Computational Methods for Fluid Flow , edition=

    Peyret, Roger and Taylor, Thomas D , year=. Computational Methods for Fluid Flow , edition=

    work page

  74. [74]

    1984 , publisher=

    Aerothermodynamics of Gas Turbine and Rocket Propulsion , series=. 1984 , publisher=

    work page 1984

  75. [75]

    Teleoperation and Robotics in Space , series=

    Techniques for Collision Prevention, Impact Stability, and Force Control by Space Manipulators , author=. Teleoperation and Robotics in Space , series=. 1994 , publisher=

    work page 1994

  76. [76]

    AIAA Guidance, Navigation, and Control Conference , series=

    Spacecraft Thermal Control, Design, and Operation , author=. AIAA Guidance, Navigation, and Control Conference , series=. 1989 , pages=

    work page 1989

  77. [77]

    Fluid Mechanics Proceedings , editor=

    work page

  78. [78]

    AIAA Paper 2016--3690 , year=

    Nonequilibrium Radiation for Earth Entry , author=. AIAA Paper 2016--3690 , year=

    work page 2016

  79. [79]

    AIAA Journal , volume=

    Improvements to the quadratic constitutive relation based on NASA juncture flow data , author=. AIAA Journal , volume=. 2020 , publisher=

    work page 2020

  80. [80]

    Subgrid-scale stress modelling based on the square of the velocity gradient tensor , volume =

    Nicoud, Franck and Ducros, Fr\'. Subgrid-scale stress modelling based on the square of the velocity gradient tensor , volume =. 1999 , journal =

    work page 1999

Showing first 80 references.