Video World Models · 2026-11-04

Ground-Wing: A Parametric 3D Wing-in-Ground-Effect Dataset for Benchmarking Neural Surrogate Models

Andrea Cenzato, Lukas Karch, Andre Luckow, Yoran Pichon, Francesco Pasqua, Abouzar Ghasemi, Rishikesh Ranade, Ira Shokar, Julia Kowalski

arXiv:2611.04571PDF

AI-assisted summary based on the paper. Consult the linked source for methods and limitations. Benchmark numbers appear after editor verification.

TL;DR

Ground-Wing provides a CFD dataset of 3D wing-in-ground-effect aerodynamics for benchmarking neural surrogate models. It includes 770 RANS simulations of 194 parametrized wing configurations spanning 27 airfoil variants and four ground distances, and evaluates six neural surrogate architectures on predicting surface pressure coefficient and wall shear stress fields, from which lift and drag are recovered. The dataset is available on Hugging Face.

Why it matters

The authors report that ground effect (near-wall flow between a wing and a ground plane) is absent from other wing/airfoil datasets, and that this regime introduces nonlinearities relevant to motorsport front-wing design. The dataset supplies a controlled parameterized geometry family and benchmark splits/metrics for comparing surrogate models on both integral aerodynamic coefficients and surface fields, including generalization to unseen airfoil profiles and aerodynamic extremes.

Method

  • Generate 194 wing geometries from a parametrized design space (wing planform and incidence/proximity variables plus a discrete airfoil profile parameter) and run RANS CFD simulations.
  • Benchmark six surrogate architectures (DoMINO, X-MeshGraphNet, AB-UPT, GeoTransolver, GAOT, AeroJEPA) to predict surface pressure coefficient and wall shear stress; recover integral drag/lift coefficients from predicted surface fields.
  • Use stratified, drag-outlier, and interpolated splits, and report coefficient accuracy plus surface field accuracy to assess generalization.
Abstract (from arXiv)

This paper presents a CFD dataset of a highly parametrized 3D wing operating in ground effect, designed for benchmarking neural surrogate models for aerodynamic prediction, using a wing shape and flow conditions typically encountered in motorsport applications. The dataset comprises 770 RANS simulations of 194 unique wing configurations, sampled across 27 airfoil profile variants and 4 distances from the ground, spanning variations in wing sweep, chord, taper, angle of attack, and tip twist. Six neural network architectures representing distinct paradigms --- convolutional (DoMINO), graph-based (X-MeshGraphNet), transformer-based (AB-UPT, GeoTransolver, GAOT), and JEPA-based (AeroJEPA) --- are evaluated on their ability to predict surface pressure coefficient and wall shear stress distributions, from which integral drag and lift coefficients are recovered. The dataset is intended to be used as a challenging benchmark for surrogate CFD models, due to the uniqueness of the ground effect being absent from other wing and airfoil datasets. The dataset is available for download at https://huggingface.co/datasets/andreacenzato/Ground-Wing

Related papers

Publication record

Bibliographic evidence describes where and when a record appeared. It does not validate scientific claims.

First announced by arXiv: 2026-11-04 · Indexed by Pub-AI: 2026-11-04 UTC

preprint

Ground-Wing: A Parametric 3D Wing-in-Ground-Effect Dataset for Benchmarking Neural Surrogate Models

Andrea Cenzato, Lukas Karch, Andre Luckow, Yoran Pichon, Francesco Pasqua, Abouzar Ghasemi, Rishikesh Ranade, Ira Shokar, Julia Kowalski

First announced by arXiv: 2026-11-04 · Original record ↗

arxiv
2611.04571
Explicit source versions (1)
  • v1 · Date not supplied
  1. Preprint available

    Source date: 2026-11-04 · First detected: 2026-11-04 UTC · Historical baseline

    Source evidence (1)
    • Official evidence ↗ · RSS guid=oai:arXiv.org:2611.04571v1; arxiv:announce_type=new; item pubDate (official metadata)
Abstract · arxiv

This paper presents a CFD dataset of a highly parametrized 3D wing operating in ground effect, designed for benchmarking neural surrogate models for aerodynamic prediction, using a wing shape and flow conditions typically encountered in motorsport applications. The dataset comprises 770 RANS simulations of 194 unique wing configurations, sampled across 27 airfoil profile variants and 4 distances from the ground, spanning variations in wing sweep, chord, taper, angle of attack, and tip twist. Six neural network architectures representing distinct paradigms --- convolutional (DoMINO), graph-based (X-MeshGraphNet), transformer-based (AB-UPT, GeoTransolver, GAOT), and JEPA-based (AeroJEPA) --- are evaluated on their ability to predict surface pressure coefficient and wall shear stress distributions, from which integral drag and lift coefficients are recovered. The dataset is intended to be used as a challenging benchmark for surrogate CFD models, due to the uniqueness of the ground effect being absent from other wing and airfoil datasets.