Reproduce “Ground-Wing: A Parametric 3D Wing-in-Ground-Effect Dataset for Benchmarking Neural Surrogate Models” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Andrea Cenzato, Lukas Karch, Andre Luckow, Yoran Pichon, Francesco Pasqua, Abouzar Ghasemi, Rishikesh Ranade, Ira Shokar and 1 more
The authors introduce Ground-Wing, a benchmark for testing aerodynamic surrogates when wing ground clearance varies. It contains 770 incompressible flow simulations across 194 single-element wing geometries and four ride heights, and evaluates six models predicting pressure and shear. On familiar held-out profiles, AB-UPT’s lift and drag errors are 0.85% and 0.89%; unseen profiles increase them to 1.56% and 4.51%.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.