Research questionHow can aerodynamic surrogate models predict vehicle pressure and wall shear stress without losing global flow or local geometric effects?High-fidelity CFD can make early-stage vehicle design exploration too costly. A useful surface-field predictor must represent both long-range aerodynamic coupling and geometry-induced local variation. Latest papersRecent research connected to this question, newest first.A Geometry-Aware Triplane Field Network for Vehicle Aerodynamic PredictionThe source studies GTF-Net, which builds triplane features from sampled surface points, combines AFNO spectral mixing with CNN refinement, and adds vehicle-aligned coordinates, normal-projection features, and a curvature proxy at query time. It reports comparisons with Transolver, GINO, and TripNet, plus relative L2 errors and ablations; the evidence is limited to the described experiments.research paper · Sep 2, 2026