GA-Field: Geometry-Aware Vehicle Aerodynamic Field Prediction

2026-02-24

AI Summary

High-fidelity CFD simulations are computationally prohibitive for rapid aerodynamic field prediction in vehicle design, while existing learning-based approaches struggle to simultaneously capture long-range geometric dependencies and fine-grained local flow structures. To address this challenge, this work proposes a geometry-aware aerodynamic field prediction network that integrates multi-stage global geometric embeddings with a coarse-to-fine field reconstruction strategy, effectively balancing geometric consistency and localized sharp flow features. The method achieves new state-of-the-art performance on the ShapeNet-Car and DrivAerNet++ benchmarks for predicting surface pressure, wall shear stress, and 3D velocity fields, and demonstrates strong generalization across diverse vehicle geometries.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Search and Optimization: Learning to Search
• Machine Learning: Learning with Manifolds

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Accurate aerodynamic field prediction is crucial for vehicle drag evaluation, but the computational cost of high-fidelity CFD hinders its use in iterative design workflows. While learning-based methods enable fast and scalable inference, accurately aerodynamic fields modeling remains challenging, as it demands capturing both long-range geometric effects and fine-scale flow structures. Existing approaches typically encode geometry only once at the input and formulate prediction as a one-shot mapping, which often leads to diluted global shape awareness and insufficient resolution of sharp local flow variations. To address these issues, we propose GA-Field, a Geometry-Aware Field prediction network that introduces two complementary design components: (i) a global geometry injection mechanism that repeatedly conditions the network on a compact 3D geometry embedding at multiple stages to preserve long-range geometric consistency, and (ii) a coarse-to-fine field refinement strategy to recover sharp local aerodynamic details. GA-Field achieves new state-of-the-art performance on ShapeNet-Car and the large-scale DrivAerNet++ benchmark for surface pressure, wall shear stress, and 3D velocity prediction tasks, while exhibiting strong out-of-distribution generalization across different vehicle categories.

Problem

• aerodynamic field prediction
• geometry-aware modeling
• long-range geometric effects
• local flow structures
• vehicle drag evaluation

Innovation

• Geometry-Aware
• Aerodynamic Field Prediction
• Global Geometry Injection
• Coarse-to-Fine Refinement
• CFD Surrogate