# Benchmarking Convolutional Neural Network and Graph Neural Network based Surrogate Models on a Real-World Car External Aerodynamics Dataset

arXiv: https://arxiv.org/abs/2504.06699 · HTML: https://mlsanity.com/paper/2504.06699/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 34 references that are in the map.
- First posted on arXiv 9 Apr 2025.

## Builds on (most cited first, 22 of 22)

- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [Learning to Simulate Complex Physics with Graph Networks](https://mlsanity.com/paper/2002.09405/) (2020)
- [Learning Mesh-Based Simulation with Graph Networks](https://mlsanity.com/paper/2010.03409/) (2020)
- [On the Variance of the Adaptive Learning Rate and Beyond](https://mlsanity.com/paper/1908.03265/) (2019)
- [Cyclical Learning Rates for Training Neural Networks](https://mlsanity.com/paper/1506.01186/) (2015)
- [Machine Learning for Fluid Mechanics](https://mlsanity.com/paper/1905.11075/) (2019)
- [Geometry-Informed Neural Operator for Large-Scale 3D PDEs](https://mlsanity.com/paper/2309.00583/) (2023)
- [Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations of Airfoil Flows](https://mlsanity.com/paper/1810.08217/) (2018)
- [Prediction of Aerodynamic Flow Fields Using Convolutional Neural Networks](https://mlsanity.com/paper/1905.13166/) (2019)
- [Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional Networks](https://mlsanity.com/paper/1803.02579/) (2018)
- [DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks](https://mlsanity.com/paper/2406.09624/) (2024)
- [Geodesic Convolutional Shape Optimization](https://mlsanity.com/paper/1802.04016/) (2018)
- [DrivAerNet: A Parametric Car Dataset for Data-Driven Aerodynamic Design and Prediction](https://mlsanity.com/paper/2403.08055/) (2024)
- [DoMINO: A Decomposable Multi-scale Iterative Neural Operator for Modeling Large Scale Engineering Simulations](https://mlsanity.com/paper/2501.13350/) (2025)
- [fVDB: A Deep-Learning Framework for Sparse, Large-Scale, and High-Performance Spatial Intelligence](https://mlsanity.com/paper/2407.01781/) (2024)
- [X-MeshGraphNet: Scalable Multi-Scale Graph Neural Networks for Physics Simulation](https://mlsanity.com/paper/2411.17164/) (2024)
- [Deep Learning for Real-Time Aerodynamic Evaluations of Arbitrary Vehicle Shapes](https://mlsanity.com/paper/2108.05798/) (2021)

## Built on by (most cited first, 3 of 3)

- [CarBench: A Comprehensive Benchmark for Neural Surrogates on High-Fidelity 3D Car Aerodynamics](https://mlsanity.com/paper/2512.07847/) (2025)
- [PMRT: A Training Recipe for Fast, 3D High-Resolution Aerodynamic Prediction](https://mlsanity.com/paper/2509.17182/) (2025)
- [HGPTrans: Hierarchical Graph-Pooling Transolver for Automotive Aerodynamic Drag Coefficient Prediction](https://mlsanity.com/paper/2609.31765/) (2026)

## Abstract (arXiv)

Aerodynamic optimization is crucial for developing eco-friendly, aerodynamic, and stylish cars, which requires close collaboration between aerodynamicists and stylists, a collaboration impaired by the time-consuming nature of aerodynamic simulations. Surrogate models offer a viable solution to reduce this overhead, but they are untested in real-world aerodynamic datasets. We present a comparative evaluation of two surrogate modeling approaches for predicting drag on a real-world dataset: a Convolutional Neural Network (CNN) model that uses a signed distance field as input and a commercial tool based on Graph Neural Networks (GNN) that directly processes a surface mesh. In contrast to previous studies based on datasets created from parameterized geometries, our dataset comprises 343 geometries derived from 32 baseline vehicle geometries across five distinct car projects, reflecting the diverse, free-form modifications encountered in the typical vehicle development process. Our results show that the CNN-based method achieves a mean absolute error of 2.3 drag counts, while the GNN-based method achieves 3.8. Both methods achieve approximately 77% accuracy in predicting the direction of drag change relative to the baseline geometry. While both methods effectively capture the broader trends between baseline groups (set of samples derived from a single baseline geometry), they struggle to varying extents in capturing the finer intra-baseline group variations. In summary, our findings suggest that aerodynamicists can effectively use both methods to predict drag in under two minutes, which is at least 600 times faster than performing a simulation. However, there remains room for improvement in capturing the finer details of the geometry.