SMART: Scalable Mesh-free Aerodynamic Simulations from Raw Geometries using a Transformer-based Surrogate Model

TL;DR

SMART introduces a mesh-free neural surrogate model that efficiently predicts physical quantities from raw point-cloud geometries, eliminating the need for computationally expensive mesh generation while maintaining high accuracy.

Contribution

The paper presents SMART, a novel transformer-based surrogate model that predicts physical fields directly from raw geometries without mesh input, improving efficiency and accuracy.

Findings

SMART outperforms mesh-based models in accuracy.

The model is scalable for industry-level simulations.

It effectively captures complex geometric and physical features.

Abstract

Machine learning-based surrogate models have emerged as more efficient alternatives to numerical solvers for physical simulations over complex geometries, such as car bodies. Many existing models incorporate the simulation mesh as an additional input, thereby reducing prediction errors. However, generating a simulation mesh for new geometries is computationally costly. In contrast, mesh-free methods, which do not rely on the simulation mesh, typically incur higher errors. Motivated by these considerations, we introduce SMART, a neural surrogate model that predicts physical quantities at arbitrary query locations using only a point-cloud representation of the geometry, without requiring access to the simulation mesh. The geometry and simulation parameters are encoded into a shared latent space that captures both structural and parametric characteristics of the physical field. A physics decoder then attends to the encoder's intermediate latent representations to map spatial queries to physical quantities. Through this cross-layer interaction, the model jointly updates latent geometric features and the evolving physical field. Extensive experiments show that SMART is competitive with and often outperforms existing methods that rely on the simulation mesh as input, demonstrating its capabilities for industry-level simulations.