DrivAerML: High-Fidelity Computational Fluid Dynamics Dataset for Road-Car External Aerodynamics

TL;DR

This paper introduces DrivAerML, a comprehensive open-source high-fidelity CFD dataset of 500 parametrically morphed road-car models, designed to facilitate machine learning applications in automotive aerodynamics.

Contribution

It provides the first large-scale, high-fidelity CFD dataset of complex automotive geometries, enabling ML research without proprietary data barriers.

Findings

Generated 500 high-fidelity CFD simulations of car variants

Published geometries and aerodynamic data in open-source formats

Established automated workflows for industrial-grade CFD data generation

Abstract

Machine Learning (ML) has the potential to revolutionise the field of automotive aerodynamics, enabling split-second flow predictions early in the design process. However, the lack of open-source training data for realistic road cars, using high-fidelity CFD methods, represents a barrier to their development. To address this, a high-fidelity open-source (CC-BY-SA) public dataset for automotive aerodynamics has been generated, based on 500 parametrically morphed variants of the widely-used DrivAer notchback generic vehicle. Mesh generation and scale-resolving CFD was executed using consistent and validated automatic workflows representative of the industrial state-of-the-art. Geometries and rich aerodynamic data are published in open-source formats. To our knowledge, this is the first large, public-domain dataset for complex automotive configurations generated using high-fidelity CFD.