A Benchmarking Framework for AI models in Automotive Aerodynamics
This work provides a standardized methodology for comparing AI models in automotive aerodynamics, aimed at researchers and industry professionals to accelerate development in the field, but it is incremental as it builds on existing frameworks and datasets.
The authors introduced a benchmarking framework within the NVIDIA PhysicsNeMo-CFD framework to systematically assess AI models for automotive aerodynamics predictions, evaluating three models on the DrivAerML dataset to enhance transparency and consistency in performance assessment.
In this paper, we introduce a benchmarking framework within the open-source NVIDIA PhysicsNeMo-CFD framework designed to systematically assess the accuracy, performance, scalability, and generalization capabilities of AI models for automotive aerodynamics predictions. The open extensible framework enables incorporation of a diverse set of metrics relevant to the Computer-Aided Engineering (CAE) community. By providing a standardized methodology for comparing AI models, the framework enhances transparency and consistency in performance assessment, with the overarching goal of improving the understanding and development of these models to accelerate research and innovation in the field. To demonstrate its utility, the framework includes evaluation of both surface and volumetric flow field predictions on three AI models: DoMINO, X-MeshGraphNet, and FIGConvNet using the DrivAerML dataset. It also includes guidelines for integrating additional models and datasets, making it extensible for physically consistent metrics. This benchmarking study aims to enable researchers and industry professionals in selecting, refining, and advancing AI-driven aerodynamic modeling approaches, ultimately fostering the development of more efficient, accurate, and interpretable solutions in automotive aerodynamics