NeurIPS 2024 ML4CFD Competition: Harnessing Machine Learning for Computational Fluid Dynamics in Airfoil Design

TL;DR

The NeurIPS 2024 ML4CFD Competition aims to advance machine learning methods for efficient and accurate airfoil design simulations, using a unified evaluation framework to promote innovation in physics-informed ML models.

Contribution

This competition introduces a novel benchmark and evaluation framework for ML-based surrogate models in CFD, focusing on airfoil design and balancing accuracy with computational efficiency.

Findings

First ML-driven surrogate methods for airfoil CFD evaluated

Framework assesses accuracy, efficiency, and physical consistency

Promotes development of physics-informed ML models for industry use

Abstract

The integration of machine learning (ML) techniques for addressing intricate physics problems is increasingly recognized as a promising avenue for expediting simulations. However, assessing ML-derived physical models poses a significant challenge for their adoption within industrial contexts. This competition is designed to promote the development of innovative ML approaches for tackling physical challenges, leveraging our recently introduced unified evaluation framework known as Learning Industrial Physical Simulations (LIPS). Building upon the preliminary edition held from November 2023 to March 2024, this iteration centers on a task fundamental to a well-established physical application: airfoil design simulation, utilizing our proposed AirfRANS dataset. The competition evaluates solutions based on various criteria encompassing ML accuracy, computational efficiency, Out-Of-Distribution performance, and adherence to physical principles. Notably, this competition represents a pioneering effort in exploring ML-driven surrogate methods aimed at optimizing the trade-off between computational efficiency and accuracy in physical simulations. Hosted on the Codabench platform, the competition offers online training and evaluation for all participating solutions.