ML4PhySim : Machine Learning for Physical Simulations Challenge (The airfoil design)
This addresses the need for reliable evaluation of ML models in industrial physical simulations, though it is incremental as it builds on existing frameworks.
The paper introduces a competition to develop machine learning techniques for physical simulations, specifically for airfoil design, using a unified evaluation framework to assess computational cost and accuracy trade-offs.
The use of machine learning (ML) techniques to solve complex physical problems has been considered recently as a promising approach. However, the evaluation of such learned physical models remains an important issue for industrial use. The aim of this competition is to encourage the development of new ML techniques to solve physical problems using a unified evaluation framework proposed recently, called Learning Industrial Physical Simulations (LIPS). We propose learning a task representing a well-known physical use case: the airfoil design simulation, using a dataset called AirfRANS. The global score calculated for each submitted solution is based on three main categories of criteria covering different aspects, namely: ML-related, Out-Of-Distribution, and physical compliance criteria. To the best of our knowledge, this is the first competition addressing the use of ML-based surrogate approaches to improve the trade-off computational cost/accuracy of physical simulation.The competition is hosted by the Codabench platform with online training and evaluation of all submitted solutions.