Machine Learning for Physical Simulation Challenge

TAILOR is participating in the organisation of a new Challenge! The Challenge is organized by IRT SystemX and the RTE company, with Marc Schoenauer and Sébastien Treguer from Inria contributing to the organization with other researchers, and will be TAILOR representatives for this initiative.

This competition aims at promoting the use of ML based surrogate models to solve physical problems, through a task addressing a CFD usecase: Airfoil design.


The ML for Physical Simulation Challenge aims at promoting the use of ML based surrogate models to solve physicalproblems, through a task addressing a recently published dataset called AirfRANS related to airfoil design (CFD simulation). It will address the challenge of improving baseline solutions of the Airfoils design use case by building ML-based surrogate models. The overall aim is to improve tradeoff between accuracy of obtained solutions and related computational cost, while considering Out-of-Distribution (OOD) generalization and respect of some basic physical constraints.

Who can participate

Anyone interested in solving physical problems using ML technics is encouraged to participate in this competition. It could be a great opportunity to gather people from ML and the Scientific computing communities to leverage synergies between these two domains.


The competition will officially start on November 16th, and the schedule is the following:

  • Competition kick-off November 16th
  • Warmup phase November 16th – December 13th
  • Development phase December 14th – February 15th
  • Final phase February 16th – February 22nd
  • Announcement of winners : event to be planned between 22nd and 29th February (to be confirmed)

If you are interested in joining the challenge and you want to know more about it, visit the webpage: