Harnessing Machine Learning for Computational Fluid Dynamics in Airfoil Design
![hero](illustration_airfoil.png)
# Competition Overview
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.
To do so, the competition rely on our recently proposed benchmarking framework called LIPS (“Learning Industrial Physical Systems”) (opens new window). This framework will be used to evaluate candidate solutions provided by the participants regarding significant criteria organized into 3 categories namely: ML related criteria, Physical Compliance criteria and OOD generalization criteria. For each submitted solution, a global score will be computed based on the aforementioned criteria to rank it.
Competition proposal paper https://openreview.net/pdf?id=5Vw8xOVVkS (opens new window)
More details on LIPS : LIPS paper (opens new window)
LIPS : Github repository (opens new window)
More details on the Airfoil design DataSet : AirfRANS paper (opens new window)
More details about NVIDIA SDKs & RTX GPUs resources
# Protocol
The competition will be hosted by the Codabench platform (opens new window). Participants will have to:
create an account;
download a starting kit to prepare their submission;
upload on the Codabench platform their trained ML models. Then, the platform will use the LIPS framework to compute scores for the submission. The score will be published on the Codabench competition page and the participant will also have access to an additional page with detailed metrics.
# Who can take part
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.
# How to join the challenge
# Instructions:
- Go on the codabench page of the challenge: CODABENCH (opens new window)
- Go to “My sumbissions” tab.
- Click the register button.
For more information, read our complete getting started guide.
# Prizes
- 🏆 1st Prize : 4000 €
- 🥈 2nd Prize : 2000 €
- 🥉 3rd Prize : 1000 €
Special prizes: Best student solution : 1000 €
# Timeline
- Competition kick-off July 1st
- Warmup phase July 1st - August 4th
- Development phase August 5th - October 14th
- Final phase October 15th - October 31st
- Announcement of winners : event to be planned.
# Competition phases
# This competition will run over 3 phases:
- Warm-up phase (5 weeks): participants can get familiar with provided material and the competition platform, make their first submissions and provide feedback to organizers. Based on this feedback, organizers can adjust and improve the competition for the next phase.
- Development phase (10 weeks): participants will develop their solutions and will be able to test their already trained models against a provided validation dataset. They can also have access continuously to the global score corresponding the submitted solution.
- Final phase (2 week): organizers prepare the final ranking and official results. A dedicated event will be organized to announce the winners.
# Organizer
# Organization Team:
- Mouadh Yagoubi (IRT SystemX)
- David Danan (IRT SystemX)
- Milad Leyli-Abadi (IRT SystemX)
- Jocelyn Ahmed Mazari (Ansys, SimAI team)
- Florent Bonnet (Institut des systèmes intelligents et robotique (ISIR), Sorbonne Université)
- Jean-Patrick Brunet (IRT SystemX)
- Maroua Gmati (IRT SystemX)
- Asma Farjallah (NVIDIA)
- Paola Cinnella (Sorbonne Université)
- Patrick Gallinari (Sorbonne Université, Criteo AI Lab)
- Marc Schoenauer (Inria)
# Contact us
Email address: ml4cfd-competition@irt-systemx.fr
Competition Discord channel: https://discord.gg/fufhRdTw2k (opens new window)
Competition website: https://ml-for-physical-simulation-challenge.irt-systemx.fr/airfoil-challenge-neurips2024/ (opens new window)