EAGLE: Large-Scale Learning of Turbulent Fluid Dynamics with Mesh Transformers - Archive ouverte HAL Access content directly
Conference Papers Year : 2023

EAGLE: Large-Scale Learning of Turbulent Fluid Dynamics with Mesh Transformers


Estimating fluid dynamics is classically done through the simulation and integration of numerical models solving the Navier-Stokes equations, which is computationally complex and time-consuming even on high-end hardware. This is a notoriously hard problem to solve, which has recently been addressed with machine learning, in particular graph neural networks (GNN) and variants trained and evaluated on datasets of static objects in static scenes with fixed geometry. We attempt to go beyond existing work in complexity and introduce a new model, method and benchmark. We propose EAGLE, a large-scale dataset of ∼1.1 million 2D meshes resulting from simulations of unsteady fluid dynamics caused by a moving flow source interacting with nonlinear scene structure, comprised of 600 different scenes of three different types. To perform future forecasting of pressure and velocity on the challenging EAGLE dataset, we introduce a new mesh transformer. It leverages node clustering, graph pooling and global attention to learn long-range dependencies between spatially distant data points without needing a large number of iterations, as existing GNN methods do. We show that our transformer outperforms state-of-the-art performance on, both, existing synthetic and real datasets and on EAGLE. Finally, we highlight that our approach learns to attend to airflow, integrating complex information in a single iteration.
Fichier principal
Vignette du fichier
ICLR23_Eagle.pdf (28.31 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03992436 , version 1 (16-02-2023)
hal-03992436 , version 2 (17-03-2023)


  • HAL Id : hal-03992436 , version 2


Steeven Janny, Aurélien Beneteau, Madiha Nadri, Julie Digne, Nicolas Thome, et al.. EAGLE: Large-Scale Learning of Turbulent Fluid Dynamics with Mesh Transformers. International Conference on Learning Representation, May 2023, Kigali, Rwanda. ⟨hal-03992436v2⟩
167 View
21 Download


Gmail Mastodon Facebook X LinkedIn More