3 papers
cs.LG2026
Neural Field Ensembles for Aerodynamic Surface Prediction: Winning Solution to the ONERA CRM Wall Distribution 2025 Challenge
Lionel Salesses, Caroline Sainvitu, Tariq Benamara
Machine-learning surrogate models offer a promising alternative to high-fidelity Computational Fluid Dynamics (CFD) simulations for aerodynamic analysis and design. However, constr…
cs.LG2026
Stable Long-Horizon Spatiotemporal Prediction on Meshes Using Latent Multiscale Recurrent Graph Neural Networks
Lionel Salesses, Larbi Arbaoui, Tariq Benamara +2
Accurate long-horizon prediction of spatiotemporal fields on complex geometries is a fundamental challenge in scientific machine learning, with applications such as additive manufa…
physics.flu-dyn2025
Reduced order modeling of the unsteady pressure on turbine rotor blades using deep learning
Dominique Joachim, Salesses Lionel, Thomas Jean-François +4
In transonic turbine stages, complex interactions between trailing edge shocks from nozzle guide vanes and rotor blades generate unsteady wall pressure fields, impacting rotor aero…