Geometric Deep Learning for Volumetric Computational Fluid Dynamics

This master thesis explores ways to apply geometric deep learning to the field of numerical simulations with an emphasis on the Navier-Stokes equations. With the recent success of Deep Learning, there should be room for experimentation also in the field of fluid simulations. Here we lead such an experiment. We propose an end-to-end differentiable architecture that allow object-to-mesh predictions of fluid simulations. We provide a comparison with a baseline and visual results on three different datasets: airfoils, backward facing steps and winged drones.


Advisor(s):
Fua, Pascal
Baqué, Pierre Bruno
Defferrard, Michaël
Fleuret, François
Formaggia, Luca
Year:
Jun 21 2019
Keywords:
Note:
For the slides, use pdfpc reader for visualizing correctly the videos.
Additional link:
Laboratories:




 Record created 2019-06-23, last modified 2019-07-09

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)