ERE Seminar: Jonathan Tompson, Google — Accelerating Eulerian Fluid Simulation With Convolutional Networks

Monday, February 26, 2018

12:30 pm

Room 104, Green Earth Sciences Building, 367 Panama Street, Stanford Map

Sponsored by:
Energy Resources Engineering

Accelerating Eulerian Fluid Simulation With Convolutional Networks

Jonathan Tompson
Senior Research Scientist
Google

Efficient simulation of the Navier-Stokes equations for fluid flow is a long standing problem in applied mathematics, for which state-of-the-art methods require large compute resources. In this work, we propose a data-driven approach that leverages the approximation power of deep-learning with the precision of standard solvers to obtain fast and highly realistic simulations. I will discuss our proposed method in some detail as well as it's limitations and future work.

When:
Monday, February 26, 2018
12:30 pm – 1:30 pm
Where:
Room 104, Green Earth Sciences Building, 367 Panama Street, Stanford Map
Tags:

Environment Engineering Seminar Science 

Audience:
General Public, Faculty/Staff, Students, Alumni/Friends, Members
Contact:
650.725.9835, jpcastro@stanford.edu
More info:
Visit this website