Accelerating Eulerian Fluid Simulation With Convolutional Networks

07/13/2016
by   Jonathan Tompson, et al.
0

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. Our method solves the incompressible Euler equations using the standard operator splitting method, in which a large sparse linear system with many free parameters must be solved. We use a Convolutional Network with a highly tailored architecture, trained using a novel unsupervised learning framework to solve the linear system. We present real-time 2D and 3D simulations that outperform recently proposed data-driven methods; the obtained results are realistic and show good generalization properties.

READ FULL TEXT

page 6

page 7

page 8

research
12/13/2021

Stacked Generative Machine Learning Models for Fast Approximations of Steady-State Navier-Stokes Equations

Computational fluid dynamics (CFD) simulations are broadly applied in en...
research
05/22/2022

A Deep Gradient Correction Method for Iteratively Solving Linear Systems

We present a novel deep learning approach to approximate the solution of...
research
12/22/2020

Fast Fluid Simulations in 3D with Physics-Informed Deep Learning

Physically plausible fluid simulations play an important role in modern ...
research
01/28/2021

GPU Optimization for High-Quality Kinetic Fluid Simulation

Fluid simulations are often performed using the incompressible Navier-St...
research
04/29/2019

Constraint-Aware Neural Networks for Riemann Problems

Neural networks are increasingly used in complex (data-driven) simulatio...
research
08/22/2023

Evaluation of Deep Neural Operator Models toward Ocean Forecasting

Data-driven, deep-learning modeling frameworks have been recently develo...
research
07/23/2021

Learning the structure of wind: A data-driven nonlocal turbulence model for the atmospheric boundary layer

We develop a novel data-driven approach to modeling the atmospheric boun...

Please sign up or login with your details

Forgot password? Click here to reset