Accelerating eulerian fluid simulation with convolutional networks

Jonathan Tompson, Kristofer Schlachter, Pablo Sprechmann, Kenneth Perlin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Efficient simulation of the Navicr-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.

Original languageEnglish (US)
Title of host publication34th International Conference on Machine Learning, ICML 2017
PublisherInternational Machine Learning Society (IMLS)
Pages5258-5267
Number of pages10
Volume7
ISBN (Electronic)9781510855144
StatePublished - Jan 1 2017
Event34th International Conference on Machine Learning, ICML 2017 - Sydney, Australia
Duration: Aug 6 2017Aug 11 2017

Other

Other34th International Conference on Machine Learning, ICML 2017
CountryAustralia
CitySydney
Period8/6/178/11/17

Fingerprint

Linear systems
Unsupervised learning
Fluids
Euler equations
Flow of fluids
Deep learning

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Human-Computer Interaction
  • Software

Cite this

Tompson, J., Schlachter, K., Sprechmann, P., & Perlin, K. (2017). Accelerating eulerian fluid simulation with convolutional networks. In 34th International Conference on Machine Learning, ICML 2017 (Vol. 7, pp. 5258-5267). International Machine Learning Society (IMLS).

Accelerating eulerian fluid simulation with convolutional networks. / Tompson, Jonathan; Schlachter, Kristofer; Sprechmann, Pablo; Perlin, Kenneth.

34th International Conference on Machine Learning, ICML 2017. Vol. 7 International Machine Learning Society (IMLS), 2017. p. 5258-5267.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Tompson, J, Schlachter, K, Sprechmann, P & Perlin, K 2017, Accelerating eulerian fluid simulation with convolutional networks. in 34th International Conference on Machine Learning, ICML 2017. vol. 7, International Machine Learning Society (IMLS), pp. 5258-5267, 34th International Conference on Machine Learning, ICML 2017, Sydney, Australia, 8/6/17.
Tompson J, Schlachter K, Sprechmann P, Perlin K. Accelerating eulerian fluid simulation with convolutional networks. In 34th International Conference on Machine Learning, ICML 2017. Vol. 7. International Machine Learning Society (IMLS). 2017. p. 5258-5267
Tompson, Jonathan ; Schlachter, Kristofer ; Sprechmann, Pablo ; Perlin, Kenneth. / Accelerating eulerian fluid simulation with convolutional networks. 34th International Conference on Machine Learning, ICML 2017. Vol. 7 International Machine Learning Society (IMLS), 2017. pp. 5258-5267
@inproceedings{c1406a9c81e84087ac03ce3dcd89498b,
title = "Accelerating eulerian fluid simulation with convolutional networks",
abstract = "Efficient simulation of the Navicr-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.",
author = "Jonathan Tompson and Kristofer Schlachter and Pablo Sprechmann and Kenneth Perlin",
year = "2017",
month = "1",
day = "1",
language = "English (US)",
volume = "7",
pages = "5258--5267",
booktitle = "34th International Conference on Machine Learning, ICML 2017",
publisher = "International Machine Learning Society (IMLS)",

}

TY - GEN

T1 - Accelerating eulerian fluid simulation with convolutional networks

AU - Tompson, Jonathan

AU - Schlachter, Kristofer

AU - Sprechmann, Pablo

AU - Perlin, Kenneth

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Efficient simulation of the Navicr-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.

AB - Efficient simulation of the Navicr-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.

UR - http://www.scopus.com/inward/record.url?scp=85048468396&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048468396&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85048468396

VL - 7

SP - 5258

EP - 5267

BT - 34th International Conference on Machine Learning, ICML 2017

PB - International Machine Learning Society (IMLS)

ER -