Deep learning in turbulent convection networks

Enrico Fonda, Ambrish Pandey, Jörg Schumacher, Katepalli Sreenivasan

Research output: Contribution to journalArticle

Abstract

We explore heat transport properties of turbulent Rayleigh–Bénard convection in horizontally extended systems by using deep-learning algorithms that greatly reduce the number of degrees of freedom. Particular attention is paid to the slowly evolving turbulent superstructures—so called because they are larger in extent than the height of the convection layer—which appear as temporal patterns of ridges of hot upwelling and cold downwelling fluid, including defects where the ridges merge or end. The machine-learning algorithm trains a deep convolutional neural network (CNN) with U-shaped architecture, consisting of a contraction and a subsequent expansion branch, to reduce the complex 3D turbulent superstructure to a temporal planar network in the midplane of the layer. This results in a data compression by more than five orders of magnitude at the highest Rayleigh number, and its application yields a discrete transport network with dynamically varying defect points, including points of locally enhanced heat flux or “hot spots.” One conclusion is that the fraction of heat transport by the superstructure decreases as the Rayleigh number increases (although they might remain individually strong), correspondingly implying the increased importance of small-scale background turbulence.

Original languageEnglish (US)
Pages (from-to)8667-8672
Number of pages6
JournalProceedings of the National Academy of Sciences of the United States of America
Volume116
Issue number18
DOIs
StatePublished - Apr 30 2019

Fingerprint

Convection
Hot Temperature
Learning
Data Compression

Keywords

  • Machine learning
  • Temporal networks
  • Turbulent convection

ASJC Scopus subject areas

  • General

Cite this

Deep learning in turbulent convection networks. / Fonda, Enrico; Pandey, Ambrish; Schumacher, Jörg; Sreenivasan, Katepalli.

In: Proceedings of the National Academy of Sciences of the United States of America, Vol. 116, No. 18, 30.04.2019, p. 8667-8672.

Research output: Contribution to journalArticle

Fonda, Enrico ; Pandey, Ambrish ; Schumacher, Jörg ; Sreenivasan, Katepalli. / Deep learning in turbulent convection networks. In: Proceedings of the National Academy of Sciences of the United States of America. 2019 ; Vol. 116, No. 18. pp. 8667-8672.
@article{da0146aa31504f7aa6f1c66640fb11fa,
title = "Deep learning in turbulent convection networks",
abstract = "We explore heat transport properties of turbulent Rayleigh–B{\'e}nard convection in horizontally extended systems by using deep-learning algorithms that greatly reduce the number of degrees of freedom. Particular attention is paid to the slowly evolving turbulent superstructures—so called because they are larger in extent than the height of the convection layer—which appear as temporal patterns of ridges of hot upwelling and cold downwelling fluid, including defects where the ridges merge or end. The machine-learning algorithm trains a deep convolutional neural network (CNN) with U-shaped architecture, consisting of a contraction and a subsequent expansion branch, to reduce the complex 3D turbulent superstructure to a temporal planar network in the midplane of the layer. This results in a data compression by more than five orders of magnitude at the highest Rayleigh number, and its application yields a discrete transport network with dynamically varying defect points, including points of locally enhanced heat flux or “hot spots.” One conclusion is that the fraction of heat transport by the superstructure decreases as the Rayleigh number increases (although they might remain individually strong), correspondingly implying the increased importance of small-scale background turbulence.",
keywords = "Machine learning, Temporal networks, Turbulent convection",
author = "Enrico Fonda and Ambrish Pandey and J{\"o}rg Schumacher and Katepalli Sreenivasan",
year = "2019",
month = "4",
day = "30",
doi = "10.1073/pnas.1900358116",
language = "English (US)",
volume = "116",
pages = "8667--8672",
journal = "Proceedings of the National Academy of Sciences of the United States of America",
issn = "0027-8424",
number = "18",

}

TY - JOUR

T1 - Deep learning in turbulent convection networks

AU - Fonda, Enrico

AU - Pandey, Ambrish

AU - Schumacher, Jörg

AU - Sreenivasan, Katepalli

PY - 2019/4/30

Y1 - 2019/4/30

N2 - We explore heat transport properties of turbulent Rayleigh–Bénard convection in horizontally extended systems by using deep-learning algorithms that greatly reduce the number of degrees of freedom. Particular attention is paid to the slowly evolving turbulent superstructures—so called because they are larger in extent than the height of the convection layer—which appear as temporal patterns of ridges of hot upwelling and cold downwelling fluid, including defects where the ridges merge or end. The machine-learning algorithm trains a deep convolutional neural network (CNN) with U-shaped architecture, consisting of a contraction and a subsequent expansion branch, to reduce the complex 3D turbulent superstructure to a temporal planar network in the midplane of the layer. This results in a data compression by more than five orders of magnitude at the highest Rayleigh number, and its application yields a discrete transport network with dynamically varying defect points, including points of locally enhanced heat flux or “hot spots.” One conclusion is that the fraction of heat transport by the superstructure decreases as the Rayleigh number increases (although they might remain individually strong), correspondingly implying the increased importance of small-scale background turbulence.

AB - We explore heat transport properties of turbulent Rayleigh–Bénard convection in horizontally extended systems by using deep-learning algorithms that greatly reduce the number of degrees of freedom. Particular attention is paid to the slowly evolving turbulent superstructures—so called because they are larger in extent than the height of the convection layer—which appear as temporal patterns of ridges of hot upwelling and cold downwelling fluid, including defects where the ridges merge or end. The machine-learning algorithm trains a deep convolutional neural network (CNN) with U-shaped architecture, consisting of a contraction and a subsequent expansion branch, to reduce the complex 3D turbulent superstructure to a temporal planar network in the midplane of the layer. This results in a data compression by more than five orders of magnitude at the highest Rayleigh number, and its application yields a discrete transport network with dynamically varying defect points, including points of locally enhanced heat flux or “hot spots.” One conclusion is that the fraction of heat transport by the superstructure decreases as the Rayleigh number increases (although they might remain individually strong), correspondingly implying the increased importance of small-scale background turbulence.

KW - Machine learning

KW - Temporal networks

KW - Turbulent convection

UR - http://www.scopus.com/inward/record.url?scp=85065509912&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065509912&partnerID=8YFLogxK

U2 - 10.1073/pnas.1900358116

DO - 10.1073/pnas.1900358116

M3 - Article

VL - 116

SP - 8667

EP - 8672

JO - Proceedings of the National Academy of Sciences of the United States of America

JF - Proceedings of the National Academy of Sciences of the United States of America

SN - 0027-8424

IS - 18

ER -