Deep learning in turbulent convection networks

Enrico Fonda, Ambrish Pandey, Jörg Schumacher, Katepalli R. Sreenivasan

Research output: Contribution to journalArticlepeer-review


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
Issue number18
StatePublished - Apr 30 2019


  • Machine learning
  • Temporal networks
  • Turbulent convection

ASJC Scopus subject areas

  • General


Dive into the research topics of 'Deep learning in turbulent convection networks'. Together they form a unique fingerprint.

Cite this