Assessment of supervised machine learning methods for fluid flows

Kai Fukami, Koji Fukagata, Kunihiko Taira

Research output: Contribution to journalArticlepeer-review

105 Citations (Scopus)


We apply supervised machine learning techniques to a number of regression problems in fluid dynamics. Four machine learning architectures are examined in terms of their characteristics, accuracy, computational cost, and robustness for canonical flow problems. We consider the estimation of force coefficients and wakes from a limited number of sensors on the surface for flows over a cylinder and NACA0012 airfoil with a Gurney flap. The influence of the temporal density of the training data is also examined. Furthermore, we consider the use of convolutional neural network in the context of super-resolution analysis of two-dimensional cylinder wake, two-dimensional decaying isotropic turbulence, and three-dimensional turbulent channel flow. In the concluding remarks, we summarize on findings from a range of regression-type problems considered herein.

Original languageEnglish
Pages (from-to)497-519
Number of pages23
JournalTheoretical and Computational Fluid Dynamics
Issue number4
Publication statusPublished - 2020 Aug 1


  • Supervised machine learning
  • Turbulence
  • Wake dynamics

ASJC Scopus subject areas

  • Computational Mechanics
  • Condensed Matter Physics
  • Engineering(all)
  • Fluid Flow and Transfer Processes


Dive into the research topics of 'Assessment of supervised machine learning methods for fluid flows'. Together they form a unique fingerprint.

Cite this