Model Order Reduction with Neural Networks: Application to Laminar and Turbulent Flows

Kai Fukami, Kazuto Hasegawa, Taichi Nakamura, Masaki Morimoto, Koji Fukagata

Research output: Contribution to journalArticlepeer-review

22 Citations (Scopus)


We investigate the capability of neural network-based model order reduction, i.e., autoencoder (AE), for fluid flows. As an example model, an AE which comprises of convolutional neural networks and multi-layer perceptrons is considered in this study. The AE model is assessed with four canonical fluid flows, namely: (1) two-dimensional cylinder wake, (2) its transient process, (3) NOAA sea surface temperature, and (4) a cross-sectional field of turbulent channel flow, in terms of a number of latent modes, the choice of nonlinear activation functions, and the number of weights contained in the AE model. We find that the AE models are sensitive to the choice of the aforementioned parameters depending on the target flows. Finally, we foresee the extensional applications and perspectives of machine learning based order reduction for numerical and experimental studies in the fluid dynamics community.

Original languageEnglish
Article number467
JournalSN Computer Science
Issue number6
Publication statusPublished - 2021 Nov


  • Autoencoder
  • Reduced order model
  • Turbulence
  • Wake

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Networks and Communications
  • Computer Science Applications
  • Computer Science(all)
  • Artificial Intelligence
  • Computer Graphics and Computer-Aided Design


Dive into the research topics of 'Model Order Reduction with Neural Networks: Application to Laminar and Turbulent Flows'. Together they form a unique fingerprint.

Cite this