Perspective on machine learning for advancing fluid mechanics

Abstract
A perspective is presented on how machine learning (ML), with its burgeoning popularity and the increasing availability of portable implementations, might advance fluid mechanics. As with any numerical or experimental method, ML methods have strengths and limitations, which are acknowledged. Their potential impact is high so long as outcomes are held to the long-standing critical standards that should guide studies of flow physics.
Funding Information
  • National Science Foundation (DMS-1751477)
  • Simons Foundation
  • U.S. Department of Energy
  • National Nuclear Security Administration (DE-NA0002374)