Perspectives on predicting and controlling turbulent flows through deep learning

TL;DR

This paper reviews how deep learning is transforming the prediction, simulation, and control of wall-bounded turbulent flows, emphasizing the integration of ML with traditional scientific methods.

Contribution

It provides a comprehensive overview of recent advances in applying deep learning to turbulent flow prediction and control, highlighting the importance of combining ML with theory, experiments, and simulations.

Findings

ML enhances turbulence modeling accuracy

Deep learning enables real-time flow control

Synergies between ML and traditional methods are crucial

Abstract

The current revolution in the field of machine learning (ML) is leading to many interesting developments in a wide range of areas, including fluid mechanics. Here we review recent and emerging possibilities in the context of predictions, simulations and control of fluid flows, focusing on wall-bounded turbulence. A number of important areas are benefiting from ML, and it is important to identify the synergies with the existing pillars of scientific discovery, i.e. theory, experiments and simulations. It is essential to adopt a balanced approach as a community in order to harness all the positive potential of these novel methods.