Machine Learning for Fluid Mechanics

By Steven L. Brunton, Bernd R. Noack, Petros Koumoutsakos. Annual Review of Fluid Mechanics, 2019

2,811 citations recorded by the source corpus.

The field of fluid mechanics is rapidly advancing, driven by unprecedented volumes of data from experiments, field measurements, and large-scale simulations at multiple spatiotemporal scales. Machine learning (ML) offers a wealth of techniques to extract information from data that can be translated into knowledge about the underlying fluid mechanics. Moreover, ML algorithms can augment domain knowledge and automate tasks related to flow control and optimization. This article presents an overview of past history, current developments, and emerging opportunities of ML for fluid mechanics. We outline fundamental ML methodologies and discuss their uses for understanding, modeling, optimizing, and controlling fluid flows. The strengths and limitations of these methods are addressed from the perspective of scientific inquiry that considers data as an inherent part of modeling, experiments, and simulations. ML provides a powerful information-processing framework that can augment, and possibly even transform, current lines of fluid mechanics research and industrial applications.

Subfields: Computer Vision and Pattern Recognition, Materials Chemistry, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/4087e84fc695bb6433d0104ee94f9d7e9f4b7da5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Materials Chemistry

In Statistical and Nonlinear Physics

Citations in the corpus

Transformer for Partial Differential Equations' Operator Learning (2022, background): “In the ﬁrst group, attention layers are used to capture the structures and patterns lie in the PDEs’ spatial domain (Cao, 2021; Kissas et al., 2022; Shao et al., 2022).”
NSFnets (Navier-Stokes flow nets): Physics-informed neural networks for the incompressible Navier-Stokes equations (2020, background): “Comprehensive summaries of progress in fluid mechanics due to the introduction of various machine learning techniques can be found in [11, 12].”
Machine-learning-based spatio-temporal super resolution reconstruction of turbulent flows (2020, methodology): “In recent years, machine learning methods have been utilized to tackle various problems in ﬂuid dynamics (Brunton et al. 2020; Fukami et al. 2020; Brenner et al. 2019).”
Characterizing possible failure modes in physics-informed neural networks (2021, background): “In this vein, there have been a number of ML approaches to incorporate scientific knowledge into such problems while keeping the automatic, data-driven estimates of the solution [2, 17, 33, 39].”
Enhancing computational fluid dynamics with machine learning (2021, background): “Several authors have surveyed the potential of machine learning to improve fluid mechanics [11, 12], including topics beyond the scope of CFD, such as experimental techniques, control applications, and related fields.”
Physics-Informed Neural Operator for Learning Partial Differential Equations (2021, positive): “Machine learning methods have recently shown promise in solving partial differential equations ( PDEs ) [1–5].”
Neural operators for accelerating scientific simulations and design (2023, neutral): “Artificial intelligence (AI) is now transforming our ability to create fast, high-fidelity simulations of many complex multi-scale processes [5, 6].”
Digital Twin: Values, Challenges and Enablers From a Modeling Perspective (2019, neutral): “For example, we refer to recent surveys of ML in domainspecific areas of molecular and material science [326] and fluid mechanics [327].”
Deep learning methods for super-resolution reconstruction of turbulent flows (2020, methodology): “16 The deep learning method was first used in the SR problem by Dong et al. 17 in 2014.”
Towards Physics-informed Deep Learning for Turbulent Flow Prediction (2019, background): “ccurately the properties of complex physical systems. Developing deep learning methods that can incorporate physical laws in a systematic manner is a key element in advancing AI for physical sciences [32]. Recently, several studies in data science and computational mathematics communities have attem”
A review on Deep Reinforcement Learning for Fluid Mechanics (2019, background): “Machine learning has been making especially rapid inroads in fluid mechanics, as a flexible modeling framework that can be fit to address many challenges, including reduced-order modeling, experimental data processing, shape optimization, turbulence closure modeling, and control [5].”
Flow over an espresso cup: inferring 3-D velocity and pressure fields from tomographic background oriented Schlieren via physics-informed neural networks (2021, background): “Recently, deep learning techniques have become increasingly popular in both computational and experimental fluid dynamics (Brunton et al. 2020; Duraisamy et al. 2019).”