Compressing fluid flows with nonlinear machine learning: mode decomposition, latent modeling, and flow control

Abstract

An autoencoder is a self-supervised machine-learning network trained to output a quantity identical to the input. Owing to its structure possessing a bottleneck with a lower dimension, an autoencoder works to achieve data compression, extracting the essence of the high-dimensional data into the resulting latent space. We review the fundamentals of flow field compression using convolutional neural network-based autoencoder (CNN-AE) and its applications to various fluid dynamics problems. We cover the structure and the working principle of CNN-AE with an example of unsteady flows while examining the theoretical similarities between linear and nonlinear compression techniques. Representative applications of CNN-AE to various flow problems, such as mode decomposition, latent modeling, and flow control, are discussed. Throughout the present review, we show how the outcomes from the nonlinear machine-learning-based compression may support modeling and understanding a range of fluid mechanics problems.

26 pages, 20 figures

References in corpus (36)

• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• Machine Learning for Fluid Mechanics
• Turbulence Modeling in the Age of Data
• Deep learning for universal linear embeddings of nonlinear dynamics
• Super-resolution reconstruction of turbulent flows with machine learning
• Enhancing Computational Fluid Dynamics with Machine Learning
• Nonlinear mode decomposition with convolutional neural networks for fluid dynamics
• Assessment of supervised machine learning methods for fluid flows
• Convolutional neural network and long short-term memory based reduced order surrogate for minimal turbulent channel flow
• Convolutional neural network based hierarchical autoencoder for nonlinear mode decomposition of fluid field data
• Machine-learning-based reduced order modeling for unsteady flows around bluff bodies of various shapes
• A neural network approach for the blind deconvolution of turbulent flows
• Super-Resolution Analysis via Machine Learning: A Survey for Fluid Flows
• Synthetic turbulent inflow generator using machine learning
• Convolutional neural networks for fluid flow analysis: toward effective metamodeling and low-dimensionalization
• Sparse identification of nonlinear dynamics with low-dimensionalized flow representations
• Stable a posteriori LES of 2D turbulence using convolutional neural networks: Backscattering analysis and generalization to higher Re via transfer learning
• Grasping Extreme Aerodynamics on a Low-Dimensional Manifold
• Learning dominant physical processes with data-driven balance models
• A transformer-based synthetic-inflow generator for spatially-developing turbulent boundary layers
• Stabilized Neural Ordinary Differential Equations for Long-Time Forecasting of Dynamical Systems
• Machine learning building-block-flow wall model for large-eddy simulation
• Phase-response analysis of synchronization for periodic flows
• Revealing the state space of turbulence using machine learning
• Single-snapshot machine learning for super-resolution of turbulence
• Transfer learning for nonlinear dynamics and its application to fluid turbulence
• Data-driven low-dimensional dynamic model of Kolmogorov flow
• Data-driven transient lift attenuation for extreme vortex gust-airfoil interactions
• Data-driven nonlinear turbulent flow scaling with Buckingham Pi variables
• A cyclic perspective on transient gust encounters through the lens of persistent homology
• Exact coherent structures in two-dimensional turbulence identified with convolutional autoencoders
• Model-Based Reinforcement Learning for Control of Strongly-Disturbed Unsteady Aerodynamic Flows
• Decoder Decomposition for the Analysis of the Latent Space of Nonlinear Autoencoders With Wind-Tunnel Experimental Data
• Flow control by a hybrid use of machine learning and control theory
• Actuation manifold from snapshot data
• A practical guide to estimation and uncertainty quantification of aerodynamic flows

Cited by in corpus (5)

• Information-theoretic machine learning for time-varying mode decomposition of separated aerodynamic flows
• Compact representation of transonic airfoil buffet flows with observable-augmented machine learning
• Phase autoencoder for rapid data-driven synchronization of rhythmic spatiotemporal patterns
• Convolutional causal learning for aerodynamic flows
• Gaussian Field Representations for Turbulent Flow: Compression, Scale Separation, and Physical Fidelity