Exact coherent structures in two-dimensional turbulence identified with convolutional autoencoders

Abstract

Convolutional autoencoders are used to deconstruct the changing dynamics of two-dimensional Kolmogorov flow as $Re$ is increased from weakly chaotic flow at $Re=40$ to a chaotic state dominated by a domain-filling vortex pair at $Re=400$. The highly accurate embeddings allow us to visualise the evolving structure of state space and are interpretable using `latent Fourier analysis' (Page {\em et. al.}, \emph{Phys. Rev. Fluids} \textbf{6}, 2021). Individual latent Fourier modes decode into vortical structures with a streamwise lengthscale controlled by the latent wavenumber, $l$, with only a small number $l\lesssim 8$ required to accurately represent the flow. Latent Fourier projections reveal a detached class of bursting events at $Re=40$ which merge with the low-dissipation dynamics as $Re$ is increased to $100$. We use doubly- ($l=2$) or triply- ($l=3$) periodic latent Fourier modes to generate guesses for UPOs (unstable periodic orbits) associated with high-dissipation events. While the doubly-periodic UPOs are representative of the high-dissipation dynamics at $Re=40$, the same class of UPOs move away from the attractor at $Re=100$ -- where the associated bursting events typically involve larger-scale ($l=1$) structure too. At $Re=400$ an entirely different embedding structure is formed within the network in which no distinct representations of small-scale vortices are observed; instead the network embeds all snapshots based around a large-scale template for the condensate. We use latent Fourier projections to find an associated `large-scale' UPO which we believe to be a finite-$Re$ continuation of a solution to the Euler equations.

References in corpus (28)

• Machine Learning for Fluid Mechanics
• The Significance of Simple Invariant Solutions in Turbulent Flows
• Recurrent motions within plane Couette turbulence
• Visualizing the geometry of state space in plane Couette flow
• Lower branch coherent states in shear flows: transition and control
• Variational method for finding periodic orbits in a general flow
• Relative periodic orbits form the backbone of turbulent pipe flow
• Deep learning to discover and predict dynamics on an inertial manifold
• A variational approach to probing extreme events in turbulent dynamical systems
• Revealing the state space of turbulent pipe flow by symmetry reduction
• Spatially localized solutions of shear flows
• Spatiotemporal dynamics in 2D Kolmogorov flow over large domains
• An adjoint-based approach for finding invariant solutions of Navier-Stokes equations
• Streamwise and doubly-localised periodic orbits in plane Poiseuille flow
• Reduction of SO(2) symmetry for spatially extended dynamical systems
• Recurrent flow analysis in spatiotemporally chaotic 2-dimensional Kolmogorov flow
• Revealing the state space of turbulence using machine learning
• Coarse graining the state space of a turbulent flow using periodic orbits
• Searching turbulence for periodic orbits with dynamic mode decomposition
• Data-driven low-dimensional dynamic model of Kolmogorov flow
• Capturing Turbulent Dynamics and Statistics in Experiments with Unstable Periodic Orbits
• Small scale exact coherent structures at large Reynolds numbers in plane Couette flow
• Variational methods for finding periodic orbits in the incompressible Navier-Stokes equations
• Exact coherent structures and shadowing in turbulent Taylor-Couette flow
• Dipoles and streams in two-dimensional turbulence
• Self-similar invariant solution in the near-wall region of a turbulent boundary layer at asymptotically high Reynolds numbers
• Exact Coherent Structures in Fully Developed Two-Dimensional Turbulence
• Periodic orbits in Large Eddy Simulation of Box Turbulence

Cited by in corpus (7)

• Compressing fluid flows with nonlinear machine learning: mode decomposition, latent modeling, and flow control
• Compact representation of transonic airfoil buffet flows with observable-augmented machine learning
• Minimal cover of high-dimensional chaotic attractors by embedded recurrent patterns
• Data-driven guessing and gluing of unstable periodic orbits
• Stabilising nonlinear travelling waves in pipe flow using time-delayed feedback
• Dynamical relevance of periodic orbits under increasing Reynolds number and connections to inviscid dynamics
• On nonlinear transitions, minimal seeds and exact solutions for the geodynamo