Dynamical system analysis of a data-driven model constructed by reservoir computing

Abstract

This study evaluates data-driven models from a dynamical system perspective, such as unstable fixed points, periodic orbits, chaotic saddle, Lyapunov exponents, manifold structures, and statistical values. We find that these dynamical characteristics can be reconstructed much more precisely by a data-driven model than by computing directly from training data. With this idea, we predict the laminar lasting time distribution of a particular macroscopic variable of chaotic fluid flow, which cannot be calculated from a direct numerical simulation of the Navier-Stokes equation because of its high computational cost.

8 pages, 9 figures

References in corpus (9)

• Using Machine Learning to Replicate Chaotic Attractors and Calculate Lyapunov Exponents from Data
• Attractor Reconstruction by Machine Learning
• Characterizing dynamics with covariant Lyapunov vectors
• Using a reservoir computer to learn chaotic attractors, with applications to chaos synchronisation and cryptography
• Machine-learning inference of fluid variables from data using reservoir computing
• Reservoir computing model of two-dimensional turbulent convection
• Using reservoir computer to predict and prevent extreme events
• Unstable Periodic Orbit Analysis of Histograms of Chaotic Time Series
• Machine-learning construction of a model for a macroscopic fluid variable using the delay-coordinate of a scalar observable