Using Machine Learning to Replicate Chaotic Attractors and Calculate Lyapunov Exponents from Data

Abstract

We use recent advances in the machine learning area known as 'reservoir computing' to formulate a method for model-free estimation from data of the Lyapunov exponents of a chaotic process. The technique uses a limited time series of measurements as input to a high-dimensional dynamical system called a 'reservoir'. After the reservoir's response to the data is recorded, linear regression is used to learn a large set of parameters, called the 'output weights'. The learned output weights are then used to form a modified autonomous reservoir designed to be capable of producing arbitrarily long time series whose ergodic properties approximate those of the input signal. When successful, we say that the autonomous reservoir reproduces the attractor's 'climate'. Since the reservoir equations and output weights are known, we can compute derivatives needed to determine the Lyapunov exponents of the autonomous reservoir, which we then use as estimates of the Lyapunov exponents for the original input generating system. We illustrate the effectiveness of our technique with two examples, the Lorenz system, and the Kuramoto-Sivashinsky (KS) equation. In particular, we use the Lorenz system to show that achieving climate reproduction may require tuning of the reservoir parameters. For the case of the KS equation, we note that as the system's spatial size is increased, the number of Lyapunov exponents increases, thus yielding a challenging test of our method, which we find the method successfully passes.

Cited by in corpus (27)

• Next Generation Reservoir Computing
• Forecasting Chaotic Systems with Very Low Connectivity Reservoir Computers
• Long short-term memory embedded nudging schemes for nonlinear data assimilation of geophysical flows
• Consistency in Echo-State Networks
• Inferring the dynamics of oscillatory systems using recurrent neural networks
• Using Machine Learning to predict extreme events in the Hénon map
• Data driven soliton solution of the nonlinear Schrödinger equation with certain $\mathcal{P}\mathcal{T}$-symmetric potentials via deep learning
• EM-like Learning Chaotic Dynamics from Noisy and Partial Observations
• Model-free prediction of emergence of extreme events in a parametrically driven nonlinear dynamical system by Deep Learning
• Risk bounds for reservoir computing
• Transfer learning of chaotic systems
• Stability Analysis of Reservoir Computers Dynamics via Lyapunov Functions
• Neural Echo State Network using oscillations of gas bubbles in water
• Scattering Statistics in Nonlinear Wave Chaotic Systems
• Learning Dynamics from Noisy Measurements using Deep Learning with a Runge-Kutta Constraint
• Computing with vortices: Bridging fluid dynamics and its information-processing capability
• STENCIL-NET: Data-driven solution-adaptive discretization of partial differential equations
• Reservoir Computers Modal Decomposition and Optimization
• Capturing the Continuous Complexity of Behavior in C. elegans
• Representing ill-known parts of a numerical model using a machine learning approach
• Model-free prediction of spatiotemporal dynamical systems with recurrent neural networks: Role of network spectral radius
• Error Bounds of the Invariant Statistics in Machine Learning of Ergodic Itô Diffusions
• Accuracy and Architecture Studies of Residual Neural Network solving Ordinary Differential Equations
• Model-free inference of unseen attractors: Reconstructing phase space features from a single noisy trajectory using reservoir computing
• Scope and Sense of Explainability for AI-Systems
• Stability of exoplanetary systems retrieved from scalar time series
• Physical reservoir computing using finitely-sampled quantum systems