Two methods to approximate the Koopman operator with a reservoir computer

Abstract

The Koopman operator provides a powerful framework for data-driven analysis of dynamical systems. In the last few years, a wealth of numerical methods providing finite-dimensional approximations of the operator have been proposed (e.g. extended dynamic mode decomposition (EDMD) and its variants). While convergence results for EDMD require an infinite number of dictionary elements, recent studies have shown that only few dictionary elements can yield an efficient approximation of the Koopman operator, provided that they are well-chosen through a proper training process. However, this training process typically relies on nonlinear optimization techniques. In this paper, we propose two novel methods based on a reservoir computer to train the dictionary. These methods rely solely on linear convex optimization. We illustrate the efficiency of the method with several numerical examples in the context of data reconstruction, prediction, and computation of the Koopman operator spectrum. These results pave the way to the use of the reservoir computer in the Koopman operator framework.

References in corpus (18)

• A Data-Driven Approximation of the Koopman Operator: Extending Dynamic Mode Decomposition
• On Dynamic Mode Decomposition: Theory and Applications
• Deep learning for universal linear embeddings of nonlinear dynamics
• Linear predictors for nonlinear dynamical systems: Koopman operator meets model predictive control
• Ergodic theory, Dynamic Mode Decomposition and Computation of Spectral Properties of the Koopman operator
• Extended dynamic mode decomposition with dictionary learning: a data-driven adaptive spectral decomposition of the Koopman operator
• Hybrid Forecasting of Chaotic Processes: Using Machine Learning in Conjunction with a Knowledge-Based Model
• Isostables, isochrons, and Koopman spectrum for the action-angle representation of stable fixed point dynamics
• On Explaining the Surprising Success of Reservoir Computing Forecaster of Chaos? The Universal Machine Learning Dynamical System with Contrasts to VAR and DMD
• Extensive Chaos in the Lorenz-96 Model
• Physics-Informed Probabilistic Learning of Linear Embeddings of Non-linear Dynamics With Guaranteed Stability
• Using a reservoir computer to learn chaotic attractors, with applications to chaos synchronisation and cryptography
• Learning Koopman Invariant Subspaces for Dynamic Mode Decomposition
• Applications of Koopman Mode Analysis to Neural Networks
• A Koopman-based framework for forecasting the spatiotemporal evolution of chaotic dynamics with nonlinearities modeled as exogenous forcings
• Optimizing Neural Networks via Koopman Operator Theory
• Modeling and Control of Soft Robots Using the Koopman Operator and Model Predictive Control
• Feedback Stabilization Using Koopman Operator

Cited by in corpus (5)

• Nonequilibrium Statistical Mechanics and Optimal Prediction of Partially-Observed Complex Systems
• Estimating asymptotic phase and amplitude functions of limit-cycle oscillators from time series data
• Combining Dynamic Mode Decomposition with Ensemble Kalman Filtering for Tracking and Forecasting
• Restrictions on Physical Stochastic Reservoir Computers
• Learning dynamical systems from data: Gradient-based dictionary optimization