Two methods to approximate the Koopman operator with a reservoir computer

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.

[1]  Erik Bollt,et al.  On explaining the surprising success of reservoir computing forecaster of chaos? The universal machine learning dynamical system with contrast to VAR and DMD. , 2020, Chaos.

[2]  Clarence W. Rowley,et al.  A Data–Driven Approximation of the Koopman Operator: Extending Dynamic Mode Decomposition , 2014, Journal of Nonlinear Science.

[3]  Karthik Duraisamy,et al.  Physics-Informed Probabilistic Learning of Linear Embeddings of Nonlinear Dynamics with Guaranteed Stability , 2019, SIAM J. Appl. Dyn. Syst..

[4]  B. O. Koopman,et al.  Hamiltonian Systems and Transformation in Hilbert Space. , 1931, Proceedings of the National Academy of Sciences of the United States of America.

[5]  Michelle Girvan,et al.  Hybrid Forecasting of Chaotic Processes: Using Machine Learning in Conjunction with a Knowledge-Based Model , 2018, Chaos.

[6]  Soumya Kundu,et al.  Learning Deep Neural Network Representations for Koopman Operators of Nonlinear Dynamical Systems , 2017, 2019 American Control Conference (ACC).

[7]  Joshua L. Proctor,et al.  Discovering dynamic patterns from infectious disease data using dynamic mode decomposition , 2015, International health.

[8]  M. A. Khodkar,et al.  A Koopman-based framework for forecasting the spatiotemporal evolution of chaotic dynamics with nonlinearities modeled as exogenous forcings , 2019, 1909.00076.

[9]  Julien M. Hendrickx,et al.  Spectral Identification of Networks Using Sparse Measurements , 2016, SIAM J. Appl. Dyn. Syst..

[10]  Igor Mezic,et al.  Linear predictors for nonlinear dynamical systems: Koopman operator meets model predictive control , 2016, Autom..

[11]  Naoya Takeishi,et al.  Learning Koopman Invariant Subspaces for Dynamic Mode Decomposition , 2017, NIPS.

[12]  I. Mezic,et al.  Nonlinear Koopman Modes and Coherency Identification of Coupled Swing Dynamics , 2011, IEEE Transactions on Power Systems.

[13]  Igor Mezic,et al.  Global Stability Analysis Using the Eigenfunctions of the Koopman Operator , 2014, IEEE Transactions on Automatic Control.

[14]  Serge Massar,et al.  Using a reservoir computer to learn chaotic attractors, with applications to chaos synchronisation and cryptography , 2018, Physical review. E.

[15]  I. Mezić,et al.  Spectral analysis of nonlinear flows , 2009, Journal of Fluid Mechanics.

[16]  Zlatko Drmac,et al.  Data Driven Modal Decompositions: Analysis and Enhancements , 2017, SIAM J. Sci. Comput..

[17]  The Koopman Operator in Systems and Control , 2020, Lecture Notes in Control and Information Sciences.

[18]  Igor Mezic,et al.  Ergodic Theory, Dynamic Mode Decomposition, and Computation of Spectral Properties of the Koopman Operator , 2016, SIAM J. Appl. Dyn. Syst..

[19]  Steven L. Brunton,et al.  Data-driven discovery of Koopman eigenfunctions for control , 2017, Mach. Learn. Sci. Technol..

[20]  Amit Surana,et al.  Koopman Operator Framework for Time Series Modeling and Analysis , 2018, Journal of Nonlinear Science.

[21]  C. David Remy,et al.  Modeling and Control of Soft Robots Using the Koopman Operator and Model Predictive Control , 2019, Robotics: Science and Systems.

[22]  I. Mezić,et al.  Isostables, isochrons, and Koopman spectrum for the action-angle representation of stable fixed point dynamics , 2013, 1302.0032.

[23]  I. Mezić Spectral Properties of Dynamical Systems, Model Reduction and Decompositions , 2005 .

[24]  Benjamin Schrauwen,et al.  Phoneme Recognition with Large Hierarchical Reservoirs , 2010, NIPS.

[25]  Akshunna S. Dogra,et al.  Optimizing Neural Networks via Koopman Operator Theory , 2020, NeurIPS.

[26]  Ioannis G Kevrekidis,et al.  Extended dynamic mode decomposition with dictionary learning: A data-driven adaptive spectral decomposition of the Koopman operator. , 2017, Chaos.

[27]  Benjamin Schrauwen,et al.  Reservoir Computing Trends , 2012, KI - Künstliche Intelligenz.

[28]  L. Glass,et al.  Oscillation and chaos in physiological control systems. , 1977, Science.

[29]  Steven L. Brunton,et al.  Deep learning for universal linear embeddings of nonlinear dynamics , 2017, Nature Communications.

[30]  Yoshihiko Susuki,et al.  A prony approximation of Koopman Mode Decomposition , 2015, 2015 54th IEEE Conference on Decision and Control (CDC).

[31]  P. Schmid,et al.  Dynamic mode decomposition of numerical and experimental data , 2008, Journal of Fluid Mechanics.

[32]  Umesh Vaidya,et al.  Feedback Stabilization Using Koopman Operator , 2018, 2018 IEEE Conference on Decision and Control (CDC).

[33]  Yoshihiko Susuki,et al.  Nonlinear Koopman modes and power system stability assessment without models , 2014, 2014 IEEE PES General Meeting | Conference & Exposition.

[34]  Steven L. Brunton,et al.  On dynamic mode decomposition: Theory and applications , 2013, 1312.0041.

[35]  Christiam F. Frasser,et al.  Cyclic Reservoir Computing with FPGA Devices for Efficient Channel Equalization , 2018, ICAISC.

[36]  Herbert Jaeger,et al.  Reservoir computing approaches to recurrent neural network training , 2009, Comput. Sci. Rev..

[37]  Maria Fonoberova,et al.  Applications of Koopman Mode Analysis to Neural Networks , 2020, AAAI Spring Symposium: MLPS.

[38]  Herbert Jaeger,et al.  The''echo state''approach to analysing and training recurrent neural networks , 2001 .

[39]  Harald Haas,et al.  Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication , 2004, Science.

[40]  D. Giannakis,et al.  Reproducing kernel Hilbert space compactification of unitary evolution groups , 2018, 1808.01515.