Model-free inference of unseen attractors: Reconstructing phase space features from a single noisy trajectory using reservoir computing

Reservoir computers are powerful tools for chaotic time series prediction. They can be trained to approximate phase space flows and can thus both predict future values to a high accuracy and reconstruct the general properties of a chaotic attractor without requiring a model. In this work, we show that the ability to learn the dynamics of a complex system can be extended to systems with multiple co-existing attractors, here a four-dimensional extension of the well-known Lorenz chaotic system. We demonstrate that a reservoir computer can infer entirely unexplored parts of the phase space; a properly trained reservoir computer can predict the existence of attractors that were never approached during training and, therefore, are labeled as unseen. We provide examples where attractor inference is achieved after training solely on a single noisy trajectory.

[1]  Michelle Girvan,et al.  Encoding of a Chaotic Attractor in a Reservoir Computer: A Directional Fiber Investigation , 2019, 2019 International Joint Conference on Neural Networks (IJCNN).

[2]  George J. Pappas,et al.  Teaching recurrent neural networks to infer global temporal structure from local examples , 2021, Nature Machine Intelligence.

[3]  Henry Markram,et al.  Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations , 2002, Neural Computation.

[4]  Christoph Räth,et al.  Good and bad predictions: Assessing and improving the replication of chaotic attractors by means of reservoir computing. , 2019, Chaos.

[5]  Erik Bollt,et al.  Next generation reservoir computing , 2021, Nature Communications.

[6]  S. Brunton,et al.  Discovering governing equations from data by sparse identification of nonlinear dynamical systems , 2015, Proceedings of the National Academy of Sciences.

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

[8]  Edward Ott,et al.  Attractor reconstruction by machine learning. , 2018, Chaos.

[9]  Julien Clinton Sprott,et al.  Coexisting Hidden Attractors in a 4-D Simplified Lorenz System , 2014, Int. J. Bifurc. Chaos.

[10]  M. C. Soriano,et al.  Constructive Role of Noise for High-Quality Replication of Chaotic Attractor Dynamics Using a Hardware-Based Reservoir Computer , 2019, Physical Review Applied.

[11]  S. Billings Nonlinear System Identification: NARMAX Methods in the Time, Frequency, and Spatio-Temporal Domains , 2013 .

[12]  Jaideep Pathak,et al.  Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data. , 2017, Chaos.

[13]  Tongfeng Weng,et al.  Mapping topological characteristics of dynamical systems into neural networks: A reservoir computing approach. , 2020, Physical review. E.

[14]  Joschka Herteux,et al.  Reducing network size and improving prediction stability of reservoir computing. , 2020, Chaos.

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

[16]  Kailiang Wu,et al.  Data Driven Governing Equations Approximation Using Deep Neural Networks , 2018, J. Comput. Phys..

[17]  Huanfei Ma,et al.  Detecting unstable periodic orbits based only on time series: When adaptive delayed feedback control meets reservoir computing. , 2019, Chaos.

[18]  Gao Zhi-zhong A Novel Hyperchaotic System , 2011 .

[19]  Juan-Pablo Ortega,et al.  Reservoir Computing Universality With Stochastic Inputs , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[20]  Guang-Bin Huang,et al.  Extreme learning machine: a new learning scheme of feedforward neural networks , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[21]  Conrad Sanderson,et al.  Armadillo: a template-based C++ library for linear algebra , 2016, J. Open Source Softw..