Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data

DOI10.1063/1.5010300zbMath1390.37138arXiv1710.07313OpenAlexW2765128778WikidataQ47172677 ScholiaQ47172677MaRDI QIDQ4563888

Michelle Girvan, Brian R. Hunt, Zhixin Lu, Edward Ott, Jaideep Pathak

Publication date: 4 June 2018

Published in: Chaos: An Interdisciplinary Journal of Nonlinear Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1710.07313

Mathematics Subject Classification ID

Dynamical systems in fluid mechanics, oceanography and meteorology (37N10) Computational methods for ergodic theory (approximation of invariant measures, computation of Lyapunov exponents, entropy, etc.) (37M25)

Related Items (65)

Simple estimation method for the second-largest Lyapunov exponent of chaotic differential equations ⋮ Robustness of LSTM neural networks for multi-step forecasting of chaotic time series ⋮ Machine-learning construction of a model for a macroscopic fluid variable using the delay-coordinate of a scalar observable ⋮ Synchronization of reservoir computers with applications to communications ⋮ Unnamed Item ⋮ Data-driven forecasting of high-dimensional chaotic systems with long short-term memory networks ⋮ Modeling chaotic systems: dynamical equations vs machine learning approach ⋮ Dissecting cell fate dynamics in pediatric glioblastoma through the lens of complex systems and cellular cybernetics ⋮ Detection of generalized synchronization using echo state networks ⋮ Time series analysis and prediction of nonlinear systems with ensemble learning framework applied to deep learning neural networks ⋮ A framework for machine learning of model error in dynamical systems ⋮ Fading memory echo state networks are universal ⋮ Robust optimization and validation of echo state networks for learning chaotic dynamics ⋮ Reservoir computing with error correction: long-term behaviors of stochastic dynamical systems ⋮ Learning dynamical systems from data: a simple cross-validation perspective. IV: Case with partial observations ⋮ Accuracy and architecture studies of residual neural network method for ordinary differential equations ⋮ Approximation bounds for random neural networks and reservoir systems ⋮ Parsimony as the ultimate regularizer for physics-informed machine learning ⋮ Stability analysis of chaotic systems from data ⋮ Learning Theory for Dynamical Systems ⋮ Learning strange attractors with reservoir systems ⋮ Inferring symbolic dynamics of chaotic flows from persistence ⋮ Ensemble forecasts in reproducing kernel Hilbert space family ⋮ Learning dynamics by reservoir computing (In Memory of Prof. Pavol Brunovský) ⋮ Identification of chimera using machine learning ⋮ Invertible generalized synchronization: A putative mechanism for implicit learning in neural systems ⋮ Reducing network size and improving prediction stability of reservoir computing ⋮ Seeking optimal parameters for achieving a lightweight reservoir computing: a computational endeavor ⋮ Using reservoir computer to predict and prevent extreme events ⋮ Machine learning, alignment of covariant Lyapunov vectors, and predictability in Rikitake’s geomagnetic dynamo model ⋮ Deep learning of dynamics and signal-noise decomposition with time-stepping constraints ⋮ Modeling the dynamics of PDE systems with physics-constrained deep auto-regressive networks ⋮ Assessing observability of chaotic systems using Delay Differential Analysis ⋮ Learning dynamical systems in noise using convolutional neural networks ⋮ A novel method based on the pseudo-orbits to calculate the largest Lyapunov exponent from chaotic equations ⋮ Embedding and approximation theorems for echo state networks ⋮ Measuring Lyapunov exponents of large chaotic systems with global coupling by time series analysis ⋮ Identifying the linear region based on machine learning to calculate the largest Lyapunov exponent from chaotic time series ⋮ Reservoir Computing with an Inertial Form ⋮ Unnamed Item ⋮ Learning the tangent space of dynamical instabilities from data ⋮ Artificial Intelligence, Chaos, Prediction and Understanding in Science ⋮ Using machine learning to predict extreme events in the Hénon map ⋮ Collective dynamics of rate neurons for supervised learning in a reservoir computing system ⋮ Good and bad predictions: Assessing and improving the replication of chaotic attractors by means of reservoir computing ⋮ Stability analysis of reservoir computers dynamics via Lyapunov functions ⋮ Predicting critical transitions in multiscale dynamical systems using reservoir computing ⋮ Breaking symmetries of the reservoir equations in echo state networks ⋮ Using machine learning to predict statistical properties of non-stationary dynamical processes: System climate,regime transitions, and the effect of stochasticity ⋮ Inferring the dynamics of oscillatory systems using recurrent neural networks ⋮ Transfer learning of chaotic systems ⋮ Multifunctionality in a reservoir computer ⋮ Error bounds of the invariant statistics in machine learning of ergodic Itô diffusions ⋮ Learning dynamical systems from data: a simple cross-validation perspective. I: Parametric kernel flows ⋮ Echo state networks trained by Tikhonov least squares are \(L^2(\mu)\) approximators of ergodic dynamical systems ⋮ Using data assimilation to train a hybrid forecast system that combines machine-learning and knowledge-based components ⋮ Detecting unstable periodic orbits based only on time series: When adaptive delayed feedback control meets reservoir computing ⋮ The reservoir’s perspective on generalized synchronization ⋮ Unnamed Item ⋮ Chaos: From theory to applications for the 80th birthday of Otto E. Rössler ⋮ Synchronization of reservoir computing models via a nonlinear controller ⋮ Clustered and deep echo state networks for signal noise reduction ⋮ Generalized Cell Mapping Method with Deep Learning for Global Analysis and Response Prediction of Dynamical Systems ⋮ One-shot learning of stochastic differential equations with data adapted kernels ⋮ Chaotic diffusion of dissipative solitons: from anti-persistent random walks to hidden Markov models

Cites Work

This page was built for publication: Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data