Modeling chaotic systems: dynamical equations vs machine learning approach

DOI10.1016/J.CNSNS.2022.106452MaRDI QIDQ2160910zbMATH OpenOpenAlexWikidataFDO

Authors Tongfeng Weng, Jie Zhang, Michael Small, Huijie Yang

Publication date 3 August 2022

Published in Communications in Nonlinear Science and Numerical Simulation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.cnsns.2022.106452

zbMATH Keywords

chaotic systemsrecurrencereservoir computing approachsynchronization

Mathematics Subject Classification ID

Simulation of dynamical systems (37M05) Dynamical systems in numerical analysis (37N30) Learning and adaptive systems in artificial intelligence (68T05) Computational aspects of data analysis and big data (68T09) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20)

Recommendations

• Transfer learning of chaotic systems
• Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data
• MODELING OF CHAOTIC SYSTEMS WITH MULTIWAVELET TRANSFORM COMBINED WITH RECURRENT LEAST SQUARES SUPPORT VECTOR MACHINES
• Fitting model equations to time series using chaos synchronization
• Reservoir computing for forecasting large spatiotemporal dynamical systems

Cites work

• Defining chaos
• Deterministic Nonperiodic Flow
• Echo state networks are universal
• Echo state property linked to an input: exploring a fundamental characteristic of recurrent neural networks
• Good and bad predictions: assessing and improving the replication of chaotic attractors by means of reservoir computing
• Laplacian energy of a graph
• Nonlinear Time Series Analysis
• Recurrence networks -- a novel paradigm for nonlinear time series analysis
• Recurrence-based time series analysis by means of complex network methods
• Reservoir computing approaches to recurrent neural network training
• Superfamily phenomena and motifs of networks induced from time series
• Synchronization in chaotic systems
• The synchronization of chaotic systems
• Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data

Cited in

(13)

• Deep learning of conjugate mappings
• Synchronization of reservoir computing models via a nonlinear controller
• Reservoir computing for forecasting large spatiotemporal dynamical systems
• Neural machine-based forecasting of chaotic dynamics
• Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data
• Transfer learning of chaotic systems
• Synchronization of machine learning oscillators in complex networks
• Recurrence microstates for machine learning classification
• Synchronization of quantum reservoir computers
• Constructing bifurcation diagram of reservoir computing
• Dynamic response and chaos analysis of a spatial multi-body system with multiple clearance joints and a flexible component
• Modeling dynamical systems: from chaotic models to next-generation reservoir computers
• Machine-learning construction of a model for a macroscopic fluid variable using the delay-coordinate of a scalar observable

Describes a project that uses

Uses Software

• K2

This page was built for publication: Modeling chaotic systems: dynamical equations vs machine learning approach

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2160910)