Prediction of unobserved bifurcation by unsupervised extraction of slowly time-varying system parameter dynamics from time series using reservoir computing

IntroductionNonlinear and non-stationary processes are prevalent in various natural and physical phenomena, where system dynamics can change qualitatively due to bifurcation phenomena. Machine learning methods have advanced our ability to learn and predict such systems from observed time series data...

Full description

Saved in:
Bibliographic Details
Main Authors: Keita Tokuda, Yuichi Katori
Format: Article
Language:English
Published: Frontiers Media S.A. 2024-10-01
Series:Frontiers in Artificial Intelligence
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/frai.2024.1451926/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850215119060992000
author Keita Tokuda
Yuichi Katori
author_facet Keita Tokuda
Yuichi Katori
author_sort Keita Tokuda
collection DOAJ
description IntroductionNonlinear and non-stationary processes are prevalent in various natural and physical phenomena, where system dynamics can change qualitatively due to bifurcation phenomena. Machine learning methods have advanced our ability to learn and predict such systems from observed time series data. However, predicting the behavior of systems with temporal parameter variations without knowledge of true parameter values remains a significant challenge.MethodsThis study uses reservoir computing framework to address this problem by unsupervised extraction of slowly varying system parameters from time series data. We propose a model architecture consisting of a slow reservoir with long timescale internal dynamics and a fast reservoir with short timescale dynamics. The slow reservoir extracts the temporal variation of system parameters, which are then used to predict unknown bifurcations in the fast dynamics.ResultsThrough experiments on chaotic dynamical systems, our proposed model successfully extracted slowly varying system parameters and predicted bifurcations that were not included in the training data. The model demonstrated robust predictive performance, showing that the reservoir computing framework can handle nonlinear, non-stationary systems without prior knowledge of the system's true parameters.DiscussionOur approach shows potential for applications in fields such as neuroscience, material science, and weather prediction, where slow dynamics influencing qualitative changes are often unobservable.
format Article
id doaj-art-e6b5207fb76d481b8361b4c2d6ca2f7e
institution OA Journals
issn 2624-8212
language English
publishDate 2024-10-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Artificial Intelligence
spelling doaj-art-e6b5207fb76d481b8361b4c2d6ca2f7e2025-08-20T02:08:42ZengFrontiers Media S.A.Frontiers in Artificial Intelligence2624-82122024-10-01710.3389/frai.2024.14519261451926Prediction of unobserved bifurcation by unsupervised extraction of slowly time-varying system parameter dynamics from time series using reservoir computingKeita Tokuda0Yuichi Katori1Faculty of Health Data Science, Juntendo University, Urayasu, JapanThe School of Systems Information Science, Future University Hakodate, Hakodate, JapanIntroductionNonlinear and non-stationary processes are prevalent in various natural and physical phenomena, where system dynamics can change qualitatively due to bifurcation phenomena. Machine learning methods have advanced our ability to learn and predict such systems from observed time series data. However, predicting the behavior of systems with temporal parameter variations without knowledge of true parameter values remains a significant challenge.MethodsThis study uses reservoir computing framework to address this problem by unsupervised extraction of slowly varying system parameters from time series data. We propose a model architecture consisting of a slow reservoir with long timescale internal dynamics and a fast reservoir with short timescale dynamics. The slow reservoir extracts the temporal variation of system parameters, which are then used to predict unknown bifurcations in the fast dynamics.ResultsThrough experiments on chaotic dynamical systems, our proposed model successfully extracted slowly varying system parameters and predicted bifurcations that were not included in the training data. The model demonstrated robust predictive performance, showing that the reservoir computing framework can handle nonlinear, non-stationary systems without prior knowledge of the system's true parameters.DiscussionOur approach shows potential for applications in fields such as neuroscience, material science, and weather prediction, where slow dynamics influencing qualitative changes are often unobservable.https://www.frontiersin.org/articles/10.3389/frai.2024.1451926/fullchaosnonlinear dynamicsbifurcation (mathematics)reservoir computingslow - fast dynamics
spellingShingle Keita Tokuda
Yuichi Katori
Prediction of unobserved bifurcation by unsupervised extraction of slowly time-varying system parameter dynamics from time series using reservoir computing
Frontiers in Artificial Intelligence
chaos
nonlinear dynamics
bifurcation (mathematics)
reservoir computing
slow - fast dynamics
title Prediction of unobserved bifurcation by unsupervised extraction of slowly time-varying system parameter dynamics from time series using reservoir computing
title_full Prediction of unobserved bifurcation by unsupervised extraction of slowly time-varying system parameter dynamics from time series using reservoir computing
title_fullStr Prediction of unobserved bifurcation by unsupervised extraction of slowly time-varying system parameter dynamics from time series using reservoir computing
title_full_unstemmed Prediction of unobserved bifurcation by unsupervised extraction of slowly time-varying system parameter dynamics from time series using reservoir computing
title_short Prediction of unobserved bifurcation by unsupervised extraction of slowly time-varying system parameter dynamics from time series using reservoir computing
title_sort prediction of unobserved bifurcation by unsupervised extraction of slowly time varying system parameter dynamics from time series using reservoir computing
topic chaos
nonlinear dynamics
bifurcation (mathematics)
reservoir computing
slow - fast dynamics
url https://www.frontiersin.org/articles/10.3389/frai.2024.1451926/full
work_keys_str_mv AT keitatokuda predictionofunobservedbifurcationbyunsupervisedextractionofslowlytimevaryingsystemparameterdynamicsfromtimeseriesusingreservoircomputing
AT yuichikatori predictionofunobservedbifurcationbyunsupervisedextractionofslowlytimevaryingsystemparameterdynamicsfromtimeseriesusingreservoircomputing