{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T22:11:44Z","timestamp":1785881504366,"version":"3.56.0"},"reference-count":38,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T00:00:00Z","timestamp":1729555200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Nonlinear 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.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>This 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.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Through 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.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>Our approach shows potential for applications in fields such as neuroscience, material science, and weather prediction, where slow dynamics influencing qualitative changes are often unobservable.<\/jats:p><\/jats:sec>","DOI":"10.3389\/frai.2024.1451926","type":"journal-article","created":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T05:10:31Z","timestamp":1729573831000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Prediction of unobserved bifurcation by unsupervised extraction of slowly time-varying system parameter dynamics from time series using reservoir computing"],"prefix":"10.3389","volume":"7","author":[{"given":"Keita","family":"Tokuda","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuichi","family":"Katori","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,10,22]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1016\/j.neunet.2011.08.004","article-title":"Learning slow features with reservoir computing for biologically-inspired robot localization","volume":"25","author":"Antonelo","year":"2012","journal-title":"Neural Netw"},{"key":"B2","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1051\/jphystap:0190100100025400","article-title":"Les tourbillons cellulaires dans une nappe liquide. mthodes optiques dobservation et denregistrement","volume":"10","author":"Bnard","year":"1901","journal-title":"Journal de Physique Thorique et Applique"},{"key":"B3","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1016\/S0896-6273(02)00586-X","article-title":"Theta oscillations in the hippocampus","volume":"33","author":"Buzski","year":"2002","journal-title":"Neuron"},{"key":"B4","doi-asserted-by":"publisher","first-page":"013102","DOI":"10.1063\/1.5128898","article-title":"Dimension of reservoir computers","volume":"30","author":"Carroll","year":"2020","journal-title":"Chaos: Interdisc. J. Nonlinear Sci"},{"key":"B5","doi-asserted-by":"publisher","first-page":"14308","DOI":"10.1073\/pnas.0802430105","article-title":"Slowing down as an early warning signal for abrupt climate change","volume":"105","author":"Dakos","year":"2008","journal-title":"Proc. Nat. Acad. Sci"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1750","DOI":"10.1126\/science.254.5039.1750","article-title":"Oscillatory kinetics and spatio-temporal self-organization in reactions at solid surfaces","volume":"254","author":"Ertl","year":"1991","journal-title":"Science"},{"key":"B7","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1016\/j.neucom.2016.12.089","article-title":"Deep reservoir computing: A critical experimental analysis","volume":"268","author":"Gallicchio","year":"2017","journal-title":"Neurocomputing"},{"key":"B8","doi-asserted-by":"publisher","first-page":"2217","DOI":"10.1175\/1520-0469(1996)053&lt;2217:MAACII&gt;2.0.CO;2","article-title":"Multiple attractors and chaotic itinerancy in a quasigeostrophic model with realistic topography: implications for weather regimes and low-frequency variability","volume":"53","author":"Itoh","year":"1996","journal-title":"J. Atmosph. Sci"},{"key":"B9","doi-asserted-by":"publisher","first-page":"579","DOI":"10.1587\/nolta.14.579","article-title":"Verifying the robustness of using parameter space estimation with ridge regression to predict a critical transition","volume":"14","author":"Itoh","year":"2023","journal-title":"Nonlinear Theory Appl. IEICE"},{"key":"B10","first-page":"1","author":"Jaeger","year":"2008","journal-title":"Discovering Multiscale Dynamical Features with Hierarchical Echo State Networks"},{"key":"B11","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1126\/science.1091277","article-title":"Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication","volume":"304","author":"Jaeger","year":"2004","journal-title":"Science"},{"key":"B12","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1016\/j.neunet.2007.04.016","article-title":"Optimization and applications of echo state networks with leaky- integrator neurons","volume":"20","author":"Jaeger","year":"2007","journal-title":"Neural Netw"},{"key":"B13","doi-asserted-by":"publisher","first-page":"926","DOI":"10.1063\/1.1607783","article-title":"Chaotic itinerancy","volume":"13","author":"Kaneko","year":"2003","journal-title":"Chaos: Interdisc. J. Nonlinear Sci"},{"key":"B14","first-page":"341","article-title":"\u201cHierarchical network model of predictive coding based on reservoir computing,\u201d","volume-title":"The 2019 International Symposium on Nonlinear Theory and Its Applications (NOLTA2019)","author":"Katori","year":"2019"},{"key":"B15","doi-asserted-by":"publisher","first-page":"e1002266","DOI":"10.1371\/journal.pcbi.1002266","article-title":"Representational switching by dynamical reorganization of attractor structure in a network model of the prefrontal cortex","volume":"7","author":"Katori","year":"2011","journal-title":"PLoS Comp. Biol"},{"key":"B16","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1038\/s42256-021-00321-2","article-title":"Teaching recurrent neural networks to infer global temporal structure from local examples","volume":"3","author":"Kim","year":"2021","journal-title":"Nat. Mach. Intell"},{"key":"B17","doi-asserted-by":"publisher","first-page":"013090","DOI":"10.1103\/PhysRevResearch.3.013090","article-title":"Machine learning prediction of critical transition and system collapse","volume":"3","author":"Kong","year":"2021","journal-title":"Phys. Rev. Res"},{"key":"B18","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/s40484-013-0008-0","article-title":"Dynamical network biomarkers for identifying critical transitions and their driving networks of biologic processes","volume":"1","author":"Liu","year":"2013","journal-title":"Quant. Biol"},{"key":"B19","doi-asserted-by":"publisher","first-page":"063133","DOI":"10.1063\/5.0004344","article-title":"Invertible generalized synchronization: A putative mechanism for implicit learning in neural systems","volume":"30","author":"Lu","year":"2020","journal-title":"Chaos"},{"key":"B20","doi-asserted-by":"publisher","first-page":"061104","DOI":"10.1063\/1.5039508","article-title":"Attractor reconstruction by machine learning","volume":"28","author":"Lu","year":"2018","journal-title":"Chaos"},{"key":"B21","doi-asserted-by":"publisher","first-page":"041102","DOI":"10.1063\/1.4979665","article-title":"Reservoir observers: Model-free inference of unmeasured variables in chaotic systems","volume":"27","author":"Lu","year":"2017","journal-title":"Chaos"},{"key":"B22","doi-asserted-by":"publisher","first-page":"616658","DOI":"10.3389\/fams.2020.616658","article-title":"Exploiting multiple timescales in hierarchical echo state networks","volume":"6","author":"Manneschi","year":"2021","journal-title":"Front. Appl. Mathemat. Statist"},{"key":"B23","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1140\/epjs\/s11734-022-00739-8","article-title":"Trends in recurrence analysis of dynamical systems","volume":"232","author":"Marwan","year":"2023","journal-title":"Eur. Phys. J. Spec. Topics"},{"key":"B24","doi-asserted-by":"publisher","first-page":"033149","DOI":"10.1063\/5.0042598","article-title":"Using machine learning to predict statistical properties of non-stationary dynamical processes: System climate, regime transitions, and the effect of stochasticity","volume":"31","author":"Patel","year":"2021","journal-title":"Chaos"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-023-36434-y","article-title":"Emergence of chaos in a compartmentalized catalytic reaction nanosystem","volume":"14","author":"Raab","year":"2023","journal-title":"Nat. Commun"},{"key":"B26","doi-asserted-by":"publisher","first-page":"068102","DOI":"10.1103\/PhysRevLett.87.068102","article-title":"Dynamical encoding by networks of competing neuron groups: winnerless competition","volume":"87","author":"Rabinovich","year":"2001","journal-title":"Phys. Rev. Lett"},{"key":"B27","doi-asserted-by":"publisher","first-page":"980","DOI":"10.1103\/PhysRevE.51.980","article-title":"Generalized synchronization of chaos in directionally coupled chaotic systems","volume":"51","author":"Rulkov","year":"1995","journal-title":"Phys. Rev. E"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1605","DOI":"10.1143\/PTP.61.1605","article-title":"A numerical approach to ergodic problem of dissipative dynamical systems","volume":"61","author":"Shimada","year":"1979","journal-title":"Prog. Theoret. Phys"},{"key":"B29","doi-asserted-by":"publisher","first-page":"3252","DOI":"10.1523\/JNEUROSCI.13-08-03252.1993","article-title":"A novel slow (< 1 hz) oscillation of neocortical neurons in vivo: depolarizing and hyperpolarizing components","volume":"13","author":"Steriade","year":"1993","journal-title":"J. Neurosci"},{"key":"B30","doi-asserted-by":"publisher","first-page":"42","DOI":"10.2991\/jrnal.k.190531.009","article-title":"Possible mechanism of internal visual perception: Context-dependent processing by predictive coding and reservoir computing network","volume":"6","author":"Tamura","year":"2019","journal-title":"J. Robot. Network. Artif. Life"},{"key":"B31","doi-asserted-by":"publisher","first-page":"L032014","DOI":"10.1103\/PhysRevResearch.4.L032014","article-title":"Reservoir computing with diverse timescales for prediction of multiscale dynamics","volume":"4","author":"Tanaka","year":"2022","journal-title":"Phys. Rev. Res"},{"key":"B32","doi-asserted-by":"publisher","first-page":"113115","DOI":"10.1063\/1.5110327","article-title":"Chaotic dynamics as a mechanism of rapid transition of hippocampal local field activity between theta and non-theta states","volume":"29","author":"Tokuda","year":"2019","journal-title":"Chaos"},{"key":"B33","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1038\/nature10723","article-title":"Recovery rates reflect distance to a tipping point in a living system","volume":"481","author":"Veraart","year":"2011","journal-title":"Nature"},{"key":"B34","doi-asserted-by":"publisher","first-page":"20","DOI":"10.3389\/fnsys.2020.00020","article-title":"Ghost attractors in spontaneous brain activity: recurrent excursions into functionally-relevant bold phase-locking states","volume":"14","author":"Vohryzek","year":"2020","journal-title":"Front. Syst. Neurosci"},{"key":"B35","first-page":"257","article-title":"\u201cGenetic assimilation,\u201d","volume-title":"Advances in Genetics","author":"Waddington","year":"1961"},{"key":"B36","doi-asserted-by":"publisher","first-page":"715","DOI":"10.1162\/089976602317318938","article-title":"Slow feature analysis: unsupervised learning of invariances","volume":"14","author":"Wiskott","year":"2002","journal-title":"Neural Comp"},{"key":"B37","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1587\/nolta.12.143","article-title":"Network model of predictive coding based on reservoir computing for multi-modal processing of visual and auditory signals","volume":"12","author":"Yonemura","year":"2021","journal-title":"Nonlinear Theory Appl. IEICE"},{"key":"B38","doi-asserted-by":"publisher","first-page":"013196","DOI":"10.1103\/PhysRevResearch.6.013196","article-title":"Machine-learning parameter tracking with partial state observation","volume":"6","author":"Zhai","year":"2024","journal-title":"Phys. Rev. Res"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1451926\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T05:10:34Z","timestamp":1729573834000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1451926\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,22]]},"references-count":38,"alternative-id":["10.3389\/frai.2024.1451926"],"URL":"https:\/\/doi.org\/10.3389\/frai.2024.1451926","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,22]]},"article-number":"1451926"}}