Identifying disturbances in network-coupled dynamical systems without knowledge of the disturbances or underlying dynamics is a problem with a wide range of applications. For example, one might want to know which nodes in the network are being disturbed and identify the type of disturbance. Here, we present a model-free method based on machine learning to identify such unknown disturbances based only on prior observations of the system when forced by a known training function. We find that this method is able to identify the locations and properties of many different types of unknown disturbances using a variety of known forcing functions. We illustrate our results with both linear and nonlinear disturbances using food web and neuronal activity models. Finally, we discuss how to scale our method to large networks.
REFERENCES
1.
G.
Tanaka
, T.
Yamane
, J. B.
Héroux
, R.
Nakane
, N.
Kanazawa
, S.
Takeda
, H.
Numata
, D.
Nakano
, and A.
Hirose
, “Recent advances in physical reservoir computing: A review
,” Neural Netw.
115
, 100
(2019
). 2.
S. L.
Brunton
and J. N.
Kutz
, Data-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control
(Cambridge University Press
, 2019
).3.
Y.
Tang
, J.
Kurths
, W.
Lin
, E.
Ott
, and L.
Kocarev
, “Introduction to focus issue: When machine learning meets complex systems: Networks, chaos, and nonlinear dynamics
,” Chaos
30
(6
), 063151
(2020
). 4.
K.
Nakajima
and I.
Fischer
, Reservoir Computing
(Springer
, New York
, 2021
).5.
J.
Pathak
, B. R.
Hunt
, M.
Girvan
, Z.
Lu
, and E.
Ott
, “Model-free prediction of large spatiotemporally chaotic systems from data: A reservoir computing approach
,” Phys. Rev. Lett.
120
, 024102
(2018
). 6.
K.
Srinivasan
, N.
Coble
, J.
Hamlin
, T.
Antonsen
, E.
Ott
, and M.
Girvan
, “Parallel machine learning for forecasting the dynamics of complex networks
,” Phys. Rev. Lett.
128
, 164101
(2022
). 7.
S.
Shahi
, C. D.
Marcotte
, C. J.
Herndon
, F. H.
Fenton
, Y.
Shiferaw
, and E. M.
Cherry
, “Long-time prediction of arrhythmic cardiac action potentials using recurrent neural networks and reservoir computing
,” Front. Physiol.
12
, 734178
(2021
). 8.
S.
Shahi
, F. H.
Fenton
, and E. M.
Cherry
, “Prediction of chaotic time series using recurrent neural networks and reservoir computing techniques: A comparative study
,” Mach. Learn. Appl.
8
, 100300
(2022
). 9.
J.
Pathak
, Z.
Lu
, B. R.
Hunt
, M.
Girvan
, and E.
Ott
, “Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data
,” Chaos
27
, 121102
(2017
). 10.
Q.
Zhu
, M.
Huanfei Ma
, and W.
Lin
, “Detecting unstable periodic orbits based only on time series: When adaptive delayed feedback control meets reservoir computing
,” Chaos
29
, 9
(2019
). 11.
A.
Banerjee
, J.
Pathak
, R.
Roy
, J. G.
Restrepo
, and E.
Ott
, “Using machine learning to assess short term causal dependence and infer network links
,” Chaos
29
, 121104
(2019
). 12.
V.
Pyragas
and K.
Pyragas
, “Using reservoir computer to predict and prevent extreme events
,” Phys. Lett. A
384
, 126591
(2020
). 13.
L.-W.
Kong
, Y.
Weng
, B.
Glaz
, M.
Haile
, and Y.-C.
Lai
, “Reservoir computing as digital twins for nonlinear dynamical systems
,” Chaos
33
, 033111
(2023
). 14.
D.
Patel
and E.
Ott
, “Using machine learning to anticipate tipping points and extrapolate to post-tipping dynamics of non-stationary dynamical systems
,” Chaos
33
, 023143
(2023
). 15.
D.
Canaday
, A.
Pomerance
, and D. J.
Gauthier
, “Model-free control of dynamical systems with deep reservoir computing
,” J. Phys.: Complex.
2
, 035025
(2021
). 16.
H.
Jaeger
and H.
Haas
, “Harnessing nonlinearity: Predicting chaotic systems and saving energy in wireless communication
,” Science
304
, 78
(2004
). 17.
S.
Wakabayashi
, T.
Arie
, S.
Akita
, K.
Nakajima
, and K.
Takei
, “A multitasking flexible sensor via reservoir computing
,” Adv. Mater.
34
, 2201663
(2022
). 18.
R.
Sakurai
, M.
Nishida
, H.
Sakurai
, Y.
Wakao
, N.
Akashi
, Y.
Kuniyoshi
, Y.
Minami
, and K.
Nakajima
, “Emulating a sensor using soft material dynamics: A reservoir computing approach to pneumatic artificial muscle,” in 2020 3rd IEEE International Conference on Soft Robotics (RoboSoft) (IEEE, 2020), pp. 710–717.19.
J. G.
Restrepo
and P. S.
Skardal
, “Suppressing unknown disturbances to dynamical systems using machine learning,” arXiv:2307.03690 (2023).20.
S.
Upadhyaya
and S.
Mohanty
, “Power quality disturbance localization using maximal overlap discrete wavelet transform,” in 2015 Annual IEEE India Conference (INDICON) (IEEE, New York City, 2015), pp. 1–6.21.
A. T.
Mathew
and M. N.
Aravind
, “PMU based disturbance analysis and fault localization of a large grid using wavelets and list processing,” in 2016 IEEE Region 10 Conference (TENCON) (IEEE, New York City, 2016), pp. 879–883.22.
W.-H.
Chen
, J.
Yang
, L.
Guo
, and S.
Li
, “Disturbance-observer-based control and related methods—An overview
,” IEEE Trans. Ind. Electron.
63
, 1083
(2015
). 23.
V. H.
Ferreira
, R.
Zanghi
, M. Z.
Fortes
, G. G.
Sotelo
, R.
da Boa Morte Silva
, J. C. S.
Souza
, C. H. C.
Guimaraes
, and S.
Gomes
, Jr., “A survey on intelligent system application to fault diagnosis in electric power system transmission lines
,” Electr. Power Syst. Res.
136
, 135
–153
(2016
). 24.
D.
Wang
, X.
Wang
, Y.
Zhang
, and L.
Jin
, “Detection of power grid disturbances and cyber-attacks based on machine learning
,” J. Inf. Secur. Appl.
46
, 45
–52
(2019
). 25.
R.
Delabays
, L.
Pagnier
, and M.
Tyloo
, “Locating line and node disturbances in networks of diffusively coupled dynamical agents
,” New J. Phys.
23
, 043037
(2021
). 26.
R.
Delabays
, L.
Pagnier
, and M.
Tyloo
, “Locating fast-varying line disturbances with the frequency mismatch
,” IFAC-PapersOnLine
55
, 270
(2022
). 27.
G.
Meurant
, The Ecology of Natural Disturbance and Patch Dynamics
(Academic Press
, New York
, 2012
).28.
C.
Battisti
, G.
Poeta
, and G.
Fanelli
, An Introduction to Disturbance Ecology
(Springer
, Cham
, 2016
), pp. 13–29.29.
T. R.
Bewley
and S.
Liu
, “Optimal and robust control and estimation of linear paths to transition
,” J. Fluid Mech.
365
, 305
(1998
). 30.
T. R.
Bewley
, R.
Temam
, and M.
Ziane
, “A general framework for robust control in fluid mechanics
,” Phys. D
138
, 360
(2000
). 31.
J.
Verbesselt
, R.
Hyndman
, A.
Zeileis
, and D.
Culvenor
, “Phenological change detection while accounting for abrupt and gradual trends in satellite image time series
,” Remote Sens. Environ.
114
, 2970
(2010
). 32.
T. R.
Nudell
and A.
Chakrabortty
, “A graph-theoretic algorithm for disturbance localization in large power grids using residue estimation,” in 2013 American Control Conference (IEEE, New York City, 2013), pp. 3467–3472.33.
H.-W.
Lee
, J.
Zhang
, and E.
Modiano
, “Data-driven localization and estimation of disturbance in the inter-connected power system,” in 2018 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm) (IEEE, New York City, 2018), pp. 1–6.34.
T.
Carroll
and L.
Pecora
, “Network structure effects in reservoir computers
,” Chaos
29
, 083130
(2019
). 35.
A.
Shirin
, I. S.
Klickstein
, and F.
Sorrentino
, “Stability analysis of reservoir computers dynamics via Lyapunov functions
,” Chaos
29
, 103147
(2019
). 36.
E.
Del Frate
, A.
Shirin
, and F.
Sorrentino
, “Reservoir computing with random and optimized time-shifts
,” Chaos
31
, 121103
(2021
). 37.
J.
Hart
, F.
Sorrentino
, and T.
Carroll
, “Time-shift selection for reservoir computing using a rank-revealing QR algorithm
,” Chaos
33
, 043133
(2023
). 38.
C.
Nathe
, C.
Pappu
, N. A.
Mecholsky
, J.
Hart
, T.
Carroll
, and F.
Sorrentino
, “Reservoir computing with noise
,” Chaos
33
, 041101
(2023
). 39.
J. C.
Canfield
, Active Disturbance Cancellation in Nonlinear Dynamical Systems Using Neural Networks
(University of New Hampshire
, 2003
).40.
J.
Hofbauer
, Evolutionary Games and Population Dynamics
(Cambridge University Press
, 2012
).41.
H. R.
Wilson
, “Hyperchaos in Wilson-Cowan oscillator circuits
,” J. Neurophysiol.
122
, 2449
(2019
). © 2023 Author(s). Published under an exclusive license by AIP Publishing.
2023
Author(s)
You do not currently have access to this content.
