This paper introduces a novel data-driven approximation method for the Koopman operator, called the RC-HAVOK algorithm. The RC-HAVOK algorithm combines Reservoir Computing (RC) and the Hankel Alternative View of Koopman (HAVOK) to reduce the size of the linear Koopman operator with a lower error rate. The accuracy and feasibility of the RC-HAVOK algorithm are assessed on Lorenz-like systems and dynamical systems with various nonlinearities, including the quadratic and cubic nonlinearities, hyperbolic tangent function, and piece-wise linear function. Implementation results reveal that the proposed model outperforms a range of other data-driven model identification algorithms, particularly when applied to commonly used Lorenz time series data.
REFERENCES
1.
W.
Ren
, X.
Na
, Y.
Li
, and M.
Han
, “Physics-informed hierarchical echo state network for predicting the dynamics of chaotic systems
,” Expert Syst. Appl.
228
, 120155
(2023
). 2.
B.
Ovilla-Martinez
, E.
Tlelo-Cuautle
, A. M.
Gonzalez-Zapata
, L. G.
de la Fraga
, and I.
Cruz-Vega
, “Enhanced FPGA implementation of echo state networks for chaotic time series prediction
,” Integration
92
, 48
–57
(2023
). 3.
C.
Marone
, M.
Cocco
, A.
Gualandi
, D.
Faranda
, and G.
Mengaldo
, “Deterministic and stochastic chaos characterize laboratory earthquakes
,” Earth Planet Sci. Lett.
604
, 117995
(2023
). 4.
G.
Ghosh
et al., “Secure surveillance systems using partial-regeneration-based non-dominated optimization and 5D-chaotic map
,” Symmetry (Basel)
13
, 1447
(2021
).5.
Y.
Liu
and H. H. C.
Iu
, “Antimonotonicity, chaos and multidirectional scroll attractor in autonomous odes chaotic system
,” IEEE Access
8
, 77171
–77178
(2020
). 6.
B. O.
Koopman
, “Hamiltonian systems and transformation in Hilbert space
,” Proc. Natl. Acad. Sci.
17
, 315
(1931
). 7.
I.
Mezić
, “Spectral properties of dynamical systems, model reduction and decompositions
,” Nonlinear Dyn.
41
, 309
–325
(2005
).8.
S.
Maćešić
, N.
Črnjarić Žic
, and I.
Mezić
, “Koopman operator spectrum for random dynamical systems
,” J. Nonlinear Sci.
30
, 2007
–2056
(2020
).9.
R.
Mohr
, M.
Budišić
and I.
Mezić
, “Applied Koopmanism
,” Chaos
22
, 047510
(2012
).10.
B.
Chen
et al., “Data-driven Koopman model predictive control for optimal operation of high-speed trains
,” IEEE Access
9
, 82233
–82248
(2021
). 11.
C. S.
Kallesøe
, J. N.
Jensen
, L. H.
Andersen
, C. M.
Jensen
, M. C.
Frederiksen
, and R.
Izadi-Zamanabadi
, “HAVOK model predictive control for time-delay systems with applications to district heating,” IFAC-PapersOnLine (22nd IFAC World Congress, 2022), Vol. 56, pp. 2238–2243.12.
M.
Yadegar
, M.
Bakhtiaridoust
, F. N.
Irani
, and N.
Meskin
, “Data-driven sensor fault detection and isolation of nonlinear systems: Deep neural-network Koopman operator
,” ET Control Theory Appl.
17
, 123
–132
(2022
).13.
X.
Xu
, X.
Liu
, Y.
Xiao
, X.
Zhang
, and J.
Liu
, “Deep neural networks with Koopman operators for modeling and control of autonomous vehicles
,” IEEE Trans. Intell. Veh.
8
, 153
–146
(2023
).14.
L. J.
Ratliff
, E.
Ling
, L.
Zheng
, and S.
Coogani
, “Koopman operator applications in signalized traffic systems
,” IEEE Trans. Intell. Transp. Syst.
23
, 3214
–3225
(2022
). 15.
R. G.
Moulder
, E.
Martynova
and S. M.
Boker
, “HAVOK extensions for psychological time series forecasting
,” Multivariate Behav. Res.
57
, 171
–172
(2022
). 16.
J.
Ding
, C.
Cheng
and Y.
Zhang
, “A Koopman operator approach for machinery health monitoring and prediction with noisy and low-dimensional industrial time series
,” Neurocomputing
406
, 204
–214
(2020
). 17.
N.
Cassamo
and J. W.
van Wingerden
, “On the potential of reduced order models for wind farm control: A Koopman dynamic mode decomposition approach
,” Energies (Basel)
13
, 6513
(2020
). 18.
X.
Li
, Y.
Liu
, Z.
Ping
, Z.
Yin
, and T.
Yang
, “Deep Koopman model predictive control for enhancing transient stability in power grids
,” Int. J. Robust Nonlinear Control
31
, 1964
–1978
(2021
). 19.
F.
Lunkeit
, A.
Tantet
, V.
Lucarini
, and H. A.
Dijkstra
, “Crisis of the chaotic attractor of a climate model: A transfer operator approach
,” Nonlinearity
31
, 2221
–2251
(2018
). 20.
P.
Schlatter
, H.
Azizpour
, H.
Eivazi
, L.
Guastoni
, and R.
Vinuesa
, “Recurrent neural networks and Koopman-based frameworks for temporal predictions in a low-order model of turbulence
,” Int. J. Heat Fluid Flow
90
, 108816
(2021
). 21.
S. H.
Son
, A.
Narasingam
and J. S. I.
Kwon
, “Data-driven feedback stabilisation of nonlinear systems: Koopman-based model predictive control
,” Int. J. Control
96
, 770
–781
(2023
).22.
A.
Surana
, “Koopman operator framework for time series modeling and analysis
,” J. Nonlinear Sci.
30
, 1973
–2006
(2020
). 23.
E.
Bollt
, “On explaining the surprising success of reservoir computing forecaster of chaos? The universal machine learning dynamical system with contrast to VAR and DMD
,” Chaos
31
, 013108
(2021
).24.
M.
Gulina
and A.
Mauroy
, “Two methods to approximate the Koopman operator with a reservoir computer
,” Chaos
31
, 023116
(2021
). 25.
J. H.
Tu
, K. K.
Chen
and C. W.
Rowley
, “Variants of dynamic mode decomposition: Boundary condition, Koopman, and Fourier analyses
,” J. Nonlinear Sci.
22
, 887
–915
(2012
). 26.
S.
Sosnowski
, P.
Bevanda
and S.
Hirche
, “Koopman operator dynamical models: Learning, analysis and control
,” Annu. Rev. Control
52
, 197
–212
(2021
). 27.
A. T.
Ihler
, D. J.
Alford-Lago
, C. W.
Curtis
, and O.
Issan
, “Deep learning enhanced dynamic mode decomposition
,” Chaos
32
, 033116
(2022
). 28.
I. G.
Kevrekidis
, M. O.
Williams
and C. W.
Rowley
, “A data-driven approximation of the Koopman operator: Extending dynamic mode decomposition
,” J. Nonlinear Sci.
25
, 1307
–1346
(2015
). 29.
E. M.
Bollt
, Q.
Li
, F.
Dietrich
, and I. G.
Kevrekidis
, “Extended dynamic mode decomposition with dictionary learning: A data-driven adaptive spectral decomposition of the Koopman operator
,” Chaos
27
, 103111
(2017
). 30.
J. L.
Proctor
, S. L.
Brunton
and J. N.
Kutz
, “Discovering governing equations from data by sparse identification of nonlinear dynamical systems
,” Proc. Natl. Acad Sci. U.S.A.
113
, 3932
–3937
(2016
). 31.
J. L.
Proctor
, S. L.
Brunton
and J. N.
Kutz
, “Sparse identification of nonlinear dynamics with control (SINDYc),” IFAC-PapersOnLine (10th IFAC Symposium on Nonlinear Control Systems NOLCOS, 2016), Vol. 49, pp. 710–715.32.
M.
Stender
, C.
Geier
and N.
Hoffmann
, “Data-driven reduced order modeling for mechanical oscillators using Koopman approaches
,” Front Appl. Math. Stat.
9
, 1124602
(2023
). 33.
J. N.
Kutz
, K.
Kaheman
and S. L.
Brunton
, “SINDy-PI: A robust algorithm for parallel implicit sparse identification of nonlinear dynamics
,” Proc. R. Soc. A
476
, 20200279
(2020
). 34.
J. L.
Proctor
, E.
Kaiser
, S. L.
Brunton
, B. W.
Brunton
, and J. N.
Kutz
, “Chaos as an intermittently forced linear system
,” Nat. Commun.
8
, 19
(2016
).35.
P.
Goyal
, A.
Forootani
and P.
Benner
, “A robust SINDy approach by combining neural networks and an integral form,” arXiv preprint arXiv:2309.07193 (2023).36.
G.
Tanaka
et al., “Recent advances in physical reservoir computing: A review
,” Neural Netw.
115
, 100
–123
(2019
). 37.
L.
Larger
et al., “Photonic information processing beyond turing: An optoelectronic implementation of reservoir computing
,” Opt. Express
20
, 3241
(2012
). 38.
E. A.
Viktorov
, A.
Locquet
, D. S.
Citrin
, G. O.
Danilenko
, A. V.
Kovalev
, and D.
Rontani
, “Impact of filtering on photonic time-delay reservoir computing
,” Chaos
33
, 013116
(2023
). 39.
J.
Bueno
, A.
Argyris
and I.
Fischer
, “Photonic machine learning implementation for signal recovery in optical communications
,” Sci. Rep.
8
, 8487
(2018
). 40.
M.
Small
, T.
Lymburn
, S. D.
Algar
, and T.
Jüngling
, “Reservoir computing with swarms
,” Chaos
31
, 033121
(2021
). 41.
T. L.
Carroll
and L. M.
Pecora
, “Network structure effects in reservoir computers
,” Chaos
29
, 083130
(2019
). 42.
E.
Martynova
, R. G.
Moulder
and S. M.
Boker
, “Extracting nonlinear dynamics from psychological and behavioral time series through HAVOK analysis
,” Multivariate Behav. Res.
58
, 441
–465
(2023
). 43.
E. N.
Lorenz
, “Deterministic nonperiodic flow
,” J. Atmos Sci.
20
, 130
–141
(1963
). 44.
L.
Liu
, C.
Liu
, T.
Liu
, and K.
Liu
, “A new chaotic attractor
,” Chaos Solitons Fractals
22
, 1031
–1038
(2004
). 45.
S.
Yan-Chen
, L.
Ling
and L.
Chong-Xin
, “Experimental confirmation of a new reversed butterfly-shaped attractor
,” Chin. Phys. Soc.
16
, 1897
–1900
(2007
). 46.
M.
Zhang
and Q.
Han
, “Dynamic analysis of an autonomous chaotic system with cubic nonlinearity
,” Optik (Stuttg)
27
, 4315
–43199
(2016
). 47.
T.
Matsumoto
, “The double scroll family
,” IEEE Trans. Circuits Syst.
33
, 1072
–1118
(1986
).48.
R.
Madan
, Chua’s Circuit: A Paradigm fir Chaos
(World Scientific
, 1993
).49.
Z.
Zhang
, Y.
Huang
, S.
Cai
, F.
Yu
, H.
Shen
, and S.
Du
, “A new multi-scroll Chua’s circuit with composite hyperbolic tangent-cubic nonlinearity: Complex dynamics, hardware implementation and image encryption application
,” Integration
81
, 71
–83
(2021
). 50.
C.
Wah Wu
, A.
Huang
, L.
Pivka
, and M.
Franz
, “Chua’s equation with cubic nonlinearity
,” Int. J. Bifurcation Chaos Appl. Sci. Eng.
6
, 2175
–2222
(1996
). 51.
J.
Song
, J.
Wu
, C.
Zhao
, J.
Yang
, J.
Zhao
, and H.
Leng
, “A hybrid method using HAVOK analysis and machine learning for predicting chaotic time series
,” Entropy
24
, 408
(2022
). 52.
S.
Ouala
et al., “Learning latent dynamics for partially observed chaotic systems
,” Chaos
30
, 103121
(2020
). 53.
M.
Li
and L.
Jiang
, “Deep learning nonlinear multiscale dynamic problems using Koopman operator
,” J. Comput. Phys.
446
, 110660
(2021
). 54.
J.
Axås
and G.
Haller
, “Model reduction for nonlinearizable dynamics via delay-embedded spectral submanifolds
,” Nonlinear Dyn.
111
, 22079
–22099
(2023
).55.
J. N.
Kutz
, E.
Kaiser
and S. L.
Brunton
, “Data-driven discovery of Koopman eigenfunctions for control
,” Mach. Learn. Sci. Technol.
2
, 035023
(2021
). © 2024 Author(s). Published under an exclusive license by AIP Publishing.
2024
Author(s)
You do not currently have access to this content.
