We propose a method based on autoencoders to reconstruct attractors from recorded footage, preserving the topology of the underlying phase space. We provide theoretical support and test the method with (i) footage of the temperature and stream function fields involved in the Lorenz atmospheric convection problem and (ii) a time series obtained by integrating the Rössler equations.
REFERENCES
1.
J.
Guckenheimer
and P.
Holmes
, Nonlinear Oscillations, Dynamical Systems, and Bifurcations of Vector Fields
(Springer Science & Business Media
, 2013
), Vol. 42.2.
H. G.
Solari
, M. A.
Natiello
, and G. B.
Mindlin
, Nonlinear Dynamics: A Two-Way Trip from Physics to Math
(Taylor & Francis Group
, 1996
).3.
H. D.
Abarbanel
, R.
Brown
, J. J.
Sidorowich
, and L. S.
Tsimring
, “The analysis of observed chaotic data in physical systems
,” Rev. Mod. Phys.
65
, 1331
(1993
). 4.
P.
Grassberger
and I.
Procaccia
, “Characterization of strange attractors
,” Phys. Rev. Lett.
50
, 346
(1983
). 5.
A.
Wolf
, J. B.
Swift
, H. L.
Swinney
, and J. A.
Vastano
, “Determining Lyapunov exponents from a time series
,” Phys. D
16
, 285
–317
(1985
). 6.
T. C.
Halsey
, M. H.
Jensen
, L. P.
Kadanoff
, I.
Procaccia
, and B. I.
Shraiman
, “Fractal measures and their singularities: The characterization of strange sets
,” Phys. Rev. A
33
, 1141
(1986
). 7.
R.
Gilmore
and M.
Lefranc
, The Topology of Chaos: Alice in Stretch and Squeezeland
(John Wiley & Sons
, 2012
).8.
G. B.
Mindlin
, X.-J.
Hou
, H. G.
Solari
, R.
Gilmore
, and N.
Tufillaro
, “Classification of strange attractors by integers
,” Phys. Rev. Lett.
64
, 2350
(1990
). 9.
Z.
Lu
, B. R.
Hunt
, and E.
Ott
, “Attractor reconstruction by machine learning
,” Chaos
28
, 061104
(2018
). 10.
S. L.
Brunton
and J. N.
Kutz
, Data-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control
(Cambridge University Press
, Cambridge, England
, 2019
).11.
K.
Champion
, B.
Lusch
, J. N.
Kutz
, and S. L.
Brunton
, “Data-driven discovery of coordinates and governing equations
,” Proc. Natl. Acad. Sci. U.S.A.
116
, 22445
–22451
(2019
). 12.
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
, 063151
(2020
). 13.
L.
Agostini
, “Exploration and prediction of fluid dynamical systems using auto-encoder technology
,” Phys. Fluids
32
, 067103
(2020
). 14.
Z.
Liu
and M.
Tegmark
, “Machine learning conservation laws from trajectories
,” Phys. Rev. Lett.
126
, 180604
(2021
). 15.
D.
Floryan
and M. D.
Graham
, “Data-driven discovery of intrinsic dynamics
,” Nat. Mach. Intell.
4
, 1113
–1120
(2022
). 16.
C. D.
Young
and M. D.
Graham
, “Deep learning delay coordinate dynamics for chaotic attractors from partial observable data
,” Phys. Rev. E
107
, 034215
(2023
). 17.
C.
Pagliantini
and S.
Jain
, “Nonlinear model reduction from equations and data
,” Chaos
34
, 090401
(2024
). 18.
G. E.
Hinton
and R. R.
Salakhutdinov
, “Reducing the dimensionality of data with neural networks
,” Science
313
, 504
–507
(2006
). 19.
W.
Chen
, H.
Sidky
, and A. L.
Ferguson
, “Capabilities and limitations of time-lagged autoencoders for slow mode discovery in dynamical systems
,” J. Chem. Phys.
151
, 1
–14
(2019
). 20.
N.
Almazova
, G. D.
Barmparis
, and G. P.
Tsironis
, “Analysis of chaotic dynamical systems with autoencoders
,” Chaos
31
, 103109
(2021
). 21.
K.
Zeng
, C. E. P.
De Jesús
, A. J.
Fox
, and M. D.
Graham
, “Autoencoders for discovering manifold dimension and coordinates in data from complex dynamical systems
,” Mach. Learn.: Sci. Technol.
5
, 025053
(2024
). 22.
N. B.
Erichson
, M.
Muehlebach
, and M. W.
Mahoney
, “Physics-informed autoencoders for Lyapunov-stable fluid flow prediction,” arXiv:1905.10866 (2019).23.
W.
Gilpin
, “Deep reconstruction of strange attractors from time series,” in Advances in Neural Information Processing Systems 33 (NeurIPS 2020) (Curran Associates, 2020), pp. 204–216.24.
J. T.
Quinn
, “Autoencoder embeddings in dynamical systems: A comparison of current frameworks,” master’s thesis (University of Colorado at Boulder, 2024).25.
J.
Bakarji
, K.
Champion
, J.
Nathan Kutz
, and S. L.
Brunton
, “Discovering governing equations from partial measurements with deep delay autoencoders
,” Proc. R. Soc. A
479
, 20230422
(2023
). 26.
P.
Goyal
and P.
Benner
, “Generalized quadratic embeddings for nonlinear dynamics using deep learning
,” Phys. D
463
, 134158
(2024
). 27.
S. E.
Otto
, G. R.
Macchio
, and C. W.
Rowley
, “Learning nonlinear projections for reduced-order modeling of dynamical systems using constrained autoencoders
,” Chaos
33
, 113130
(2023
). 28.
K.
Lee
and K. T.
Carlberg
, “Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders
,” J. Comput. Phys.
404
, 108973
(2020
). 29.
D.
Sondak
and P.
Protopapas
, “Learning a reduced basis of dynamical systems using an autoencoder
,” Phys. Rev. E
104
, 034202
(2021
). 30.
M. A.
Mendez
, A.
Ianiro
, B. R.
Noack
, and S. L.
Brunton
, Data-Driven Fluid Mechanics: Combining First Principles and Machine Learning
(Cambridge University Press
, 2023
).31.
G.
Uribarri
and G. B.
Mindlin
, “The structure of reconstructed flows in latent spaces
,” Chaos
30
, 093109
(2020
). 32.
F.
Fainstein
, J.
Catoni
, C. P.
Elemans
, and G. B.
Mindlin
, “The reconstruction of flows from spatiotemporal data by autoencoders
,” Chaos, Solitons Fractals
176
, 114115
(2023
). 33.
E. N.
Lorenz
, “Deterministic nonperiodic flow
,” J. Atmos. Sci.
20
, 130
–141
(1963
). 34.
O. E.
Rössler
, “An equation for continuous chaos
,” Phys. Lett. A
57
, 397
–398
(1976
). 35.
Y.
LeCun
, Y.
Bengio
, and G.
Hinton
, “Deep learning
,” Nature
521
, 436
–444
(2015
). 36.
Y.
Bengio
, I.
Goodfellow
, and A.
Courville
, Deep Learning
(MIT Press
, Cambridge, MA
, 2017
), Vol. 1.37.
38.
V. I.
Arnold
, Geometrical Methods in the Theory of Ordinary Differential Equations
(Springer Science & Business Media
, 2012
), Vol. 250.39.
M.
Belkin
, D.
Hsu
, S.
Ma
, and S.
Mandal
, “Reconciling modern machine-learning practice and the classical bias-variance trade-off
,” Proc. Natl. Acad. Sci. U.S.A.
116
, 15849
–15854
(2019
). 40.
A.
Radhakrishnan
, M.
Belkin
, and C.
Uhler
, “Overparameterized neural networks implement associative memory
,” Proc. Natl. Acad. Sci. U.S.A.
117
, 27163
(2020
). 41.
M.
Belkin
, “Fit without fear: Remarkable mathematical phenomena of deep learning through the prism of interpolation
,” Acta Numer.
30
, 203
–248
(2021
). 42.
A.
Radhakrishnan
, K.
Yang
, M.
Belkin
, and C.
Uhler
, “Memorization in overparameterized autoencoders,” in Deep Phenomena Workshop, International Conference on Machine Learning (The International Machine Learning Society, 2019).43.
J. S.
Birman
and R. F.
Williams
, “Knotted periodic orbits in dynamical systems I: Lorenz’s equations
,” Topology
22
, 47
–82
(1983
). 44.
For software implementation to compute linking numbers, see https://github.com/gon-uri/linking_number.
45.
F.
Takens
, “Detecting strange attractors in turbulence,” in Dynamical Systems and Turbulence, Warwick 1980 (Springer, 2006), pp. 366–381.© 2025 Author(s). Published under an exclusive license by AIP Publishing.
2025
Author(s)
You do not currently have access to this content.
