Machine learning classification of dynamical phases in a driven nonlinear Su-Schrieffer-Heeger lattice

Abstract

Driven nonlinear photonic lattices can settle into steady, symmetry-broken, periodic, or chaotic states, and mapping where each occurs in parameter space is key to device design. Brute-force mapping is slow and relies on hand-built criteria, while machine-learning classifiers are usually tested on different systems, so it is unclear which suits a new lattice. We therefore apply four classifiers to the same coherently driven Su-Schrieffer-Heeger (SSH) chain of Kerr resonators: a hand-built heuristic classifier based on Lyapunov exponents and spectral diagnostics, a supervised convolutional neural network (CNN) trained on the heuristic labels, an unsupervised library-building scheme based on augmented dynamic mode decomposition (aDMD), and an unsupervised Gaussian mixture model (GMM) on four dynamical invariants that include an aDMD reconstruction error. Using a converged heuristic diagram as the reference, the CNN reaches 98.0% held-out accuracy, while the two label-free methods reach adjusted Rand indices (ARIs) of 0.916 and 0.947, respectively, without seeing any labels. We show that the aDMD library cleanly resolves the stable and bistable phases and separates symmetric from symmetry-broken periodic oscillations, which the heuristic misses, though it cannot distinguish periodic from chaotic switching. We also find that a poorly converged reference understates the label-free methods' accuracy.

A machine-learned dynamical phase diagram of the one-dimensional nonlinear Schrödinger equation with quasiperiodic disorder and a static field
Marcos Pérez
arXiv11 Sep 2026PreprintCC BY 4.0Full textAtomic, molecular & optical physics Condensed matterarXiv
Even--odd classification of reentrant topology in a Su--Schrieffer--Heeger chain with integer-power quasiperiodic hopping
Yusheng Niu, Hui Liu, Zhihao Xu
arXiv2 Sep 2026PreprintCC BY 4.0Full textCondensed matterarXiv
Nonlinear polarization effects in optical fiber-based extreme learning machine
Lilian Emonin, Andrei Ermolaev, Mathilde Hary +5
Optics Letters25 Sep 2026Peer-reviewedPublisher termsFull textOptics & photonicsHAL
Failure classification of wind turbine operational conditions using hybrid machine learning
Marcela R Machado, Amanda Aryda S Sousa, Jefferson S Coelho +1
Wind Energy Science19 Oct 2026Peer-reviewedPublisher termsFull textGeneral physicsHAL
Digital Twins of Networked Dynamical Systems: Machine Learning Prediction of Synchronization Transitions in Coupled Chaotic Oscillators
Huawei Fan, Yao Du, Meng-Xia Bi +2
arXiv22 Oct 2026PreprintarXiv licenceFull textStatistical & nonlinear physicsarXiv

Cite

BibTeX RIS

BibTeX

@misc{izediuno2026machine,
  title = {{Machine learning classification of dynamical phases in a driven nonlinear Su-Schrieffer-Heeger lattice}},
  author = {Chukwunaedum Patrick Izediuno and Ghada H. Alharbi and Stephan Wong and Zeeshan Ahmad and Sunae So and Minkyung Kim and Sang Soon Oh},
  howpublished = {arXiv},
  year = {2026},
  month = nov,
  doi = {10.48550/arxiv.2611.08287},
  eprint = {2611.08287},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.08287},
  note = {CC BY 4.0},
}

RIS

TY  - UNPB
TI  - Machine learning classification of dynamical phases in a driven nonlinear Su-Schrieffer-Heeger lattice
AU  - Chukwunaedum Patrick Izediuno
AU  - Ghada H. Alharbi
AU  - Stephan Wong
AU  - Zeeshan Ahmad
AU  - Sunae So
AU  - Minkyung Kim
AU  - Sang Soon Oh
PY  - 2026
DA  - 2026/11/05
PB  - arXiv
DO  - 10.48550/arxiv.2611.08287
UR  - https://arxiv.org/abs/2611.08287
AB  - Driven nonlinear photonic lattices can settle into steady, symmetry-broken, periodic, or chaotic states, and mapping where each occurs in parameter space is key to device design. Brute-force mapping is slow and relies on hand-built criteria, while machine-learning classifiers are usually tested on different systems, so it is unclear which suits a new lattice. We therefore apply four classifiers to the same coherently driven Su-Schrieffer-Heeger (SSH) chain of Kerr resonators: a hand-built heuristic classifier based on Lyapunov exponents and spectral diagnostics, a supervised convolutional neural network (CNN) trained on the heuristic labels, an unsupervised library-building scheme based on augmented dynamic mode decomposition (aDMD), and an unsupervised Gaussian mixture model (GMM) on four dynamical invariants that include an aDMD reconstruction error. Using a converged heuristic diagram as the reference, the CNN reaches 98.0% held-out accuracy, while the two label-free methods reach adjusted Rand indices (ARIs) of 0.916 and 0.947, respectively, without seeing any labels. We show that the aDMD library cleanly resolves the stable and bistable phases and separates symmetric from symmetry-broken periodic oscillations, which the heuristic misses, though it cannot distinguish periodic from chaotic switching. We also find that a poorly converged reference understates the label-free methods' accuracy.
ER  -

Abstract

Related

Cite