Neural-Network-Aided Supermode Basis Tracking for Feedforward Equalization in Strongly Coupled Multicore Fibers

Authors

  • Abdullah ORAN Abdullah Gül Üniversitesi

DOI:

https://doi.org/10.4302/plp.v18i3.1392

Abstract

Environmental perturbations make the supermode basis of strongly coupled multicore fibers (SC-MCFs) drift in time, so that a receiver relying on a fixed basis suffers from inter-supermode crosstalk. We propose a feedforward receiver in which a small multilayer perceptron refines short sequences of pilot-based least-squares estimates of the channel unitary, and the refined estimate rotates the received core signals back into the supermode domain once per frame. In simulations of a six-core SC-MCF carrying 16-QAM, the tracker reduces the basis-estimation error by 2.3 dB with respect to pilot-only estimation, gains about 0.5 dB in required signal-to-noise ratio and extends the reach at the hard-decision FEC limit from 1480 to 1635 km. It remains within 0.5 dB of an adaptive multiple-input multiple-output (MIMO) equalizer while avoiding its symbol-rate update loop.

Full Text: PDF

References

  1. D.J. Richardson, J.M. Fini, L.E. Nelson, "Space-division multiplexing in optical fibres," Nat. Photonics, 7(5), 354 (2013). CrossRef
  2. C. Xia et al., "Supermodes for optical transmission," Opt. Express, 19(17), 16653 (2011). CrossRef
  3. T. Hayashi, Y. Tamura, T. Hasegawa, T. Taru, "Record-low spatial mode dispersion and ultra-low loss coupled multi-core fiber for ultra-long-haul transmission," J. Lightwave Technol., 35(3), 450 (2017). CrossRef
  4. R. Ryf et al., "Mode-division multiplexing over 96 km of few-mode fiber using coherent 6×6 MIMO processing," J. Lightwave Technol., 30(4), 521 (2012). CrossRef
  5. S.Ö. Arık, D. Askarov, J.M. Kahn, "Adaptive frequency-domain equalization in mode-division multiplexing systems," J. Lightwave Technol., 32(10), 1841 (2014). CrossRef
  6. D. Zibar, M. Piels, R. Jones, C. G. Schäffer, "Machine learning techniques in optical communication," J. Lightwave Technol., 34(6), 1442 (2016). CrossRef
  7. B. Karanov et al., "End-to-end deep learning of optical fiber communications," J. Lightwave Technol., 36(20), 4843 (2018). CrossRef
  8. T. Koike-Akino et al., "Neural turbo equalization: Deep learning for fiber-optic nonlinearity compensation," J. Lightwave Technol., 38(11), 3059 (2020). CrossRef
  9. N. J. Higham, "Computing the polar decomposition-with applications," SIAM J. Sci. Stat. Comput., 7(4), 1160 (1986). CrossRef
  10. K.-P. Ho, J.M. Kahn, "Statistics of group delays in multimode fiber with strong mode coupling," J. Lightwave Technol., 29(21), 3119 (2011). CrossRef

Downloads

Published

2026-10-18

How to Cite

[1]
A. ORAN, “Neural-Network-Aided Supermode Basis Tracking for Feedforward Equalization in Strongly Coupled Multicore Fibers”, Photonics Lett. Pol., vol. 18, no. 3, pp. 41–43, Oct. 2026.

Issue

Vol. 18 No. 3 (2026): Photonics Letters of Poland Vol.18 No.3

Section

Articles

License

Copyright (c) 2026 Abdullah ORAN

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).