Authors

Kirubel Solomon Tesfaye, Solomon M. Serunjogi, Mahmoud S. Rasras

Abstract

                Delay-based reservoir computing with temporally multiplexed virtual nodes provides a hardware-efficient platform for photonic implementations, yet parameter selection is often guided by empirical tuning. Here, we report a systematic experimental study of a single-node delay-based photonic reservoir computer that resolves the key physical and dynamical factors governing computational performance using the nonlinear channel equalization (NCE) benchmark. By mapping the bifurcation landscape of the system using port-Hamiltonian formulation, we establish a direct correspondence between operating regime and NCE performance as well as memory capacity, showing that optimal performance occurs near, but below, the onset of oscillatory and chaotic dynamics. We further provide a unified comparison of temporal optimization strategies, including delay–input period desynchronization and controlled local node coupling, within the same physical platform. At a 19 dB signal-to-noise ratio, the symbol error rate (SER) decreases with increasing node count before saturating beyond                    N                     ≈ 50, indicating task-dependent performance saturation and practical scaling constraints in delay-based reservoir architectures. A readout shifting strategy further improves the performance, achieving an SER of 0.003. These results provide physics-informed insights into parameter selection and architectural optimization in delay-based photonic reservoir computing for scalable, high-speed operation.

Citation

  • Journal: Optics Express
  • Year: 2026
  • Volume: 34
  • Issue: 13
  • Pages: 24726
  • Publisher: Optica Publishing Group
  • DOI: 10.1364/oe.593255

BibTeX

@article{Solomon_Tesfaye_2026,
  title={{High-performance delay-based photonic reservoir computing}},
  volume={34},
  ISSN={1094-4087},
  DOI={10.1364/oe.593255},
  number={13},
  journal={Optics Express},
  publisher={Optica Publishing Group},
  author={Solomon Tesfaye, Kirubel and Serunjogi, Solomon M. and Rasras, Mahmoud S.},
  year={2026},
  pages={24726}
}

Download the bib file

References

  • Mahadevkar SV, Khemani B, Patil S, Kotecha K, Vora DR, Abraham A, Gabralla LA (2022) A Review on Machine Learning Styles in Computer Vision—Techniques and Future Directions. IEEE Access 10:107293–107329. https://doi.org/10.1109/access.2022.320982 – 10.1109/access.2022.3209825
  • Voulodimos A, Doulamis N, Doulamis A, Protopapadakis E (2018) Deep Learning for Computer Vision: A Brief Review. Computational Intelligence and Neuroscience 2018:1–13. https://doi.org/10.1155/2018/706834 – 10.1155/2018/7068349
  • Amirabadi MA, Nezamalhosseini SA, Kahaei MH, Chen LR (2025) A Comprehensive Survey on Machine and Deep Learning for Optical Communications. IEEE Access 13:88794–88846. https://doi.org/10.1109/access.2025.356955 – 10.1109/access.2025.3569559
  • Ding J, Liu T, Xu T, Hu W, Popov S, Leeson MS, Zhao J, Xu T (2022) Intra-Channel Nonlinearity Mitigation in Optical Fiber Transmission Systems Using Perturbation-Based Neural Network. J Lightwave Technol 40(21):7106–7116. https://doi.org/10.1109/jlt.2022.320082 – 10.1109/jlt.2022.3200827
  • Wang H, Zhan Z, Hu F, Meng Y, Liu Z, Fu X, Liu Q (2023) Intelligent optoelectronic processor for orbital angular momentum spectrum measurement. PhotoniX 4(1). https://doi.org/10.1186/s43074-022-00079- – 10.1186/s43074-022-00079-9
  • Torfi A, Shirvani RA, Keneshloo Y, Tavaf N, Fox EA (2020) Natural Language Processing Advancements By Deep Learning: A Surve – 10.48550/arxiv.2003.01200
  • Ha N, Xu K, Ren G, Mitchell A, Ou JZ (2020) Machine Learning‐Enabled Smart Sensor Systems. Advanced Intelligent Systems 2(9). https://doi.org/10.1002/aisy.20200006 – 10.1002/aisy.202000063
  • Al-Ashwal NH, Al Soufy KAM, Hamza ME, Swillam MA (2023) Deep Learning for Optical Sensor Applications: A Review. Sensors 23(14):6486. https://doi.org/10.3390/s2314648 – 10.3390/s23146486
  • Bhaiyya M, Panigrahi D, Rewatkar P, Haick H (2024) Role of Machine Learning Assisted Biosensors in Point-of-Care-Testing For Clinical Decisions. ACS Sens 9(9):4495–4519. https://doi.org/10.1021/acssensors.4c0158 – 10.1021/acssensors.4c01582
  • Mienye ID, Swart TG, Obaido G (2024) Recurrent Neural Networks: A Comprehensive Review of Architectures, Variants, and Applications. Information 15(9):517. https://doi.org/10.3390/info1509051 – 10.3390/info15090517
  • Chen Y, Yi L, Ke J, Yang Z, Yang Y, Huang L, Zhuge Q, Hu W (2019) Reservoir computing system with double optoelectronic feedback loops. Opt Express 27(20):27431. https://doi.org/10.1364/oe.27.02743 – 10.1364/oe.27.027431
  • Van der Sande G, Brunner D, Soriano MC (2017) Advances in photonic reservoir computing. Nanophotonics 6(3):561–576. https://doi.org/10.1515/nanoph-2016-013 – 10.1515/nanoph-2016-0132
  • Hochreiter S (1998) The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions. Int J Unc Fuzz Knowl Based Syst 06(02):107–116. https://doi.org/10.1142/s021848859800009 – 10.1142/s0218488598000094
  • Jaeger H, Haas H (2004) Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication. Science 304(5667):78–80. https://doi.org/10.1126/science.109127 – 10.1126/science.1091277
  • Yan M, Huang C, Bienstman P, Tino P, Lin W, Sun J (2024) Emerging opportunities and challenges for the future of reservoir computing. Nat Commun 15(1). https://doi.org/10.1038/s41467-024-45187- – 10.1038/s41467-024-45187-1
  • Wang D, Nie Y, Hu G, Tsang HK, Huang C (2024) Ultrafast silicon photonic reservoir computing engine delivering over 200 TOPS. Nat Commun 15(1). https://doi.org/10.1038/s41467-024-55172- – 10.1038/s41467-024-55172-3
  • Nakajima M, Tanaka K, Hashimoto T (2021) Scalable reservoir computing on coherent linear photonic processor. Commun Phys 4(1). https://doi.org/10.1038/s42005-021-00519- – 10.1038/s42005-021-00519-1
  • Lugnan A, Katumba A, Laporte F, Freiberger M, Sackesyn S, Ma C, Gooskens E, Dambre J, Bienstman P (2020) Photonic neuromorphic information processing and reservoir computing. APL Photonics 5(2). https://doi.org/10.1063/1.512976 – 10.1063/1.5129762
  • El Srouji L, Krishnan A, Ravichandran R, Lee Y, On M, Xiao X, Ben Yoo SJ (2022) Photonic and optoelectronic neuromorphic computing. APL Photonics 7(5). https://doi.org/10.1063/5.007209 – 10.1063/5.0072090
  • Atwany M, Pardo S, Serunjogi S, Rasras M (2024) A review of emerging trends in photonic deep learning accelerators. Front Phys 12. https://doi.org/10.3389/fphy.2024.136909 – 10.3389/fphy.2024.1369099
  • Demertzis K, Papadopoulos GD, Iliadis L, Magafas L (2022) A Comprehensive Survey on Nanophotonic Neural Networks: Architectures, Training Methods, Optimization, and Activations Functions. Sensors 22(3):720. https://doi.org/10.3390/s2203072 – 10.3390/s22030720
  • Khonina SN, Kazanskiy NL, Skidanov RV, Butt MA (2024) Exploring Types of Photonic Neural Networks for Imaging and Computing—A Review. Nanomaterials 14(8):697. https://doi.org/10.3390/nano1408069 – 10.3390/nano14080697
  • Appeltant L, Soriano MC, Van der Sande G, Danckaert J, Massar S, Dambre J, Schrauwen B, Mirasso CR, Fischer I (2011) Information processing using a single dynamical node as complex system. Nat Commun 2(1). https://doi.org/10.1038/ncomms147 – 10.1038/ncomms1476
  • Vandoorne K, Mechet P, Van Vaerenbergh T, Fiers M, Morthier G, Verstraeten D, Schrauwen B, Dambre J, Bienstman P (2014) Experimental demonstration of reservoir computing on a silicon photonics chip. Nat Commun 5(1). https://doi.org/10.1038/ncomms454 – 10.1038/ncomms4541
  • Sunada S, Uchida A (2019) Photonic reservoir computing based on nonlinear wave dynamics at microscale. Sci Rep 9(1). https://doi.org/10.1038/s41598-019-55247- – 10.1038/s41598-019-55247-y
  • Paquot Y, Duport F, Smerieri A, Dambre J, Schrauwen B, Haelterman M, Massar S (2012) Optoelectronic Reservoir Computing. Sci Rep 2(1). https://doi.org/10.1038/srep0028 – 10.1038/srep00287
  • Zhu P, Wang H, Ji Y, Gao G (2024) A Novel Performance Enhancement Optical Reservoir Computing System Based on Three-Loop Mutual Coupling Structure. J Lightwave Technol 42(9):3151–3162. https://doi.org/10.1109/jlt.2024.335774 – 10.1109/jlt.2024.3357745
  • Yuan X, Jiang L, Yan L, Li S, Zhang L, Yi A, Pan W, Luo B (2024) The optoelectronic reservoir computing system based on parallel multi-time-delay feedback loops for time-series prediction and optical performance monitoring. Chaos, Solitons & Fractals 186:115306. https://doi.org/10.1016/j.chaos.2024.11530 – 10.1016/j.chaos.2024.115306
  • Donati G, Argyris A, Mancinelli M, Mirasso CR, Pavesi L (2024) Time delay reservoir computing with a silicon microring resonator and a fiber-based optical feedback loop. Opt Express 32(8):13419. https://doi.org/10.1364/oe.51461 – 10.1364/oe.514617
  • Chembo YK (2020) Machine learning based on reservoir computing with time-delayed optoelectronic and photonic systems. Chaos: An Interdisciplinary Journal of Nonlinear Science 30(1). https://doi.org/10.1063/1.512078 – 10.1063/1.5120788
  • Duport F, Schneider B, Smerieri A, Haelterman M, Massar S (2012) All-optical reservoir computing. Opt Express 20(20):22783. https://doi.org/10.1364/oe.20.02278 – 10.1364/oe.20.022783
  • Larger L, Soriano MC, Brunner D, Appeltant L, Gutierrez JM, Pesquera L, Mirasso CR, Fischer I (2012) Photonic information processing beyond Turing: an optoelectronic implementation of reservoir computing. Opt Express 20(3):3241. https://doi.org/10.1364/oe.20.00324 – 10.1364/oe.20.003241
  • Dai H, Chembo YK (2022) RF Fingerprinting Based on Reservoir Computing Using Narrowband Optoelectronic Oscillators. J Lightwave Technol 40(21):7060–7071. https://doi.org/10.1109/jlt.2022.319896 – 10.1109/jlt.2022.3198967
  • Qin J, Zhao Q, Yin H, Jin Y, Liu C (2017) Numerical Simulation and Experiment on Optical Packet Header Recognition Utilizing Reservoir Computing Based on Optoelectronic Feedback. IEEE Photonics J 9(1):1–11. https://doi.org/10.1109/jphot.2017.265802 – 10.1109/jphot.2017.2658028
  • Desai SA, Mattheakis M, Sondak D, Protopapas P, Roberts SJ (2021) Port-Hamiltonian neural networks for learning explicit time-dependent dynamical systems. Phys Rev E 104(3). https://doi.org/10.1103/physreve.104.03431 – 10.1103/physreve.104.034312
  • van der Schaft A, Jeltsema D (2014) Port-Hamiltonian Systems Theory: An Introductory Overview. Foundations and Trends® in Systems and Control 1(2–3):173–378. https://doi.org/10.1561/260000000 – 10.1561/2600000002
  • Peil M, Jacquot M, Chembo YK, Larger L, Erneux T (2009) Routes to chaos and multiple time scale dynamics in broadband bandpass nonlinear delay electro-optic oscillators. Phys Rev E 79(2). https://doi.org/10.1103/physreve.79.02620 – 10.1103/physreve.79.026208
  • Chembo Kouomou Y, Colet P, Larger L, Gastaud N (2005) Chaotic Breathers in Delayed Electro-Optical Systems. Phys Rev Lett 95(20). https://doi.org/10.1103/physrevlett.95.20390 – 10.1103/physrevlett.95.203903
  • Callan KE, Illing L, Gao Z, Gauthier DJ, Schöll E (2010) Broadband Chaos Generated by an Optoelectronic Oscillator. Phys Rev Lett 104(11). https://doi.org/10.1103/physrevlett.104.11390 – 10.1103/physrevlett.104.113901
  • Harkhoe K, Verschaffelt G, Katumba A, Bienstman P, Van der Sande G (2020) Demonstrating delay-based reservoir computing using a compact photonic integrated chip. Opt Express 28(3):3086. https://doi.org/10.1364/oe.38255 – 10.1364/oe.382556
  • Larger L, Baylón-Fuentes A, Martinenghi R, Udaltsov VS, Chembo YK, Jacquot M (2017) High-Speed Photonic Reservoir Computing Using a Time-Delay-Based Architecture: Million Words per Second Classification. Phys Rev X 7(1). https://doi.org/10.1103/physrevx.7.01101 – 10.1103/physrevx.7.011015
  • Zhang M, Liang Z, Huang ZR (2023) Hardware optimization for photonic time-delay reservoir computer dynamics. Neuromorph Comput Eng 3(1):014008. https://doi.org/10.1088/2634-4386/acb8d – 10.1088/2634-4386/acb8d7
  • Vinckier Q, Duport F, Smerieri A, Vandoorne K, Bienstman P, Haelterman M, Massar S (2015) High-performance photonic reservoir computer based on a coherently driven passive cavity. Optica 2(5):438. https://doi.org/10.1364/optica.2.00043 – 10.1364/optica.2.000438
  • Sugano C, Kanno K, Uchida A (2020) Reservoir Computing Using Multiple Lasers With Feedback on a Photonic Integrated Circuit. IEEE J Select Topics Quantum Electron 26(1):1–9. https://doi.org/10.1109/jstqe.2019.292917 – 10.1109/jstqe.2019.2929179
  • Soriano MC, Ortín S, Brunner D, Larger L, Mirasso CR, Fischer I, Pesquera L (2013) Optoelectronic reservoir computing: tackling noise-induced performance degradation. Opt Express 21(1):12. https://doi.org/10.1364/oe.21.00001 – 10.1364/oe.21.000012
  • Tezuka M, Kanno K, Bunsen M (2016) Reservoir computing with a slowly modulated mask signal for preprocessing using a mutually coupled optoelectronic system. Jpn J Appl Phys 55(8S3):08RE06. https://doi.org/10.7567/jjap.55.08re0 – 10.7567/jjap.55.08re06
  • Duport F, Smerieri A, Akrout A, Haelterman M, Massar S (2016) Fully analogue photonic reservoir computer. Sci Rep 6(1). https://doi.org/10.1038/srep2238 – 10.1038/srep22381
  • Kuriki Y, Nakayama J, Takano K, Uchida A (2018) Impact of input mask signals on delay-based photonic reservoir computing with semiconductor lasers. Opt Express 26(5):5777. https://doi.org/10.1364/oe.26.00577 – 10.1364/oe.26.005777
  • van der Schaft AJ, Maschke BM (2013) Port-Hamiltonian Systems on Graphs. SIAM J Control Optim 51(2):906–937. https://doi.org/10.1137/11084009 – 10.1137/110840091
  • Tang D, Liang E, Lu Q, Zhao H, Li Z (2024) Complex dynamics in nonlinear small time-delayed optoelectronic oscillator and application in fast reservoir computing and pulse generation. Sci Rep 14(1). https://doi.org/10.1038/s41598-024-69585- – 10.1038/s41598-024-69585-z
  • Jaeger, (2001)
  • Dambre J, Verstraeten D, Schrauwen B, Massar S (2012) Information Processing Capacity of Dynamical Systems. Sci Rep 2(1). https://doi.org/10.1038/srep0051 – 10.1038/srep00514
  • Stelzer F, Röhm A, Lüdge K, Yanchuk S (2020) Performance boost of time-delay reservoir computing by non-resonant clock cycle. Neural Networks 124:158–169. https://doi.org/10.1016/j.neunet.2020.01.01 – 10.1016/j.neunet.2020.01.010
  • Köster F, Yanchuk S, Lüdge K (2021) Insight into delay based reservoir computing via eigenvalue analysis. J Phys Photonics 3(2):024011. https://doi.org/10.1088/2515-7647/abf23 – 10.1088/2515-7647/abf237
  • Ortín S, Soriano MC, Pesquera L, Brunner D, San-Martín D, Fischer I, Mirasso CR, Gutiérrez JM (2015) A Unified Framework for Reservoir Computing and Extreme Learning Machines based on a Single Time-delayed Neuron. Sci Rep 5(1). https://doi.org/10.1038/srep1494 – 10.1038/srep14945