Autoencoder-driven MIMO architecture for underwater optical wireless communications systems

Haneen Majid Shalol; Mustafa Dh. Hassib; Ahmed Al Asadi

doi:10.1515/joc-2025-0399

Article

Autoencoder-driven MIMO architecture for underwater optical wireless communications systems

Haneen Majid Shalol , Mustafa Dh. Hassib and Ahmed Al Asadi

Published/Copyright: December 31, 2025

Published by

Become an author with De Gruyter Brill

Submit Manuscript Author Information

From the journal Journal of Optical Communications

Abstract

A deep autoencoder-based multiple-input multiple-output (AE-MIMO) architecture is proposed for underwater wireless optical communication (UWOC) systems operating in low-noise, turbulence-affected channels. A low-noise regime is assumed (normalized noise variance σ n 2 ∈ [ 1 0 − 4 , 1 0 − 2 ] ). Unlike conventional schemes, the model jointly learns transmitter and receiver mappings via a differentiable neural pipeline informed by Beer–Lambert attenuation, log-normal turbulence, and additive Gaussian noise. Evaluations across SISO, SIMO, MISO, and MIMO configurations demonstrate that AE-aided schemes consistently outperform conventional baselines by achieving 3–4 dB lower signal-to-noise ratio (SNR) requirements at symbol error rate (SER) ≤ 1 0 − 3 . In particular, the proposed 3 × 2 AE-MIMO achieves a 22 % increase in effective 3 dB bandwidth, a fifty-three-fold reduction in SER at moderate SNR, 56 % faster convergence, and requires 7 dB less SNR to maintain SER ≤ 1 0 − 3 in turbid water. These gains align with diversity gain and capacity scaling predictions, confirming the model’s physical validity. The framework exhibits strong robustness against attenuation, scattering, and fading, making it suitable for high-throughput, low-latency underwater applications such as autonomous vehicle coordination, IoT sensor networks, and real-time inspection.

Keywords: underwater optical communications; MIMO systems; autoencoders; deep learning; neural receivers

Corresponding author: Haneen Majid Shalol, Department of Communications Engineering, University of Technology, Baghdad, Iraq, E-mail: coe.23.06@grad.uotechnology.edu.iq

Acknowledgments

The author gratefully acknowledges the support of the Department of Communication Engineering, University of Technology, Baghdad, Iraq.

Research ethics: Not applicable. This study did not involve human participants or animal experiments.
Informed consent: Not applicable. No human participants or personal data were involved in this study.
Author contributions: The authors have accepted responsibility for the entire content of this manuscript and approved its submission.
Use of Large Language Models, AI and Machine Learning Tools: None declared.
Conflict of interest: The authors state no conflict of interest.
Research funding: None declared.
Data availability: Not applicable. The study is based on simulations and does not include raw or experimental data.

References

1. Mohamed, AG, Abd El-Mottaleb, SA, Singh, M, Ahmed, HY, Zeghid, M, Abdulkawi, WM, et al.. Chaos fractal digital image encryption transmission in underwater optical wireless communication system. IEEE Access 2024;12:117541–59. https://doi.org/10.1109/ACCESS.2024.3446836.Search in Google Scholar

2. Yang, L, Bi, Z, Liang, X, Zhao, L, Zhang, J, Peng, J. Advancements in underwater optical wireless communication: channel modeling, PAPR reduction, and simulations with OFDM. IEEE Photon J 2024;16:1–8. https://doi.org/10.1109/JPHOT.2024.3475448.Search in Google Scholar

3. Al-Karawi, Y, Alhumaima, RS, Al-Raweshidy, H. Quality of service of quantum entanglement in mobile networks. IEEE Access 2021;9:167242–51. https://doi.org/10.1109/ACCESS.2021.3136782.Search in Google Scholar

4. Zhang, J, Xu, Z, Liu, Y, Yang, Y, Zhou, W, Yang, Z, et al.. A general multilayer analytical radiative transfer-based model for reflectance over shallow water. IEEE Trans Geosci Remote Sens 2024;62:1–20. https://doi.org/10.1109/TGRS.2024.3389683.Search in Google Scholar

5. Almaymoni, N, Alkhazragi, O, Gunawan, WH, Melinte, G, Ng, TK, Ooi, BS. High-speed 645-nm VCSELs for low-scattering-loss Gb/s underwater wireless optical communications. IEEE Photon Technol Lett 2024;36:377–80. https://doi.org/10.1109/LPT.2024.3360229.Search in Google Scholar

6. Saiyyed, R, Sindhwani, M, Ambudkar, B, Sachdeva, S, Kumar, A, Shukla, MK. Free space optical communication system: a review of practical constraints, applications, and challenges. J Opt Commun 2025;46:357–63. https://doi.org/10.1515/joc-2024-0011.Search in Google Scholar

7. Shen, L, Xia, H, Zhang, X, Zhao, Y, Li, N, Kong, SG, et al.. U2PNet: an unsupervised underwater image-restoration network using polarization. IEEE Trans Cybern 2024;54:5164–77. https://doi.org/10.1109/TCYB.2024.3365693.Search in Google Scholar PubMed

8. Wang, J, Du, H, Niyato, D, Kang, J, Cui, S, Shen, X, et al.. Generative AI for integrated sensing and communication: insights from the physical layer perspective. IEEE Trans Geosci Remote Sens 2024;31:246–55. https://doi.org/10.1109/MWC.013.2300485.Search in Google Scholar

9. Islam, N, Shin, S. Deep learning in physical layer: review on data driven end-to-end communication systems and their enabling semantic applications. IEEE Open J Commun Soc 2024;5:4207–40. https://doi.org/10.1109/OJCOMS.2024.3425314.Search in Google Scholar

10. Vijayalakshmi, BA, Lekashri, S, Gomathi, M, Ashwini, R, Arunsundar, B, Nesasudha, M. VLC system using LEDs for transmitting underwater information. J Opt 2024;54:2187–96. https://doi.org/10.1007/s12596-024-01947-2.Search in Google Scholar

11. Ai, B, Liu, X, Wen, Z, Wang, L, Ma, H, Lv, G. A novel coral reef classification method combining radiative transfer model with deep learning. IEEE J Sel Top Appl Earth Obs Remote Sens 2024;17:13400–12. https://doi.org/10.1109/JSTARS.2024.3430899.Search in Google Scholar

12. Al-Karawi, Y, Alhumaima, RS, Hussein Khudair, K, Ahmed, A. Optimizing the placement of cloud data center in virtualized environment. Int J Electr Comput Eng 2022;12:3276–86. https://doi.org/10.11591/ijece.v12i3.pp3276-3286.Search in Google Scholar

13. Chen, D, Li, Z, Wang, J, Lu, H, Hao, R, Fan, K, et al.. Experimental study of laser spot tracking for underwater optical wireless communication. Opt Express 2024;32:6409–22. https://doi.org/10.1364/OE.514542.Search in Google Scholar PubMed

14. Theocharidis, T, Kavallieratou, E. Underwater communication technologies: a review. Telecommun Syst 2025;88:54. https://doi.org/10.1007/s11235-025-01279-x.Search in Google Scholar

15. Hu, J, Guo, Z, Shi, J, Jiang, X, Chen, Q, Chen, H, et al.. A metasurface-based full-color circular auto-focusing airy beam transmitter for stable high-speed underwater wireless optical communications. Nat Commun 2024;15:2944. https://doi.org/10.1038/s41467-024-47105-x.Search in Google Scholar PubMed PubMed Central

16. Mahmud, M, Younis, M, Ahmed, M, Choa, FS. Deep learning-based joint channel equalization and symbol detection for air-water optoacoustic communications. IEEE Trans Cogn Commun Netw 2025;11:1482–92. https://doi.org/10.1109/TCCN.2024.3480036.Search in Google Scholar

17. Wibisono, A, Alsharif, MH, Song, HK, Lee, BM. A survey on underwater wireless power and data transfer system. IEEE Access 2024;12:34942–57. https://doi.org/10.1109/ACCESS.2024.3373791.Search in Google Scholar

18. Bi, S, Hieronymi, M. Holistic optical water type classification for ocean, coastal, and inland waters. Limnol Oceanogr 2024;69:1547–61. https://doi.org/10.1002/lno.12606.Search in Google Scholar

19. Rose, KC. Light in inland waters. In: Jones, ID, Smol, JP, editors. Wetzel’s limnology, 4th ed. San Diego, CA, USA: Academic Press; 2024:75–94 pp.10.1016/B978-0-12-822701-5.00006-9Search in Google Scholar

20. Ji, J, Dai, Y, Qiu, Y. A distance adaptive dual-hop routing algorithm for underwater optical wireless networks. Opt Switch Netw 2024;54:100782. https://doi.org/10.1016/j.osn.2024.100782.Search in Google Scholar

21. Alhosani, A, Alshehhi, F, Almenhali, M, Abu Hilal, H. Optical communication advancements in free space and applications of free space orbital technology. J Inst Eng: Ser B 2025;106:805–14. https://doi.org/10.1007/s40031-024-01137-5.Search in Google Scholar

22. Zhao, C, Du, H, Niyato, D, Kang, J, Xiong, Z, Kim, DI, et al.. Generative AI for secure physical layer communications: a survey. IEEE Trans Cogn Commun Netw 2025;11:3–26. https://doi.org/10.1109/TCCN.2024.3438379.Search in Google Scholar

23. Kaushal, H, Kaddoum, G. Underwater optical wireless communication. IEEE Access 2016;4:1518–47. https://doi.org/10.1109/ACCESS.2016.2552538.Search in Google Scholar

24. Zhao, X, Qi, Z, Pompili, D. Link adaptation in underwater wireless optical communications based on deep learning. Comput Netw 2024;242:110233. https://doi.org/10.1016/j.comnet.2024.110233.Search in Google Scholar

25. Li, B, Fu, M, Sun, M, Liu, X, Zheng, B. Experimental demonstration of a MIMO-OFDM underwater optical communication system for reducing alignment angle requirements. IEEE Photon J 2024;16:1–8. https://doi.org/10.1109/JPHOT.2024.3356723.Search in Google Scholar

26. Aala, S, Sikhakolli, SK, Chinnadurai, S, Deshpande, A, Elumalai, K, Sarker, MAL, et al.. SVHAE: spectral variability-aware hybrid autoencoder for hyperspectral underwater target detection. IEEE Access 2025:1. https://doi.org/10.1109/ACCESS.2025.3587438.Search in Google Scholar

27. Khan, FMA, Abou-Zeid, H, Hassan, SA. Deep compression for efficient and accelerated over-the-air federated learning. IEEE Internet Things J 2024;11:25802–17. https://doi.org/10.1109/JIOT.2024.3373460.Search in Google Scholar

28. Khonina, SN, Kazanskiy, NL, Butt, MA. Exploring diffractive optical elements and their potential in free space optics and imaging – a comprehensive review. Laser Photon Rev 2024;18:2400377. https://doi.org/10.1002/lpor.202400377.Search in Google Scholar

29. Illi, E, Qaraqe, M. On the physical layer security of underwater optical wireless communication networks. IEEE J Ocean Eng 2024;49:583–91. https://doi.org/10.1109/JOE.2023.3341461.Search in Google Scholar

30. Ata, Y, Baykal, Y, Gökçe, MC. Analysis of optical wireless MIMO communication in underwater medium. IEEE Internet Things J 2024;11:20660–72. https://doi.org/10.1109/JIOT.2024.3371112.Search in Google Scholar

31. Kaur, R, Bansal, B, Majhi, S, Jain, S, Huang, C, Yuen, C. A survey on reconfigurable intelligent surface for physical layer security of next-generation wireless communications. IEEE Open J Veh Technol 2024;5:172–99. https://doi.org/10.1109/OJVT.2023.3348658.Search in Google Scholar

32. Abrar, AS, Rani, MSD. Underwater visible light communication: recent advancements and channel modeling. J Opt 2025;1–15. https://doi.org/10.1007/s12596-025-02839-9.Search in Google Scholar

33. Cheng, Q, Shi, Z, Yuan, J, Lin, H. MIMO-ODDM signal detection: a spatial-based generative adversarial network approach. IEEE Trans Wireless Commun 2024;23:12499–512. https://doi.org/10.1109/TWC.2024.3392881.Search in Google Scholar

34. Zayed, MM, Mohsen, S, Alghuried, A, Hijry, H, Shokair, M. IoUT-oriented an efficient CNN model for modulation schemes recognition in optical wireless communication systems. IEEE Access 2024;12:186836–55. https://doi.org/10.1109/ACCESS.2024.3515895.Search in Google Scholar

35. Al-Karawi, Y, Al-Raweshidy, H, Nilavalan, R. Optimizing the energy efficiency using quantum based load balancing in open radio access networks. IEEE Access 2024;12:37903–18. https://doi.org/10.1109/ACCESS.2024.3375530.Search in Google Scholar

36. Huynh, NV, Wang, J, Du, H, Hoang, DT, Niyato, D, Nguyen, DN, et al.. Generative AI for physical layer communications: a survey. IEEE Trans Cogn Commun Netw 2024;10:706–28. https://doi.org/10.1109/TCCN.2024.3384500.Search in Google Scholar

37. Cao, X, Lyu, Z, Zhu, G, Xu, J, Xu, L, Cui, S. An overview on over-the-air federated edge learning. IEEE Wireless Commun 2024;31:202–10. https://doi.org/10.1109/MWC.005.2300016.Search in Google Scholar

38. Wang, CH, Huang, KY, Yao, Y, Chen, JC, Shuai, HH, Cheng, WH. Lightweight deep learning: an overview. IEEE Consum Electron Mag 2024;13:51–64. https://doi.org/10.1109/MCE.2022.3181759.Search in Google Scholar

39. Cheng, Y, Wang, D, Zhou, P, Zhang, T. Model compression and acceleration for deep neural networks: the principles, progress, and challenges. IEEE Signal Process Mag 2018;35:126–36. https://doi.org/10.1109/MSP.2017.2765695.Search in Google Scholar

40. Amirabadi, MA, Nezamalhosseini, SA, Kahaei, MH, Chen, LR. A comprehensive survey on machine and deep learning for optical communications. IEEE Access 2025;13:88794–846. https://doi.org/10.1109/ACCESS.2025.3569559.Search in Google Scholar

41. Xu, J, Huang, Z, Gao, Y, Zhai, W, Qiu, H, Ji, Y. Design and experimental demonstration of underwater wireless optical communication system based on semantic communication paradigm. Opt Express 2024;32:2188–201. https://doi.org/10.1364/OE.507955.Search in Google Scholar PubMed

42. Zhu, F, Wang, X, Zhu, C, Gong, T, Yang, Z, Huang, C, et al.. Robust deep learning-based physical layer communications: strategies and approaches. IEEE Netw 2025:1. https://doi.org/10.1109/MNET.2025.3567105.Search in Google Scholar

43. Hemanth, C, Sangeetha, RG, Krishnan, P, Singh, RP, Tharun, P, Pankaj, S, et al.. Performance insights into multi-channel underwater optical wireless communication leveraging OFDM and alamouti diversity coding. Opt Quant Electron 2024;57:53. https://doi.org/10.1007/s11082-024-07934-y.Search in Google Scholar

44. Guo, Y, Wang, X, Fu, M. QAM–OFDM transmission in underwater wireless optical communication system with limited resolution DAC. Opt Quant Electron 2020;52:419. https://doi.org/10.1007/s11082-020-02529-9.Search in Google Scholar

Received: 2025-09-12

Accepted: 2025-10-13

Published Online: 2025-12-31

You are currently not able to access this content.

https://doi.org/10.1515/joc-2025-0399

Keywords for this article

underwater optical communications; MIMO systems; autoencoders; deep learning; neural receivers