Intelligent Underwater Quantum Communications: A Review of AI-Enabled Channel Estimation, Noise Mitigation, and System Optimization

Abstract

Underwater quantum communication (UQC) has emerged as a promising approach for secure information transfer in oceanic environments by exploiting fundamental quantum mechanical principles. However, realizing UQC in practice remains highly challenging due to the inherently dynamic nature of the underwater optical channel, which is subject to wavelength-dependent absorption, multiple scattering, turbulence, and ambient noise—effects that collectively degrade photon transmission and induce quantum state errors. Conventional analytical models are insufficient to capture these nonlinear, time-varying channel characteristics, motivating the integration of artificial intelligence (AI) methods. Unlike previous surveys that focus narrowly on either underwater optical communications or quantum cryptography in isolation, this review uniquely synthesizes advances across quantum information science, ocean optics, and machine learning to address UQC-specific channel impairments. Specifically, we critically evaluate AI-driven approaches in three areas: (i) spatio-temporal deep learning models for data-driven channel estimation, demonstrating measurable improvements in channel prediction accuracy under realistic turbulence conditions; (ii) intelligent noise reduction and quantum error correction methods that reduce qubit error rates in high-scattering environments; and (iii) adaptive system optimization through reinforcement learning and hybrid optimization strategies that enhance operational fidelity and robustness. Based on this analysis, we identify key gaps in the field—including the absence of standardized underwater quantum datasets, limited experimental validation of AI-quantum hybrid frameworks, and the lack of end-to-end AI-quantum design tools—and outline concrete directions for future research. This review serves as a structured reference for researchers and practitioners working toward deployable, intelligent UQC systems.