This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.
Polychetty Veenasheela Rao,
- Professor, Lecturer, Jamshedpur, India
Abstract
Underwater wireless communication (UWC) plays a critical role in ocean exploration, environmental monitoring, offshore energy operations, disaster management, and naval defense. However, the underwater environment presents significant communication challenges, including severe signal attenuation, multipath propagation, Doppler effects, limited bandwidth, high latency, and energy constraints. Recent advancements in Artificial Intelligence (AI) and Machine Learning (ML) have emerged as promising solutions to address these limitations and enhance the efficiency, reliability, and adaptability of subsea communication networks. This review presents a comprehensive analysis of intelligent paradigms driving the evolution of underwater communications and subsea connectivity. The study examines the integration of AI and ML techniques across different layers of underwater communication systems, including physical, data-link, and network layers. Deep learning models such as Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, Generative Adversarial Networks (GANs), and Reinforcement Learning (RL) algorithms have demonstrated significant improvements in channel estimation, modulation classification, resource allocation, routing optimization, and signal detection. The review further highlights practical deployments involving autonomous underwater vehicles (AUVs), environmental surveillance systems, underwater acoustic target recognition, software-defined underwater communication platforms, and intelligent monitoring frameworks. In addition, the paper discusses AI integration across acoustic, optical, and electromagnetic communication modalities, emphasizing their respective advantages, limitations, and application domains. Challenges associated with computational complexity, energy consumption, model generalization, data scarcity, and real-time implementation are critically analyzed. Emerging approaches such as transfer learning, self-supervised learning, edge intelligence, and bio-inspired optimization are explored as potential solutions for next-generation underwater networks. The review concludes that AI-driven underwater communication systems offer substantial improvements in network performance, adaptability, and operational efficiency. Continued advancements in intelligent algorithms, low-power hardware, and autonomous networking architectures are expected to accelerate the development of resilient, scalable, and sustainable subsea communication ecosystems for future maritime applications.Underwater wireless communication (UWC) plays a critical role in ocean exploration, environmental monitoring, offshore energy operations, disaster management, and naval defense. However, the underwater environment presents significant communication challenges, including severe signal attenuation, multipath propagation, Doppler effects, limited bandwidth, high latency, and energy constraints. Recent advancements in Artificial Intelligence (AI) and Machine Learning (ML) have emerged as promising solutions to address these limitations and enhance the efficiency, reliability, and adaptability of subsea communication networks. This review presents a comprehensive analysis of intelligent paradigms driving the evolution of underwater communications and subsea connectivity. The study examines the integration of AI and ML techniques across different layers of underwater communication systems, including physical, data-link, and network layers. Deep learning models such as Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, Generative Adversarial Networks (GANs), and Reinforcement Learning (RL) algorithms have demonstrated significant improvements in channel estimation, modulation classification, resource allocation, routing optimization, and signal detection. The review further highlights practical deployments involving autonomous underwater vehicles (AUVs), environmental surveillance systems, underwater acoustic target recognition, software-defined underwater communication platforms, and intelligent monitoring frameworks. In addition, the paper discusses AI integration across acoustic, optical, and electromagnetic communication modalities, emphasizing their respective advantages, limitations, and application domains. Challenges associated with computational complexity, energy consumption, model generalization, data scarcity, and real-time implementation are critically analyzed. Emerging approaches such as transfer learning, self-supervised learning, edge intelligence, and bio-inspired optimization are explored as potential solutions for next-generation underwater networks. The review concludes that AI-driven underwater communication systems offer substantial improvements in network performance, adaptability, and operational efficiency. Continued advancements in intelligent algorithms, low-power hardware, and autonomous networking architectures are expected to accelerate the development of resilient, scalable, and sustainable subsea communication ecosystems for future maritime applications.
Keywords: Artificial Intelligence, Underwater Wireless Communication, Machine Learning, Subsea Connectivity, Autonomous Underwater Vehicles, Deep Learning, Intelligent Networking.
References
Journal of Artificial Intelligence Research & Advances
| Volume | 13 | |
| 03 | ||
| Received | 18/04/2026 | |
| Accepted | 20/06/2026 | |
| Published | 30/09/2026 | |
| Publication Time | 165 Days |