Related Experiment Video
Updated: Sep 18, 2025
09:01
Handling and Tagging Techniques for Implanting Juvenile American Shad with a New Acoustic Microtransmitter
Published on: June 14, 2024
2.4K
AI-Driven Adaptive Communications for Energy-Efficient Underwater Acoustic Sensor Networks
A Ur Rehman1, Laura Galluccio1, Giacomo Morabito1
1Dipartimento di Ingegneria Elettrica Elettronica e Informatica (DIEEI), University of Catania & CNIT, Viale A. Doria 6, 95125 Catania, Italy.
Sensors (Basel, Switzerland)
|June 27, 2025
Summary
This study introduces an AI framework for underwater acoustic sensor networks to improve energy efficiency in marine wildlife monitoring. By processing data locally and adapting transmissions, it reduces energy use and environmental impact.
Area of Science:
- Marine Biology
- Sensor Networks
- Artificial Intelligence
Background:
- Underwater acoustic sensor networks (UASNs) are vital for marine monitoring but face challenges like limited bandwidth, high delay, and energy constraints.
- Existing UASNs struggle with energy efficiency, impacting network survivability, reliability, and operational costs.
- Sustainable and energy-efficient UASN design is crucial for effective marine wildlife monitoring.
Purpose of the Study:
- To propose an artificial intelligence (AI)-driven framework to enhance energy efficiency and sustainability in UASNs for marine wildlife monitoring.
- To integrate intelligent computing into sensor nodes for local marine species classification.
- To reduce data transmission volume and energy consumption by sending only classification results.
Main Methods:
- Developed an AI-driven framework with lightweight AI models for local species classification on sensor nodes.
- Implemented a software-defined radio (SDR) methodology for dynamic adaptation of transmission parameters (modulation, packet length, power).
- Evaluated the framework's effectiveness using GNU Radio simulations, analyzing energy consumption, bit error rate, throughput, and delay.
Main Results:
- Transmitting only classification results significantly reduced data volume and conserved energy compared to raw data transmission.
- Adaptive transmission strategies demonstrated reduced energy usage compared to fixed-parameter transmission solutions.
- The framework effectively balanced energy efficiency, network performance, and ecological impact.
Conclusions:
- The proposed AI-driven framework enhances energy efficiency and sustainability in UASNs for marine wildlife monitoring.
- Local data processing and adaptive transmission are key to reducing energy consumption and environmental disruption.
- This research contributes to the development of sustainable and energy-efficient underwater wireless sensor networks.
