Transfer Learning for Distance Classification of Marine Vessels Using Underwater Sound

Marine environments are increasingly affected by human activities, which generate underwater noise as a by-product. Acoustic data from these environments can offer valuable insights for tracking human activity and improving the monitoring of sensitive areas, such as marine protected areas (MPAs) and offshore wind farms. This study presents a convolutional neural network (CNN) trained to classify vessel distances from passive acoustic recordings. We constructed an open-source, diverse dataset by integrating 116 days of acoustic data from two stations in the Belgian part of the North Sea with automatic identification system data. The CNN was trained to classify acoustic clips into discrete distance bins, representing the proximity of the nearest vessel. Our results demonstrate that the model can effectively distinguish between distance categories using underwater sound alone, confirming the feasibility of passive acoustic monitoring for vessel activity. This technology provides an innovative approach to enhance MPA oversight and represents a first step in a promising pathway for conservation efforts.

• Publication year

  2025

• Venue

  IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

• Publication date

  Unknown publication date

• Fields of study

  Computer Science, Engineering, Environmental Science

• Identifiers
  DOI 10.1109/JSTARS.2025.3593779
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Clustering and novel class recognition: evaluating bioacoustic deep learning feature extractors

  2025cited by this paper
• Oceanship: A Large-Scale Dataset for Underwater Audio Target Recognition

  2024cited by this paper
• Optical and Synthetic Aperture Radar Image Fusion for Ship Detection and Recognition: Current state, challenges, and future prospects

  2024cited by this paper
• Underwater Acoustic Signal Recognition with Small Transfer Learning-based Training Samples

  2024cited by this paper
• CLAP Learning Audio Concepts from Natural Language Supervision

  2023cited by this paper
• Applications, Evolutions, and Challenges of Drones in Maritime Transport

  2023cited by this paper
• Transferable Models for Bioacoustics with Human Language Supervision

  2023influential reference
• Natural Language Supervision For General-Purpose Audio Representations

  2023cited by this paper
• Large-Scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation

  2022cited by this paper
• DeepShip: An underwater acoustic benchmark dataset and a separable convolution based autoencoder for classification

  2021cited by this paper
• Model-based convolutional neural network approach to underwater source-range estimation.

  2021cited by this paper
• The soundscape of the Anthropocene ocean

  2021cited by this paper
• Multiclass Vessel Detection From High Resolution Optical Satellite Images Based On Deep Neural Networks

  2019cited by this paper
• Explainable Machine Learning for Scientific Insights and Discoveries

  2019cited by this paper
• Observing the Oceans Acoustically

  2019cited by this paper
• Recent pace of change in human impact on the world’s ocean

  2019cited by this paper
• Recreational vessels without Automatic Identification System (AIS) dominate anthropogenic noise contributions to a shallow water soundscape

  2019cited by this paper
• Underwater acoustic source localization using generalized regression neural network.

  2018cited by this paper
• A comparison of VMS and AIS data: the effect of data coverage and vessel position recording frequency on estimates of fishing footprints

  2018cited by this paper
• Proposal of a marine protected area surveillance system against illegal vessels using image sensing and image processing

  2018cited by this paper
• Vessel Classification through Convolutional Neural Networks using Passive Sonar Spectrogram Images

  2018cited by this paper
• Tune: A Research Platform for Distributed Model Selection and Training

  2018cited by this paper
• Source localization in an ocean waveguide using supervised machine learning

  2017cited by this paper
• Ship localization in Santa Barbara Channel using machine learning classifiers.

  2017cited by this paper
• Conservation science and policy applications of the marine vessel Automatic Identification System (AIS)—a review

  2016cited by this paper
• Deep learning approach to passive monitoring of the underwater acoustic environment

  2016cited by this paper
• Quiet(er) marine protected areas.

  2015cited by this paper
• Impacts of anthropogenic noise on marine life : publication patterns, new discoveries, and future directions in research and management

  2015cited by this paper
• Review of potential legal frameworks for effective implementation and enforcement of MPAs in the high seas

  2014influential reference
• Anthropogenic pressure on the open ocean: The growth of ship traffic revealed by altimeter data analysis

  2014cited by this paper
• Introduction to the Physical and Biological Oceanography of Shelf Seas

  2012cited by this paper
• DEMON Acoustic Ship Signature Measurements in an Urban Harbor

  2011cited by this paper
• Towards a passive acoustic underwater system for protecting harbours against intruders

  2010cited by this paper
• Stevens Passive Acoustic System for underwater surveillance

  2010cited by this paper
• Exploring the limits of matched‐field processing.

  2010cited by this paper
• Anthropogenic and natural sources of ambient noise in the ocean

  2009cited by this paper
• Pelagic protected areas: the missing dimension in ocean conservation.

  2009cited by this paper
• Italian marine reserve effectiveness: Does enforcement matter?

  2008cited by this paper
• De macrobenthosatlas van het Belgisch deel van de Noordzee

  2006cited by this paper
• Reduction in computational requirements with matched field processing

  1998cited by this paper
• Matched-field processing for broad-band source localization

  1996cited by this paper
• Enforcement in marine protected areas

  1995cited by this paper
• Robust broadband matched-field processing: performance in shallow water

  1993cited by this paper
• An overview of matched field methods in ocean acoustics

  1993cited by this paper
• Use of calculated sound fields and matched‐field detection to locate sound sources in shallow water

  1976cited by this paper

• No citing papers are available for this paper.