Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Size-Dependent Habitat Selection in a Tropical Freshwater Crayfish: Preference for Vegetated Refugia.

Ecology and evolution·2026
Same author

The impact of bladder and rectal dynamics on prostate and seminal vesicles intrafraction motion and deformation in radiotherapy.

Physics and imaging in radiation oncology·2026
Same author

From nets to barcodes: Selecting suitable methods for assessing fish and prawn assemblages in seagrass meadows.

Marine environmental research·2025
Same author

Stabilizing machine learning for reproducible and explainable results: A novel validation approach to subject-specific insights.

Computer methods and programs in biomedicine·2025
Same author

Habitat-use strategies of young barramundi (Lates calcarifer) in a heavily modified landscape.

Journal of fish biology·2025
Same author

How much data do you need? An analysis of pelvic multi-organ segmentation in a limited data context.

Physical and engineering sciences in medicine·2025

Related Experiment Video

Updated: Jan 9, 2026

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish
10:56

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Published on: March 6, 2014

13.0K

Linking fish activity and turbidity through visual and sensor data fusion and deep learning.

Mohammad Jahanbakht1, Andrea Tiernan2, Alzayat Saleh1

  • 1College of Science and Engineering, James Cook University, Townsville, QLD, 4814, Australia; Centre for AI and Data Science Innovation, James Cook University, Townsville, QLD, Australia.

Marine Pollution Bulletin
|December 2, 2025
PubMed
Summary

This study uses deep learning to monitor underwater environments, accurately estimating water turbidity and detecting fish. The findings reveal a strong correlation between fish populations and water quality, aiding marine ecosystem management.

Keywords:
Deep learningFish detectionImage and sensor fusionTurbid water monitoringTurbidity estimation

More Related Videos

Development of New Methods for Quantifying Fish Density Using Underwater Stereo-video Tools
09:32

Development of New Methods for Quantifying Fish Density Using Underwater Stereo-video Tools

Published on: November 20, 2017

9.7K
Reefshape: A System for the Efficient Collection and Automated Processing of Time-Series Underwater Photogrammetry Data for Benthic Habitat Monitoring
13:35

Reefshape: A System for the Efficient Collection and Automated Processing of Time-Series Underwater Photogrammetry Data for Benthic Habitat Monitoring

Published on: June 13, 2025

1.3K

Related Experiment Videos

Last Updated: Jan 9, 2026

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish
10:56

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Published on: March 6, 2014

13.0K
Development of New Methods for Quantifying Fish Density Using Underwater Stereo-video Tools
09:32

Development of New Methods for Quantifying Fish Density Using Underwater Stereo-video Tools

Published on: November 20, 2017

9.7K
Reefshape: A System for the Efficient Collection and Automated Processing of Time-Series Underwater Photogrammetry Data for Benthic Habitat Monitoring
13:35

Reefshape: A System for the Efficient Collection and Automated Processing of Time-Series Underwater Photogrammetry Data for Benthic Habitat Monitoring

Published on: June 13, 2025

1.3K

Area of Science:

  • Marine biology
  • Environmental monitoring
  • Artificial intelligence

Background:

  • Underwater monitoring is vital for industrial sustainability and environmental compliance.
  • Integrating imaging and water quality sensing presents challenges due to data synchronization issues.

Purpose of the Study:

  • To develop and integrate deep learning models for underwater fish detection and water turbidity estimation.
  • To analyze the interaction between fish populations and water turbidity in a port environment.
  • To showcase the application of advanced technology in ecological studies.

Main Methods:

  • Deployed an IP-based underwater camera and water quality sensors at Port Mackay.
  • Developed a custom Convolutional Neural Network (CNN) for image-based turbidity estimation (NTU).
  • Utilized YOLOWorld-based prompt-able object detectors for fish detection, evaluating YOLOWorld-v1 Large.

Main Results:

  • Achieved 89.7% accuracy for fish detection using YOLOWorld-v1 Large without training.
  • CNN model for turbidity estimation yielded a root mean square error of 1.6 NTU.
  • Identified a non-linear correlation (R²=0.93) between fish count and water turbidity.

Conclusions:

  • Deep learning models effectively estimate turbidity and detect fish, overcoming synchronization issues.
  • The study confirms a complex relationship between fish abundance and water quality.
  • This technology offers potential for automated real-time environmental monitoring and early warning systems in marine ecosystems.