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 Experiment Video

Updated: Jun 25, 2025

Necropsy-based Wild Fish Health Assessment
07:57

Necropsy-based Wild Fish Health Assessment

Published on: September 11, 2018

17.2K

Forecasting fish mortality from water and air quality data using deep learning models.

Chia-Ching Ting1, Ying-Chu Chen2

  • 1Department of Civil Engineering, National Taiwan University, Taipei City, Taiwan.

Journal of Environmental Quality
|May 29, 2024
PubMed
Summary
This summary is machine-generated.

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

Modeling transmission of hexavalent chromium concentration and its health cost with a water quality analysis simulation program.

Water environment research : a research publication of the Water Environment Federation·2021
Same journal

Assessing the performance of aged field-scale woodchip bioreactors in Iowa.

Journal of environmental quality·2026
Same journal

Spatial structuring dominates over seasonality in tropical coastal microbiomes: Insights from New Caledonia's Indo-Pacific lagoon.

Journal of environmental quality·2026
Same journal

Neonicotinoid contamination in aquatic ecosystems: A comprehensive review of toxic effects, underlying mechanisms, and mitigation strategies with implications for farmed teleosts.

Journal of environmental quality·2026
Same journal

Macroaggregates dominate colloidal phosphorus sequestration in Ultisol paddies: Evidence from size-fractionation experiments.

Journal of environmental quality·2026
Same journal

Harnessing biochar and plant growth-promoting bacteria for sustainable crop production under reclaimed water irrigation: A review.

Journal of environmental quality·2026
Same journal

Invasive plant species for compost production: Review of environmental and economic insights.

Journal of environmental quality·2026
See all related articles

Accurate fish mortality prediction is crucial. This study used deep learning with environmental data, achieving 93.4% accuracy, identifying dissolved oxygen as key to preventing aquatic deaths.

Area of Science:

  • Environmental Science
  • Data Science
  • Aquatic Ecology

Background:

  • High rates of fish mortality worldwide necessitate improved prediction methods.
  • Water quality degradation is a significant factor in aquatic ecosystems.
  • Accurate prediction models are vital for sustainable water resource management.

Purpose of the Study:

  • To develop and evaluate deep learning models for predicting accidental fish mortality.
  • To identify key environmental factors influencing fish mortality events.
  • To provide data-driven insights for mitigating aquatic mortality.

Main Methods:

  • Integrated air and water quality data with meteorological information.
  • Utilized deep learning models: multilayer perceptron (MLP) and long short-term memory (LSTM).

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

9.2K
Anesthesia-free Heartbeat Measurements in Freely Moving Zebrafish
03:57

Anesthesia-free Heartbeat Measurements in Freely Moving Zebrafish

Published on: April 18, 2025

314

Related Experiment Videos

Last Updated: Jun 25, 2025

Necropsy-based Wild Fish Health Assessment
07:57

Necropsy-based Wild Fish Health Assessment

Published on: September 11, 2018

17.2K
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

9.2K
Anesthesia-free Heartbeat Measurements in Freely Moving Zebrafish
03:57

Anesthesia-free Heartbeat Measurements in Freely Moving Zebrafish

Published on: April 18, 2025

314
  • Compared MLP and LSTM model performance against a naïve Bayesian classifier.

    • Main Results:

    • The MLP model achieved 93.4% accuracy in predicting fish mortality.
    • Environmental data from the preceding 5 days were most influential for model training.
    • Dissolved oxygen concentration below 2 mg/L and high river pollution index significantly increased mortality risk.

    Conclusions:

    • Deep learning models, particularly MLP, can accurately predict fish mortality using integrated environmental data.
    • Dissolved oxygen, river pollution index, and meteorological data are critical factors influencing fish mortality.
    • Findings support achieving Sustainable Development Goals by improving water resource management and profitability.