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 Videos

Patterning and predicting aquatic macroinvertebrate diversities using artificial neural network.

Young-Seuk Park1, Piet F M Verdonschot, Tae-Soo Chon

  • 1CESAC, UMR 5576, CNRS--Université Paul Sabatier, 118 Route de Narbonne, Toulouse, Cedex 31062, France. park@cict.fr

Water Research
|April 17, 2003
PubMed
Summary

A counterpropagation neural network (CPN) accurately predicted benthic macroinvertebrate species richness and Shannon diversity. This AI tool aids in assessing water quality and ecological status across diverse aquatic ecosystems.

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

Half a century of nutrient trends across spatial scales in the Rhine delta: overall improvements, but polder ditches lag behind.

Water research·2026
Same author

Seasonal and Spatiotemporal Dynamics of Plankton Communities Using eDNA Metabarcoding in Singal Reservoir.

Environmental management·2026
Same author

Assessment of the ecological status of benthic macroinvertebrate communities in the intertidal flats of Lake Shihwa following tidal power plant operation.

Marine pollution bulletin·2025
Same author

Macroinvertebrates, a forgotten player in the nutrient dynamics of riparian buffer zones.

Oecologia·2025
Same author

Effects of cumulative temperature and precipitation patterns on mosquito abundance in urban Seoul, South Korea.

Scientific reports·2025
Same author

Human-mediated forest transition shapes long-term occurrence patterns of pine caterpillar (Dendrolimus spectabilis) in the Korean Peninsula.

Journal of environmental management·2025

Area of Science:

  • Ecology
  • Environmental Science
  • Computational Biology

Background:

  • Benthic macroinvertebrate communities are key indicators of aquatic ecosystem health.
  • Predicting species richness (SR) and Shannon diversity (SH) requires understanding complex environmental relationships.
  • Artificial intelligence offers novel approaches for ecological data analysis.

Purpose of the Study:

  • To apply a counterpropagation neural network (CPN) for predicting species richness (SR) and Shannon diversity index (SH) of benthic macroinvertebrate communities.
  • To evaluate the CPN's effectiveness in classifying sampling sites based on environmental variables and habitat types.
  • To explore the relationships between environmental variables and diversity indices using the CPN model.

Main Methods:

Related Experiment Videos

  • Utilized a counterpropagation neural network (CPN) trained on data from 664 sites across 23 water types in The Netherlands.
  • Input data included 34 environmental variables.
  • Validated model performance using learning and testing datasets, achieving high prediction accuracy (r>0.90 and 0.67 for SH and SR, respectively).

    • Main Results:

    • The CPN successfully classified sampling sites into five groups, primarily related to pollution status and habitat type.
    • Visualizations revealed relationships between environmental variables and diversity indices.
    • The model demonstrated high predictive accuracy for both Shannon diversity (SH) and species richness (SR).

    Conclusions:

    • Counterpropagation neural networks (CPNs) are effective tools for analyzing and predicting ecological data.
    • CPNs can be utilized for assessing the ecological status and predicting water quality in various aquatic ecosystems.
    • This study highlights the potential of AI in ecological monitoring and environmental management.