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

Advancements in extracellular vesicle research.

Extracellular vesicle·2026
Same author

Real-time, automated, standardized, and transparent analysis of microfluidic nanoparticle data with RPS<sub>PASS</sub>.

bioRxiv : the preprint server for biology·2026
Same author

Behavioral patterns in iGaming across territories: Psychiatric and AI-driven insights via the internet of behavior.

Technology and health care : official journal of the European Society for Engineering and Medicine·2026
Same author

ATR-FTIR Assessment of the Antioxidant and Anti-Inflammatory Effects of (-)-Epicatechin in MASLD.

ACS omega·2026
Same author

Systemic metabolic, hormonal, and glycomic remodeling during a 72-hour fast in healthy adults: a pilot study.

Croatian medical journal·2026
Same author

Latent Factor Modeling Reveals Unexpected Spatial Heterogeneity in Human Alzheimer's Disease Brain Transcriptomes.

Computational and structural biotechnology journal·2026

Related Experiment Video

Updated: Jun 26, 2025

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.4K

Automated identification of aquatic insects: A case study using deep learning and computer vision techniques.

Predrag Simović1, Aleksandar Milosavljević2, Katarina Stojanović3

  • 1Department of Biology and Ecology, Faculty of Science, University of Kragujevac, Radoja Domanovića 12, 34000 Kragujevac, Serbia.

The Science of the Total Environment
|May 13, 2024
PubMed
Summary

Deep learning models can now accurately identify aquatic insects like mayflies, stoneflies, and caddisflies (EPT) for environmental monitoring. This AI approach significantly speeds up species identification, improving biodiversity research and water quality assessments.

Keywords:
Artificial intelligenceBiomonitoringEphemeropteraPlecopteraTrichoptera

More Related Videos

Automatic Image Processing to Determine the Community Size Structure of Riverine Macroinvertebrates
08:56

Automatic Image Processing to Determine the Community Size Structure of Riverine Macroinvertebrates

Published on: January 13, 2023

2.2K
Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT
08:04

Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT

Published on: April 23, 2020

6.8K

Related Experiment Videos

Last Updated: Jun 26, 2025

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.4K
Automatic Image Processing to Determine the Community Size Structure of Riverine Macroinvertebrates
08:56

Automatic Image Processing to Determine the Community Size Structure of Riverine Macroinvertebrates

Published on: January 13, 2023

2.2K
Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT
08:04

Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT

Published on: April 23, 2020

6.8K

Area of Science:

  • Ecology and Environmental Science
  • Computational Biology
  • Taxonomy

Background:

  • Freshwater biomonitoring relies on sensitive indicator species such as mayflies (Ephemeroptera), stoneflies (Plecoptera), and caddisflies (Trichoptera) (EPT).
  • Traditional morphological identification of EPT species is time-consuming, costly, and prone to taxonomic resolution limitations and misidentification.

Purpose of the Study:

  • To investigate the efficacy of deep learning for enhancing the efficiency and taxonomic resolution of EPT species identification in biomonitoring.
  • To develop and validate a Convolutional Neural Network (CNN) model for automated EPT classification.

Main Methods:

  • A comprehensive database of 16,650 images across 90 EPT taxa was curated.
  • A CNN model was trained on this dataset for automated species classification.
  • Gradient-weighted Class Activation Mapping (Grad-CAM) was employed to visualize classification-driving morphological features.

Main Results:

  • The CNN model achieved an overall classification accuracy of 98.7%, with 100% accuracy for 68 taxa.
  • High accuracy was obtained even for morphologically similar taxa within genera like Baetis, Hydropsyche, and Perla.
  • Grad-CAM analysis identified key morphological features (head, thorax, abdomen) crucial for classification across different EPT orders.

Conclusions:

  • Deep learning offers a powerful solution to overcome challenges in EPT species identification for biomonitoring.
  • The developed model significantly increases efficiency and taxonomic resolution, supporting more robust biodiversity research and environmental monitoring.
  • This approach establishes a new benchmark for aquatic insect identification databases and AI applications in ecological studies.