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

Plastic occurrence in Macaronesia: Three years of monitoring on forty-six beaches across nineteen islands in an Atlantic region.

The Science of the total environment·2025
Same author

Metamorphosis in <i>Aurelia aurita</i> from polyp to medusa: assessing composition and metabolism throughout development.

Marine life science & technology·2025
Same author

Corrigendum to "Impact of tire particle leachates on microplankton communities in the Canary Islands" [Ecotoxicol. Environ. Saf. (2025) 291/117787].

Ecotoxicology and environmental safety·2025
Same author

Occurrence and assessment of emerging contaminants adsorbed onto microplastic debris in the Macaronesia region.

Marine pollution bulletin·2025
Same author

Noise Levels Due to Commercial and Leisure Activities in Urban Areas: Experimental Validation of a Numerical Model Fed with Crowd Density Estimation Using Computer Vision.

Sensors (Basel, Switzerland)·2025
Same author

Chemometric discrimination of airborne fibres: microplastics, regenerated cellulose and natural fibres.

Environmental research·2025

Related Experiment Video

Updated: Dec 3, 2025

Sampling and Identification of Microplastics in Groundwater
08:27

Sampling and Identification of Microplastics in Groundwater

Published on: November 7, 2025

489

Deep learning approach for automatic microplastics counting and classification.

Javier Lorenzo-Navarro1, Modesto Castrillón-Santana1, Elena Sánchez-Nielsen2

  • 1University of Las Palmas de Gran Canaria, Inst. Univ. SIANI, 35017 Las Palmas, Spain.

The Science of the Total Environment
|October 31, 2020
PubMed
Summary

A new deep learning model automatically counts and classifies microplastic particles from phone images, offering a faster and more accessible method for environmental monitoring. This technology aids in understanding microplastic pollution.

Keywords:
Artificial intelligenceDeep learningImage analysisMicroplastics classification

More Related Videos

Sampling, Sorting, and Characterizing Microplastics in Aquatic Environments with High Suspended Sediment Loads and Large Floating Debris
05:31

Sampling, Sorting, and Characterizing Microplastics in Aquatic Environments with High Suspended Sediment Loads and Large Floating Debris

Published on: July 28, 2018

16.6K
Separation and Identification of Conventional Microplastics from Farmland Soils
14:10

Separation and Identification of Conventional Microplastics from Farmland Soils

Published on: March 21, 2025

2.7K

Related Experiment Videos

Last Updated: Dec 3, 2025

Sampling and Identification of Microplastics in Groundwater
08:27

Sampling and Identification of Microplastics in Groundwater

Published on: November 7, 2025

489
Sampling, Sorting, and Characterizing Microplastics in Aquatic Environments with High Suspended Sediment Loads and Large Floating Debris
05:31

Sampling, Sorting, and Characterizing Microplastics in Aquatic Environments with High Suspended Sediment Loads and Large Floating Debris

Published on: July 28, 2018

16.6K
Separation and Identification of Conventional Microplastics from Farmland Soils
14:10

Separation and Identification of Conventional Microplastics from Farmland Soils

Published on: March 21, 2025

2.7K

Area of Science:

  • Environmental Science
  • Computer Science
  • Materials Science

Background:

  • Microplastic quantification is crucial for monitoring and modeling, but traditional methods are time-consuming and require expensive equipment.
  • Developing automated, accessible techniques for microplastic analysis is essential for effective environmental surveillance.

Purpose of the Study:

  • To present a novel deep learning architecture for the automated counting and classification of microplastic particles.
  • To enable microplastic analysis using readily available digital cameras and mobile phones.

Main Methods:

  • A two-stage deep learning architecture was developed, utilizing U-Net for image segmentation and VGG16 for particle classification.
  • The system processes images from digital cameras or mobile phones (≥16 megapixels) to identify and categorize microplastics.
  • Particles were classified into three common types: fragments, pellets, and lines.

Main Results:

  • The proposed architecture achieved a Jaccard index of 0.8 for particle segmentation.
  • Microplastic particle classification accuracy reached 98.11%.
  • The deep learning approach demonstrated significantly faster processing times compared to traditional computer vision methods.

Conclusions:

  • The developed deep learning architecture provides an efficient and accurate automated solution for microplastic quantification.
  • This method democratizes microplastic analysis, making it more accessible for research and environmental monitoring efforts.
  • The system's speed and accuracy offer a substantial improvement over existing techniques.