How AI can Help in Detecting Marine Litter

Image Credit: Melih Evren /

MARLIT is a new floating waste detection platform that could assist scientists in monitoring ocean waste from aerial images.

Marine ecosystems worldwide currently face no greater threat than that of floating waste  —  especially plastics  —  created and discarded by humankind. The conservation of such ecosystems and the preservation of marine life hinges on identifying and removing plastic waste. But, before this can be done, researchers need to study the most impacted areas, categorizing the waste that accumulates there.

The most striking examples of floating sea macro-litter can be found in ocean gyres  —  large systems of circular ocean currents formed by global wind patterns and forces created by Earth’s rotation  —  where marine litter and debris form huge islands of garbage. Pollution from waste has also been found to be particularly abundant in semi-closed seas like the Mediterranean and in coastal regions. 

A new study, published in the journal Environmental Pollution¹, and authored by researchers from the Faculty of Biology and the Biodiversity Research Institute within the University of Barcelona (IRBio), suggests that a new open-access web app could assist in the detection and classification of plastic waste in the oceans. 

The system, dubbed MARLIT, operates on an algorithm with deep learning capabilities, which the team suggests has a reliability of 81%. The platform could be of great help in tackling floating marine macro-litter (FMML) in the future, joining current dedicated monitoring programs and mitigation measures.

“The automatization of monitoring processes and the use of apps such as MARLIT would ease the member states’ fulfillment of the directive,” the authors say in their report, referring to the application of FMML monitoring methods discussed in the EU Marine Strategy Framework Directive. 

Helping MARLIT Learn About Litter

To test MARLIT, the team applied its artificial intelligence system to almost 4,000 aerial images of the coast around Catalonia to identify the presence, density, and distribution of waste. 

This was employed as an alternative to direct observations from vehicles like boats and planes, which are commonly used in studies of this type. This is because due to the sheer scale of data to be considered and the vast area of the oceans, these conventional observation methods have limitations that constrain monitoring studies. 

Automatic aerial photography techniques combined with analytical algorithms are more efficient protocols for the control and study of this kind of pollutants. However, automated remote sensing of these materials is at an early stage.

Odei Garcia-Garin, a member of the Consolidated Research Group on Large Marine Vertebrates and lead author of the paper

Garcia-Garin continues, explaining that factors affecting the oceans like cloud coverage, wind patterns, and even waves, can severely impede the automatic detection of floating debris with images collected from the air. “This is why there are only a few studies that made the effort to work on algorithms to apply to this new research context,” the researcher adds.

MARLIT is Making Waves

The deep learning techniques of the new algorithm designed by the team automates the quantification and categorization of FMMLs and floating plastics in particular. This automated learning process is further boosted by added artificial neuronal networks. 

“The great number of images of the marine surface obtained by drones and planes in monitoring campaigns on marine litter and in experimental studies with known floating objects enabled us to develop and test a new algorithm that reaches an 80% of precision in the remote sensing of floating marine macro-litter,” Garcia-Garin, a member of the Department of Evolutionary Biology, Ecology and Environmental Sciences of the UB and IRBio, says. 

The algorithm that MARLIT operates on is based on a system called R Shiny, a package used to build web apps, that has already shown promise in the monitoring of FMMLs. Excitingly, the algorithm is open access meaning that it is available to other organizations and institutions that use aerial images to study and catalog plastic ocean waste. 

MARLIT is already showing promise in the analysis of individual images due to its ability to segment them and identify litter in separate areas. From here, it can assess the density of this waste.

Future improvements the team intends to apply to MARLIT include adapting it for use with remote sensors. This means it could be used with drones as part of a complete automated process. 


  1. Garcia-Garin. O., Monleón-Getino. T., López-Brosa. P., et al, [2021], ‘Automatic detection and quantification of floating marine macro-litter in aerial images: Introducing a novel deep learning approach connected to a web application in R,’ Environmental Pollution, []

Disclaimer: The views expressed here are those of the author expressed in their private capacity and do not necessarily represent the views of Limited T/A AZoNetwork the owner and operator of this website. This disclaimer forms part of the Terms and conditions of use of this website.

Robert Lea

Written by

Robert Lea

Robert is a Freelance Science Journalist with a STEM BSc. He specializes in Physics, Space, Astronomy, Astrophysics, Quantum Physics, and SciComm. Robert is an ABSW member, and aWCSJ 2019 and IOP Fellow.


Please use one of the following formats to cite this article in your essay, paper or report:

  • APA

    Lea, Robert. (2021, February 11). How AI can Help in Detecting Marine Litter. AZoRobotics. Retrieved on June 20, 2024 from

  • MLA

    Lea, Robert. "How AI can Help in Detecting Marine Litter". AZoRobotics. 20 June 2024. <>.

  • Chicago

    Lea, Robert. "How AI can Help in Detecting Marine Litter". AZoRobotics. (accessed June 20, 2024).

  • Harvard

    Lea, Robert. 2021. How AI can Help in Detecting Marine Litter. AZoRobotics, viewed 20 June 2024,

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.