Mature use case

FlowCam Phytoplankton Identification

Taxonomic identification of phytoplankton using Flowcam images


To establish an operational service at the iMagine platform for ingestion, storage, analysis and processing of FlowCam images for determining taxonomic composition of phytoplankton samples.

Development actions during iMagine


Setting up operational environment at iMagine platform, with the AI pipeline for processing FlowCam images, and storing resulting data


Connecting the MongoDB database to the iMagine platform for ingesting and extracting data


Refining the AI tools for taxonomic identification of phytoplankton. For instance, the current image classification model does not include sampling metadata and environmental data as context input to the CNN


Enhancing the FAIRness of data output in accordance with Darwin Core standards and relevant vocabularies


Developing guidance and training material for uptake of the FlowCam processing service


Reaching out to users for uptake and provide support and training


A long term (>4y) high quality phytoplankton image dataset is available in a NoSQL

Timeline and progress

start date
Sep 2022
end date
Aug 2025

Expected Results


The global description of the abundance and diversity of phytoplankton communities yields an indication of the health of marine ecosystems and their response to anthropic stressors. As such, the image derived phytoplankton community characteristics are used within three common OSPAR indicators for the Good Environmental Status assessment for pelagic habitats under Descriptor 1 (Biodiversity).


The provision of the Flowcam processing pipeline in iMagine will result in more users and more image providers, contributing to more phytoplankton information and more efficient biomonitoring.

Involved Partners

Related news

iMagine Empowers Phytoplankton Researchers with Advanced FlowCam Image Analysis

Read about the user story from FlowCam use case

February 06, 2024

Header image credit: Nick Decombel Fotografie

Other images: VLIZ