2025/10/24 by Melpomeni Sofia Mente, Emilie Houliez, Eleonora Scalco +2 · 1 voice
Environmental Science · Biochemistry, Genetics and Molecular Biology · Earth and Planetary Sciences · #Isotope Analysis in Ecology #Identification and Quantification in Food #Marine and coastal ecosystems
paper · pdf · doi:10.1038/s41597-025-05973-y
openalex publication_date 2025/10/24 · openalex created_date 2025/10/24 · openalex updated_date 2026/07/29
The Imaging FlowCytobot (IFCB), supported by machine learning-based classifications, has revolutionized plankton research by automating plankton monitoring and considerably increasing sampling resolution. However, building a training set of labeled IFCB images to train the machine learning algorithms remains time-consuming and challenging. Consequently, there is a growing demand within the IFCB user community for shared datasets of taxonomically annotated IFCB images. Currently, such datasets are scarce and lack Mediterranean coverage. This data descriptor introduces MedPlanktonSet, a dataset comprising 77,271 taxonomically annotated IFCB images provided with their associated features. Data were collected from November 2022 to February 2025 at six stations in the Gulf of Naples (Western Mediterranean Sea) and the IFCB images were classified into 139 categories. MedPlanktonSet will support the development of various machine learning classifiers, 3D plankton reconstructions, training of plankton taxonomists and trait-based ecological studies. Ultimately, by facilitating the use of IFCBs with their associated classifiers, MedPlanktonSet will contribute to advancing research on plankton biodiversity and ecology.