{
  "abstract": "Plankton plays a fundamental role in aquatic ecosystems, influencing biogeochemical cycles and serving as a key food source for many organisms. Recent high-throughput imaging technologies enable the rapid acquisition of large volumes of microscopic images, creating new opportunities for monitoring planktonic ecosystems. However, the manual processing and annotation of the vast amounts of data generated by these devices remain time-consuming tasks. In this context, machine learning-based classification models offer a promising solution. In this data paper, we introduce a new labeled freshwater plankton dataset comprising approximately 88,000 images distributed across 43 taxa. We also detail the methods we applied to ensure a high quality labeling, partly relying on an automatic detection of wrong labels. Finally, we present a baseline convolutional neural network (CNN), which achieves a classification accuracy of 93% on our dataset.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 8,
  "authors": [
    {
      "name": "Léo Déchaumet"
    },
    {
      "name": "Carine Puppo"
    },
    {
      "name": "Samy Blusseau"
    },
    {
      "name": "Beatriz Marcotegui"
    },
    {
      "name": "Etienne Decencière"
    },
    {
      "name": "Gérard Lacroix"
    },
    {
      "name": "David Carmignac"
    },
    {
      "name": "Jean-François Le Galliard"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/fm401gf8z30yt.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.24.753096",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.09.24.753096v1.full",
  "id": "fm401gf8z30yt",
  "issns": [],
  "landing_url": "https://cnrs.hal.science/hal-05761800v1",
  "language": "en",
  "licence": "CC-BY-NC-4.0",
  "licence_label": "CC BY-NC 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "ecology"
    ],
    [
      "hal",
      "0.info"
    ],
    [
      "hal",
      "0.sde"
    ],
    [
      "openalex",
      "1707|Advanced Neural Network Applications"
    ]
  ],
  "openalex": "W7214566289",
  "pdf_url": "https://cnrs.hal.science/hal-05761800/document",
  "pmcid": null,
  "pmid": null,
  "published": "2026-08-22",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/fm401gf8z30yt.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:40Z",
      "native_id": "hal-05761800",
      "source": "hal",
      "url": "https://cnrs.hal.science/hal-05761800v1"
    },
    {
      "first_seen": "2026-10-30T12:24:48Z",
      "native_id": "10.64898/2026.09.24.753096",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.09.24.753096v2"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:ecology",
      "subfield": "ecology"
    },
    {
      "field": "earth",
      "origin": "hal:0.sde",
      "subfield": "environmental-science"
    }
  ],
  "title": "PlanktonLake-CEREEP - A Freshwater Plankton Image Dataset with Semi-Automated Label Cleaning",
  "title_text": "PlanktonLake-CEREEP - A Freshwater Plankton Image Dataset with Semi-Automated Label Cleaning",
  "type": "preprint",
  "updated_at": "2026-10-30T12:25:13Z",
  "url": "https://research.draconitic.com/paper/fm401gf8z30yt",
  "venue": "HAL",
  "versions": []
}