Published July 21, 2025 | Version v1
Dataset Open

DIATLAS - The French freshwater DIatom ATLAS image dataset

  • 1. ROR icon Université de Lorraine
  • 2. ROR icon Laboratoire Interdisciplinaire des Environnements Continentaux
  • 3. EDMO icon National Research Institute For Agriculture, Food And Environment
  • 4. ROR icon Luxembourg Institute of Science and Technology
  • 5. ROR icon CentraleSupélec
  • 6. Institut National de Recherche pour l'Agriculture l'Alimentation et l'Environnement Nouvelle-Aquitaine Bordeaux Centre

Description

This dataset contains photonic (optical) microscopy images of diatoms extracted from French regional atlases, documenting specimens collected from freshwater streams. These images were acquired using either Bright Field (BF) or Differential Interference Contrast (DIC) techniques. Each image is associated with a taxonomic classification.

This dataset was used to train two Convolutional Neural Network (CNN) models:

Image metadata are provided in the diatoms.csv, sources.csv, and taxonomic_code.csv files.

 

Technical info

All informations are detailed in the README.pdf

Data sources

The dataset is based on images gathered from French regional diatom taxonomic atlases (available as open-access PDFs). All informations are detailed in the README.pdf

Contact information

For more information on the dataset and/or the models, you can contact martin.laviale @ univ-lorraine.fr & Jeremy.Fix @ centralesupelec.fr

Files

README.pdf

Files (1.1 GB)

Name Size Download all
md5:be2fc6d2ee5b568869725852e340dd1a
2.8 MB Preview Download
md5:24f53f1102626fd9037332df281ff8ca
1.1 GB Preview Download
md5:fa41c3ee33b6f849c08244641faf6767
98.2 kB Preview Download
md5:94c58e9b0cc9125bd17b4b831686348e
7.3 kB Preview Download
md5:63af9d3c482cd49638d95a331c47f74a
36.3 kB Preview Download

Additional details

Additional titles

Alternative title
Diatom Atlas Dataset

Related works

Is new version of
Dataset: 10.12763/UADENQ (DOI)

Funding

European Commission
iMagine - Imaging data and services for aquatic science 101058625
Agence Nationale de la Recherche
BIOINDIC-IA — Deep learning for automatic image-based biomonitoring of aquatic ecosystems ANR-24-CE04-0345