EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automated recognition of Meso-Cenozoic foraminifera from Senegalese sedimentary deposits using convolutional neural networks

Malick Thiam, Sonia Chaabane, Thibault de Garidel-Thoron

PeerJ · 26.06.2026 · 14 · e21437

DOI: 10.7717/peerj.21437 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PeerJ, online erschienen am 26.06.2026. Verfasst von Malick Thiam und 2 weiteren Autor:innen. Beteiligte Einrichtung: Aix-Marseille Université, CNRS, IRD, INRAE, CEREGE, Aix-en-Provence, France. Hauptthemen laut MEDLINE: Foraminifera, Fossils, Geologic Sediments, Neural Networks, Computer. Die Arbeit nennt 98 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Cooperation française and financial support of Cheikh Anta Diop University, The French government under the France 2030 investment plan, The Initiative d’Excellence d’Aix-Marseille Université–A*MIDEX” AMX-20-TRA-029.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fossil foraminifera are key proxies for biostratigraphy and paleoenvironmental reconstructions, providing crucial insights into past ocean conditions and climate evolution. However, their identification remains time-consuming and challenging, particularly in taxonomically complex assemblages and in samples affected by diagenetic alteration. Here, we investigate the application of convolutional neural networks (CNNs) for the automated classification of Meso-Cenozoic foraminifera from the West African margin, including planktonic, benthic, and agglutinated taxa. Three training datasets comprising 11,378 images were used to develop CNN models for microfossil detection, genus-level, and species-level classification. Genus-level classification reached a validation accuracy of 72.4%, outperforming species-level identification (50.2% validation accuracy), as it reduced misclassifications from morphological variability and post-mortem degradation in closely related species. The genus-level CNN performed well for genera with distinct morphological features, such as Muricohedbergella sp. and Heterohelix sp., but struggled with Subbotina spp. and Dicarinella spp. due to shared morphological traits and diagenetic alterations. For benthic foraminifera, Nummulites sp. was easily identified, while Gavelinella sp. posed significant challenges. These results highlight the potential of CNNs for high-throughput classification, while also revealing limitations particularly for taxa with high morphological variability or diagenetic changes. The findings have important implications for biostratigraphy, suggesting that CNNs can enhance genus-level classification in biostratigraphic applications. Further advancements such as multi-view imaging and expanded training datasets could enhance the CNN performance. By integrating deep-learning-based classification with expert biostratigraphy, our study contributes to open the way for quantitative and reproducible reconstructions of Meso-Cenozoic stratigraphic constraints.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ForaminiferaFossilsGeologic SedimentsNeural Networks, ComputerConvolutional Neural Networks

Stichwörter der Autor:innen

Automated recognitionBiostratigraphyClassificationContinental sediment depositsConvolutional neural networkForaminiferaMeso-cenozoic

Autor:innen und Institutionen

  • Aix-Marseille Université, CNRS, IRD, INRAE, CEREGE, Aix-en-Provence, France.
  • University Cheikh Anta Diop, FASTEF, Department of Life and Earth Sciences, Dakar, Senegal.
  • Fondation pour la recherche sur la biodiversité (FRB-CESAB), Montpellier, France.
  • Department of Climate Geochemistry, Max Planck Institute for Chemistry, Mainz, Germany.

Förderung

  • Cooperation française and financial support of Cheikh Anta Diop University
  • The French government under the France 2030 investment plan
  • The Initiative d’Excellence d’Aix-Marseille Université–A*MIDEX” AMX-20-TRA-029
  • French National Research Agency

Zitieren

APA

Thiam, M., Chaabane, S., & de Garidel-Thoron, T. (2026). Automated recognition of Meso-Cenozoic foraminifera from Senegalese sedimentary deposits using convolutional neural networks. PeerJ, 14, e21437. https://doi.org/10.7717/peerj.21437

Vancouver

Thiam M, Chaabane S, de Garidel-Thoron T. Automated recognition of Meso-Cenozoic foraminifera from Senegalese sedimentary deposits using convolutional neural networks. PeerJ. 2026;14:e21437. doi:10.7717/peerj.21437

BibTeX
@article{Thiam2026,
  author = {Thiam, Malick and Chaabane, Sonia and de Garidel-Thoron, Thibault},
  title = {Automated recognition of Meso-Cenozoic foraminifera from Senegalese sedimentary deposits using convolutional neural networks},
  journal = {PeerJ},
  year = {2026},
  volume = {14},
  pages = {e21437},
  doi = {10.7717/peerj.21437}
}
Kostenlos starten →