Middle Eocene Radiolarian image dataset from ODP Leg 207 (Demerara Rise)

DOI

Labeled images of middle Eocene, ca 40 million years ago (Ma), radiolarians, including other microfossils, other particles, broken fragments etc... The radiolarians in this dataset are classified into species, genus, family, superfamily or higher order levels. This dataset was used for a PhD project and in a paper titled: Convolutional neural network application on a new middle Eocene radiolarian dataset, to train a Resnet50 convolutional neural network, with an accuracy of about 86.6 %.

Identifier
DOI https://doi.org/10.57745/E9YXW6
Metadata Access https://entrepot.recherche.data.gouv.fr/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=doi:10.57745/E9YXW6
Provenance
Creator Carlsson, Veronica ORCID logo; Tetard, Martin ORCID logo; Meunier, Mathias ORCID logo; Danelian, Taniel ORCID logo
Publisher Recherche Data Gouv
Contributor Carlsson, Veronica; Entrepôt-Catalogue Recherche Data Gouv
Publication Year 2023
Funding Reference HORIZON EUROPE Marie Sklodowska-Curie Actions 847568
Rights etalab 2.0; info:eu-repo/semantics/openAccess; https://spdx.org/licenses/etalab-2.0.html
OpenAccess true
Contact Carlsson, Veronica (Université de Lille)
Representation
Resource Type Dataset
Format application/zip; text/plain
Size 264650667; 2024
Version 1.2
Discipline Computer Science; Geosciences; Earth and Environmental Science; Environmental Research; Natural Sciences