Agritrop
Home

Toward a large‐scale and deep phenological stage annotation of herbarium specimens: Case studies from temperate, tropical, and equatorial floras

Lorieul Titouan, Pearson Katelin D., Ellwood Elizabeth R., Goeau Hervé, Molino Jean-François, Sweeney Patrick W., Yost Jennifer M., Sachs Joel, Mata‐Montero Erik, Nelson Gil, Soltis Pamela S., Bonnet Pierre, Joly Alexis. 2019. Toward a large‐scale and deep phenological stage annotation of herbarium specimens: Case studies from temperate, tropical, and equatorial floras. Applications in Plant Sciences, 7 (3), n.spéc. Emerging Frontiers in Phenological Research:e01233, 14 p.

Journal article ; Article de revue à facteur d'impact Revue en libre accès total
[img]
Preview
Published version - Anglais
License Licence Creative Commons.
593491.pdf

Télécharger (968kB) | Preview

Quartile : Q2, Sujet : PLANT SCIENCES

Abstract : Premise of the Study: Phenological annotation models computed on large‐scale herbarium data sets were developed and tested in this study. Methods: Herbarium specimens represent a significant resource with which to study plant phenology. Nevertheless, phenological annotation of herbarium specimens is time‐consuming, requires substantial human investment, and is difficult to mobilize at large taxonomic scales. We created and evaluated new methods based on deep learning techniques to automate annotation of phenological stages and tested these methods on four herbarium data sets representing temperate, tropical, and equatorial American floras. Results: Deep learning allowed correct detection of fertile material with an accuracy of 96.3%. Accuracy was slightly decreased for finer‐scale information (84.3% for flower and 80.5% for fruit detection). Discussion: The method described has the potential to allow fine‐grained phenological annotation of herbarium specimens at large ecological scales. Deeper investigation regarding the taxonomic scalability of this approach is needed.

Mots-clés Agrovoc : Herbier, Collection botanique, Phénologie, Classification, Automatisation, Réseau de neurones, Flore

Mots-clés complémentaires : deep learning

Mots-clés libres : Convolutional neural network, Deep Learning, Natural history collections, Phenological stage annotation, Visual data classification

Classification Agris : F70 - Plant taxonomy and geography
U10 - Computer science, mathematics and statistics
F40 - Plant ecology

Champ stratégique Cirad : CTS 1 (2019-) - Biodiversité

Auteurs et affiliations

  • Lorieul Titouan, INRIA (FRA) - auteur correspondant
  • Pearson Katelin D., University of Florida (USA)
  • Ellwood Elizabeth R., Natural History Museum (USA)
  • Goeau Hervé, CIRAD-BIOS-UMR AMAP (FRA)
  • Molino Jean-François, IRD (FRA)
  • Sweeney Patrick W., Yale University (USA)
  • Yost Jennifer M., California State University (USA)
  • Sachs Joel, Agriculture and Agri-Food Canada (CAN)
  • Mata‐Montero Erik, Instituto Tecnológico de Costa Rica (CRI)
  • Nelson Gil, University of Florida (USA)
  • Soltis Pamela S., Natural History Museum (USA)
  • Bonnet Pierre, CIRAD-BIOS-UMR AMAP (FRA) ORCID: 0000-0002-2828-4389
  • Joly Alexis, INRIA (FRA)

Source : Cirad-Agritrop (https://agritrop.cirad.fr/593491/)

View Item (staff only) View Item (staff only)

[ Page générée et mise en cache le 2021-02-15 ]