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

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.
Liste complète des métadonnées

Littérature citée [40 références]  Voir  Masquer  Télécharger

https://hal.umontpellier.fr/hal-02137748
Contributeur : Yannick Brohard <>
Soumis le : jeudi 23 mai 2019 - 11:49:06
Dernière modification le : mercredi 6 novembre 2019 - 18:26:58

Fichier

Lorieul_et_al-2019-Application...
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

Citation

Titouan Lorieul, Katelin Pearson, Elizabeth Ellwood, Hervé Goëau, Jean‐francois Molino, et al.. Toward a large-scale and deep phenological stage annotation of herbarium specimens: Case studies from temperate, tropical, and equatorial floras. Applications in Plant Sciences, Wiley, 2019, 7 (3), pp.e01233. ⟨10.1002/aps3.1233⟩. ⟨hal-02137748⟩

Partager

Métriques

Consultations de la notice

224

Téléchargements de fichiers

188