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

• Published in: Applications in plant sciences Vol. 7; no. 3; pp. e01233 - n/a
• Main Authors: Lorieul, Titouan, Pearson, Katelin D., Ellwood, Elizabeth R., Goëau, Hervé, Molino, Jean‐Francois, Sweeney, Patrick W., Yost, Jennifer M., Sachs, Joel, Mata‐Montero, Erick, Nelson, Gil, Soltis, Pamela S., Bonnet, Pierre, Joly, Alexis
• Format: Journal Article
• Language: English
• Published: United States John Wiley & Sons, Inc 01.03.2019; Wiley; John Wiley and Sons Inc
• Subjects: Application; Automation; Biodiversity; Biodiversity and Ecology; Botanics; Climate change; convolutional neural network; deep learning; Digitization; Ecology, environment; Ecosystems; Environmental Sciences; flowers; fruits; herbaria; herbarium data; humans; Life Sciences; natural history collections; phenological stage annotation; phenology; Plant sciences; Studies; Systematics, Phylogenetics and taxonomy; Vegetal Biology; visual data classification; herbarium data; phenological stage annotation; deep learning; natural history collections; convolutional neural network; visual data classification; Deep learning; Herbarium data; Visual data classification; Phenological stage annotation; Natural history collections; Convolutional neural network
• ISSN: 2168-0450; 2168-0450
• DOI: 10.1002/aps3.1233

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.