Agritrop
Accueil

Machine learning using digitized herbarium specimens to advance phenological research

Pearson Katelin D., Nelson Gil, Aronson Myla F.J., Bonnet Pierre, Brenskelle Laura, Davis Charles C., Denny Ellen G., Ellwood Elizabeth R., Goeau Hervé, Heberling J. Mason, Joly Alexis, Lorieul Titouan, Mazer Susan J., Meineke Emily K., Stucky Brian J., Sweeney Patrick W., White Alexander E., Soltis Pamela S.. 2020. Machine learning using digitized herbarium specimens to advance phenological research. BioScience, 70 (7) : 610-620.

Article de revue ; Article de synthèse ; Article de revue à facteur d'impact
[img]
Prévisualisation
Version publiée - Anglais
Sous licence Licence Creative Commons.
biaa044.pdf

Télécharger (1MB) | Prévisualisation

Quartile : Q1, Sujet : BIOLOGY

Résumé : Machine learning (ML) has great potential to drive scientific discovery by harvesting data from images of herbarium specimens—preserved plant material curated in natural history collections—but ML techniques have only recently been applied to this rich resource. ML has particularly strong prospects for the study of plant phenological events such as growth and reproduction. As a major indicator of climate change, driver of ecological processes, and critical determinant of plant fitness, plant phenology is an important frontier for the application of ML techniques for science and society. In the present article, we describe a generalized, modular ML workflow for extracting phenological data from images of herbarium specimens, and we discuss the advantages, limitations, and potential future improvements of this workflow. Strategic research and investment in specimen-based ML methods, along with the aggregation of herbarium specimen data, may give rise to a better understanding of life on Earth.

Mots-clés Agrovoc : apprentissage machine, phénologie, herbier, collection botanique, stade de développement végétal, changement climatique, traitement numérique d'image, collecte de données, traitement des données

Mots-clés complémentaires : deep learning

Mots-clés libres : Phenology, Machine learning, Biodiversity, Climate change, Deep Learning

Classification Agris : F40 - Écologie végétale
C30 - Documentation et information
U10 - Informatique, mathématiques et statistiques

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

Auteurs et affiliations

  • Pearson Katelin D., California Polytechnic State University (USA) - auteur correspondant
  • Nelson Gil, Florida Museum of Natural History (USA)
  • Aronson Myla F.J., University of New Jersey (USA)
  • Bonnet Pierre, CIRAD-BIOS-UMR AMAP (FRA) ORCID: 0000-0002-2828-4389
  • Brenskelle Laura, Florida Museum of Natural History (USA)
  • Davis Charles C., Havard University (USA)
  • Denny Ellen G., University of Arizona (USA)
  • Ellwood Elizabeth R., Natural History Museum (USA)
  • Goeau Hervé, CIRAD-BIOS-UMR AMAP (FRA)
  • Heberling J. Mason, Carnegie Museum of Natural History (USA)
  • Joly Alexis, INRIA (FRA)
  • Lorieul Titouan, INRIA (FRA)
  • Mazer Susan J., UC (USA)
  • Meineke Emily K., UC (USA)
  • Stucky Brian J., Florida Museum of Natural History (USA)
  • Sweeney Patrick W., Yale Peabody Museum of Natural History (USA)
  • White Alexander E., Smithsonian Institution (USA)
  • Soltis Pamela S., Florida Museum of Natural History (USA)

Source : Cirad-Agritrop (https://agritrop.cirad.fr/597012/)

Voir la notice (accès réservé à Agritrop) Voir la notice (accès réservé à Agritrop)

[ Page générée et mise en cache le 2024-12-18 ]