EUVIMEDEUVIMED entdecken
LeitlinieOpen Access · CC BY-NC 4.0

Evidence‐based guidelines for automated conservation assessments of plant species

Barnaby E Walker iD, Tarciso C C Leão, Steven P Bachman iD, Eve Lucas, Eimear Nic Lughadha iD

Conservation Biology · 2023-02 · 37 (1)

DOI: 10.1111/cobi.13992 ↗

Kurz gefasst

Leitlinie in der Zeitschrift Conservation Biology, online erschienen am 13.10.2022. Verfasst von Barnaby E Walker und 4 weiteren Autor:innen. Beteiligte Einrichtung: Royal Botanic Gardens, Kew, Richmond, Surrey, TW9 3AE, UK. Hauptthemen laut MEDLINE: Conservation of Natural Resources, Endangered Species. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Biotechnology and Biological Sciences Research Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Assessing species’ extinction risk is vital to setting conservation priorities. However, assessment endeavors, such as those used to produce the IUCN Red List of Threatened Species, have significant gaps in taxonomic coverage. Automated assessment (AA) methods are gaining popularity to fill these gaps. Choices made in developing, using, and reporting results of AA methods could hinder their successful adoption or lead to poor allocation of conservation resources. We explored how choice of data cleaning type and level, taxonomic group, training sample, and automation method affect performance of threat status predictions for plant species. We used occurrences from the Global Biodiversity Information Facility (GBIF) to generate assessments for species in 3 taxonomic groups based on 6 different occurrence‐based AA methods. We measured each method's performance and coverage following increasingly stringent occurrence cleaning. Automatically cleaned data from GBIF performed comparably to occurrence records cleaned manually by experts. However, all types of data cleaning limited the coverage of AAs. Overall, machine‐learning‐based methods performed well across taxa, even with minimal data cleaning. Results suggest a machine‐learning‐based method applied to minimally cleaned data offers the best compromise between performance and species coverage. However, optimal data cleaning, training sample, and automation methods depend on the study group, intended applications, and expertise.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Conservation of Natural ResourcesEndangered SpeciesBiodiversityExtinction, BiologicalPlants

Stichwörter der Autor:innen

IUCN Red ListLista Roja UICNaprendizaje automáticoautomationautomatizaciónbiodiversity conservationconservación de la biodiversidadmachine learning

Autor:innen und Institutionen

  • Royal Botanic Gardens, Kew, Richmond, Surrey, TW9 3AE, UK.

ORCID-Profile: Barnaby E Walker, Steven P Bachman, Eimear Nic Lughadha

Förderung

  • Biotechnology and Biological Sciences Research Council

Zitieren

APA

Walker, B. E., Leão, T. C. C., Bachman, S. P., Lucas, E., & Nic Lughadha, E. (2023). Evidence‐based guidelines for automated conservation assessments of plant species. Conservation Biology, 37(1). https://doi.org/10.1111/cobi.13992

Vancouver

Walker BE, Leão TCC, Bachman SP, Lucas E, Nic Lughadha E. Evidence‐based guidelines for automated conservation assessments of plant species. Conservation Biology. 2023;37(1). doi:10.1111/cobi.13992

BibTeX
@article{Walker2023,
  author = {Walker, Barnaby E and Leão, Tarciso C C and Bachman, Steven P and Lucas, Eve and Nic Lughadha, Eimear},
  title = {Evidence‐based guidelines for automated conservation assessments of plant species},
  journal = {Conservation Biology},
  year = {2023},
  volume = {37},
  number = {1},
  doi = {10.1111/cobi.13992}
}
Kostenlos starten →