Automated conservation assessment of the orchid family with deep learning.

Citation metadata

From: Conservation Biology(Vol. 35, Issue 3)
Publisher: Wiley Subscription Services, Inc.
Document Type: Report; Brief article
Length: 397 words

Document controls

Main content

Abstract :

Keywords: biodiversity; data quality; IUC-NN; IUCN Red List; machine learning; Orchidaceae; sampling bias; aprendizaje mecánico; biodiversidad; calidad de datos; IUC-NN; Lista Roja UICN; Orchidaceae; sesgo de muestreo Abstract International Union for Conservation of Nature (IUCN) Red List assessments are essential for prioritizing conservation needs but are resource intensive and therefore available only for a fraction of global species richness. Automated conservation assessments based on digitally available geographic occurrence records can be a rapid alternative, but it is unclear how reliable these assessments are. We conducted automated conservation assessments for 13,910 species (47.3% of the known species in the family) of the diverse and globally distributed orchid family (Orchidaceae), for which most species (13,049) were previously unassessed by IUCN. We used a novel method based on a deep neural network (IUC-NN). We identified 4,342 orchid species (31.2% of the evaluated species) as possibly threatened with extinction (equivalent to IUCN categories critically endangered [CR], endangered [EN], or vulnerable [VU]) and Madagascar, East Africa, Southeast Asia, and several oceanic islands as priority areas for orchid conservation. Orchidaceae provided a model with which to test the sensitivity of automated assessment methods to problems with data availability, data quality, and geographic sampling bias. The IUC-NN identified possibly threatened species with an accuracy of 84.3%, with significantly lower geographic evaluation bias relative to the IUCN Red List and was robust even when data availability was low and there were geographic errors in the input data. Overall, our results demonstrate that automated assessments have an important role to play in identifying species at the greatest risk of extinction. Article Note: Article impact statement: An automated conservation assessment with deep learning reveals global centers of orchid extinction risk. CAPTION(S): Supplementary methods related to the sensitivity analyses (Appendix S1), information on geographic cleaning, detailed IUCN category predictions, computation time and occurrence sampling (Appendix S2), conservation assessments for 13,910 orchid species translation of the article (Appendix S3), results on the impact of feature choice on IUC-NN performance (Appendix S4), and per species comparison of IUC-NN and IUCN RL (Appendix S5) are available online. Data and analysis scripts are available from zenodo (10.5281/zenodo.3862199). The authors are solely responsible for the content and functionality of these materials. Queries (other than absence of the material) should be directed to the corresponding author. Supplementary Material Supplementary Material Supplementary Material Supplementary Material Byline: Alexander Zizka, Daniele Silvestro, Pati Vitt, Tiffany M. Knight

Source Citation

Source Citation   

Gale Document Number: GALE|A663335806