image: This is an artistic rendition of global conservation risk hotspots for land plant species. view more
Credit: Image courtesy of Abbie Zimmer (Ohio State University, Columbus, OH)
Researchers report a machine-learning approach to identify land plants at risk of extinction. Plant biodiversity supports food chain diversity, helps counter natural disasters, and contributes to ecosystem productivity. The International Union for Conservation of Nature Red List of threatened species contains only a small fraction of the species found on Earth, partly because species assessments are expensive and time-consuming. Anahí Espíndola and colleagues developed a machine-learning approach to predict plant species at risk of extinction using open-source geographic, environmental, and morphological trait data for more than 150,000 land plant species. The authors identified variables predicting extinction risk, including geographic and bioclimatic traits, and calculated the probability of a species being designated "at-risk" based on the traits. The authors report that a large number of previously unassessed land plant species are likely at risk of extinction and may need to be considered for inclusion in the Red List. Further, the approach can be used to identify species at the highest extinction risk and to pinpoint geographic regions with the greatest need for conservation efforts by pairing GPS coordinates with risk probabilities. According to the authors, the approach can be used to guide policies aimed at allocating resources for biodiversity conservation.
Article #18-04098: "Predicting plant conservation priorities on a global scale," by Tara A. Pelletier, Bryan C. Carstens, David C. Tank, Jack Sullivan, and Anahí Espíndola.
MEDIA CONTACT: Anahí Espíndola, University of Maryland, College Park, MD; tel: 301-405-3920; e-mail: anahiesp@umd.edu; Tara A. Pelletier, Radford University, VA; tel: 978-979-4057; e-mail: tpelletier@radford.edu
###
Journal
Proceedings of the National Academy of Sciences