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 extant species on Earth, partly because species assessments are expensive and time-consuming.
Researchers 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 study uses open-source geographic, environmental, and morphological trait data, making this the largest assessment of conservation risk to date and the only global assessment for plants. 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 results indicate that a large number of unassessed species are likely at risk of extinction and may need to be considered for inclusion in the Red List and also identify several geographic regions with the highest need of conservation efforts, many of which are not currently recognized as regions of global concern. 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.