Format: ORAL

Alexander Zizka1,2 Daniele Silvestro3

1 Department of Biology, Philipps-University Marburg, Marburg, Germany 2 Naturalis Biodiversity Center, Leiden, The Netherlands 3 Department of Biology, University of Fribourg

The IUCN Red List of threatened species (RL) is the most authoritative global quantification of extinction risk, and widely used in ecological research and applied conservation. Yet, due to the time-consuming assessment process, the RL is taxonomically and geographically biased, in particular towards the global North and charismatic taxa. One promising approach to speed up RL assessments and overcome these biases is the use of AI to predict extinction risk based on the combination of information from digitized collection specimens and citizen science data with remote sensing information on the environment. Here, we present IUCNN, an approach using deep learning models to predict species RL status from publicly available geographic occurrence records (and other data, such as traits if available). We show that AI methods can reach accuracies up to 95% in identifying threatened species and use the results from three recently published case studies-on the orchid family, global tree species and the biota of Madagascar-to illustrate the potential and caveats on using AI and collection specimen to predict species extinction risk.