Trees are fundamental for Earth’s biodiversity as primary producers and ecosystem engineers and are responsible for many of nature’s contributions to people. Yet, many tree species at present are threatened with extinction by human activities. Accurate identification of threatened tree species is necessary to quantify the current biodiversity crisis and to prioritize conservation efforts. However, the most comprehensive dataset of tree species extinction risk—the Red List of the International Union for the Conservation of Nature (IUCN RL)—lacks assessments for a substantial number of known tree species. The RL is based on a time-consuming expert-based assessment process, which hampers the inclusion of less-known species and the continued updating of extinction risk assessments. In this study, we used a computational pipeline to approximate RL extinction risk assessments for more than 21,000 tree species (leading to an overall assessment of 89% of all known tree species) using a supervised learning approach trained based on available IUCN RL assessments. We harvested the occurrence data for tree species worldwide from online databases, which we used with other publicly available data to design features characterizing the species’ geographic range, biome and climatic affinities, and exposure to human footprint. We trained deep neural network models to predict their conservation status, based on these features. We estimated 43% of the assessed tree species to be threatened with extinction and found taxonomic and geographic heterogeneities in the distribution of threatened species. The results are consistent with the recent estimates by the Global Tree Assessment initiative, indicating that our approach provides robust and time-efficient approximations of species’ IUCN RL extinction risk assessments.