IUCNN – Deep learning approaches to approximate species' extinction risk. (16th December 2021)

• Record Type: Journal Article
• Authors: Zizka, Alexander; Andermann, Tobias; Silvestro, Daniele
• Editors: Capinha, Cesar
• Is Part Of: Diversity & distributions. Volume 28:Number 2(2022)
• Page Start: 227
• Page End: 241
• Publication Date: 2021-12-16
• Subjects: automated assessment -- conservation assessment -- IUCN -- machine learning -- red list -- R‐package; Biodiversity -- Periodicals; Biodiversity conservation -- Periodicals; 577
• DOI: 10.1111/ddi.13450
• Languages: English
• ISSNs: 1366-9516

Abstract

Abstract: Aim: The Red List (RL) from the International Union for the Conservation of Nature is the most comprehensive global quantification of extinction risk, and widely used in applied conservation as well as in biogeographic and ecological research. Yet, due to the time‐consuming assessment process, the RL is biased taxonomically and geographically, which limits its application on large scales, in particular for underdocumented areas such as the tropics, or understudied taxa, such as most plants and invertebrates. Here, we present IUCNN, an R‐package implementing deep learning models to predict species RL status from publicly available geographic occurrence records (and other data if available). Innovation: We implement a user‐friendly workflow to train and validate neural network models, and use them to predict species RL status. IUCNN contains specific functions for extinction risk prediction in the RL framework, including a regression‐based approach to account for the ordinal nature of RL categories, a Bayesian approach for improved uncertainty quantification and a convolutional neural network to predict species RL status based on their raw geographic occurrences. Most analyses run with few lines of code, not requiring users to have prior experience with neural network models. We demonstrate the use of IUCNN on an empirical dataset of ~14, 000 orchid species, for which IUCNN models can predict extinction risk within minutes, while outperforming comparable methods based on species occurrence information. Main conclusions: IUCNN harnesses innovative methodology to estimate the RL status of large numbers of species. By providing estimates of the number and identity of threatened species in custom geographic or taxonomic datasets, IUCNN enables large‐scale automated assessments of the extinction risk of species so far not well represented on the official RL.