Accurate predictive modeling of conservation status in animal species using supervised learning

Abstract

Abstract Conservation management to mitigate extinction of wildlife becomes more crucial than ever as global impacts due to anthropogenic activities and climate change continue to create devastation for species around the globe. Despite ongoing efforts to understand species constantly changing population dynamics due to anthropogenic stressors, there is a strong disconnect between conservation research and conservation policy, what is known as the “Conservation Gap”. The International Union of Conservation of Nature, the IUCN, is a globally recognized organization that works to sustain biodiversity by maintaining a ranking of species known as their Red List. However, the IUCN does not currently utilize genetic information to assess species conservation status despite the availability of molecular data. Here we use over 7300 studies collated from the MacroPopGen database, and over 450 published articles from the public repository DataDryad, focused on conservation and population genetics, sampling across a variety of invertebrate and vertebrate taxa, and using IUCN classifications to predict species endangerment using machine learning. Our models were able to accurately predict species threat level classified by the IUCN using both measures of genetic diversity and differentiation with IUCN assessment criteria. Our goal is to use these models to help determine and communicate conservation status to practitioners that takes into consideration all available species-specific information.