TY - JOUR T1 - Machine learning (decision tree analysis) identifies ecological selectivity patterns across the end-Permian mass extinction JF - bioRxiv DO - 10.1101/2020.10.09.332999 SP - 2020.10.09.332999 AU - William J. Foster AU - Georgy Ayzel AU - Terry T. Isson AU - Maria Mutti AU - Martin Aberhan Y1 - 2020/01/01 UR - http://biorxiv.org/content/early/2020/10/10/2020.10.09.332999.abstract N2 - Decision tree algorithms are rarely utilized in paleontological research, and here we show that machine learning algorithms can be used to identify determinants of extinction as well as predict extinction risk. This application of decision tree algorithms is important because the ecological selectivity of mass extinctions can reveal critical information on organismic traits as key determinants of extinction and hence the causes of extinction. To understand which factors led to the mass extinction of life during an extreme global warming event, we quantified the ecological selectivity of marine extinctions in the well-studied South China region during the end-Permian mass extinction using the categorized gradient boosting algorithm. We find that extinction selectivity varies between different groups of organisms and that a synergy of multiple environmental stressors best explains the overall end-Permian extinction selectivity pattern. Extinction risk was greater for genera that were limited to deep-water habitats, had a stationary mode of life, possessed a siliceous skeleton or, less critically, had calcitic skeletons. These selective losses directly link the extinction to the environmental effects of rapid injections of carbon dioxide into the ocean-atmosphere system, specifically the combined effects of expanded oxygen minimum zones, rapid warming, and ocean acidification.Competing Interest StatementThe authors have declared no competing interest. ER -