The end-Permian mass extinction occurred alongside a large swath of environmental changes that are often invoked as extinction mechanisms, even when a direct link is lacking. One way to elucidate the cause(s) of a mass extinction is to investigate extinction selectivity, as it can reveal critical information on organismic traits as key determinants of extinction and survival. Here we show that machine learning algorithms, specifically gradient boosted decision trees, can be used to identify determinants of extinction as well as to predict extinction risk. To understand which factors led to the end-Permian mass extinction during an extreme global warming event, we quantified the ecological selectivity of marine extinctions in the well-studied South China region. 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 had a low species richness, narrow bathymetric ranges limited to deep-water habitats, a stationary mode of life, a siliceous skeleton, or, less critically, calcitic skeletons. These selective losses directly link the extinctions 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 potentially ocean acidification.

Many modern extinction drivers are shared with past mass extinction events, such as rapid climate warming, habitat loss, pollution and invasive species. This commonality presents a key question: can the extinction risk of species during past mass extinction events inform our predictions for a modern biodiversity crisis? To investigate if it is possible to establish which species were more likely to go extinct during mass extinctions, we applied a functional trait-based model of extinction risk using a machine learning algorithm to datasets of marine fossils for the end-Permian, end-Triassic and end-Cretaceous mass extinctions. Extinction selectivity was inferred across each individual mass extinction event, before testing whether the selectivity patterns obtained could be used to ‘predict’ the extinction selectivity exhibited during the other mass extinctions. Our analyses show that, despite some similarities in extinction selectivity patterns between ancient crises, the selectivity of mass extinction events is inconsistent, which leads to a poor predictive performance. This lack of predictability is attributed to evolution in marine ecosystems, particularly during the Mesozoic Marine Revolution, associated with shifts in community structure alongside coincident Earth system changes. Our results suggest that past extinctions are unlikely to be informative for predicting extinction risk during a projected mass extinction.

Only a fast and global transformation towards decarbonization and sustainability can keep the Earth in a civilization-friendly state. As hotspots for (green) innovation and experimentation, cities could play an important role in this transition. They are also known to profit from each other’s ideas, with policy and technology innovations spreading to other cities. In this way, cities can be conceptualized as nodes in a globe-spanning learning network. The dynamics of this process are important for society’s response to climate change and other challenges, but remain poorly understood on a macroscopic level. In this contribution, we develop an approach to identify whether network-based complex contagion effects are a feature of sustainability policy adoption by cities, based on dose-response contagion and surrogate data models. We apply this methodology to an exemplary data set, comprising empirical data on the spreading of a public transport innovation (Bus Rapid Transit Systems) and a global inter-city connection network based on scheduled flight routes. Although our approach is not able to identify detailed mechanisms, our results point towards a contagious spreading process, and cannot be explained by either the network structure or the increase in global adoption rate alone. Further research on the role of a city’s abstract “global neighborhood” regarding its policy and innovation decisions is thus both needed and promising, and may connect with research on social tipping processes. The methodology is generic, and can be used to compare the predictive power for innovation spreading of different kinds of inter-city network connections, e.g. via transport links, trade, or co-membership in political networks.