Authors' Summary: Marine plankton communities play a central role within Earth's climate system, with important processes often divided among different “functional groups.” Changes in the relative abundance of these groups can therefore impact on ecosystem function. However, the oceans are vast, and samples are sparse, so global distributions are not well known. Statistical species distribution models (SDM's) have been developed that predict global distributions based on their relationships with observed environmental variables. They appear to perform well at summarizing present day distributions, and are increasingly being used to predict ecosystem changes throughout the 21st century. But it is not guaranteed that such models remain valid over time.

Rather than wait 100 years to find out, we applied a statistical SDM to a complex virtual ocean, and trained it using virtual observations that match real-world ocean samples. This allows us to jump forward to the end-of-century to test the accuracy of our predictions. The SDM performed well at qualitatively predicting “present day” plankton distributions but yielded poor end-of-century predictions. Our case study emphasizes both the importance of environmental variable selection, and of changes in the underlying relationships between environmental variables and plankton distributions, in terms of model validity over time.