Testing the Skill of a Species Distribution Model Using a 21st Century Virtual Ecosystem

Plankton communities play an important role in marine food webs, in biogeochemical cycling, and in Earth's climate; yet observations are sparse, and predictions of how they might respond to climate change vary. Correlative species distribution models (SDM's) have been applied to predicting biogeography based on relationships to observed environmental variables. To investigate sources of uncertainty, we use a correlative SDM to predict the plankton biogeography of a 21st century marine ecosystem model (Darwin). Darwin output is sampled to mimic historical ocean observations, and the SDM is trained using generalized additive models. We find that predictive skill varies across test cases, and between functional groups, with errors that are more attributable to spatiotemporal sampling bias than sample size. End‐of‐century predictions are poor, limited by changes in target‐predictor relationships over time. Our findings illustrate the fundamental challenges faced by empirical models in using limited observational data to predict complex, dynamic systems. Plain Language 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. Key Points We use a correlative speci