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

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