Influence of model selection on the predicted distribution of the seagrass Zostera marina

There is an increasing need to model the distribution of species and habitats for effective conservation planning, but there is a paucity of models for the marine environment. We used presence (131) and absence (219) records of the marine angiosperm Zostera marina L. from the archipelago of SW Finland, northern Baltic Sea, to model its distribution in a 5400 km2 area. We used depth, slope, turbidity, wave exposure and distance to sandy shores as environmental predictors, and compared a presence-absence method: generalised additive model (GAM), with a presence only method: maximum entropy (Maxent). Models were validated using semi-independent data sets. Both models performed well and described the niche of Z. marina fairly consistently, although there were differences in the way the models weighted the environmental variables, and consequently the spatial predictions differed somewhat. A notable outcome from the process was that with relatively equal model performance, the area actually predicted in geographical space can vary by twofold. The area predicted as suitable for Z. marina by the ensemble was almost half of that predicted by the GAM model by itself. The ensemble of model predictions increased the model predictive capability marginally and clearly shifted the model towards a more conservative prediction, increasing specificity, but at the same time sacrificing sensitivity. The environmental predictors selected into the final models described the potential distribution of Z. marina well and showed that in the northern Baltic the species occupies a narrow niche, typically thriving in shallow and moderately exposed to exposed locations near sandy shores. We conclude that a prediction based on a combination of model results provides a more realistic estimate of the core area suitable for Z. marina and should be the modelling approach implemented in conservation planning and management.