Results of model performance tests for potential reservoir species using spatial subdivisions.

Shown are AUC values for models using points from the west (W) or the east (E); the percentage of the total study area predicted to be over the balance threshold; and the p-values for one-tailed binomial tests between the number of test points predicted to be suitable for the species and the fractional predicted area over the balance threshold. P-values in bold indicate models that performed significantly better than random; that is, significantly more test points were predicted to be suitable for the species than expected based on the fraction of the total area predicted to be suitable. W>E = western points were used for training, eastern for testing; E>W = eastern points were used for training, and western for testing.