A test of species' mobility hypothesis in ecological niche modeling

Abstract
Aim: Ecological niche modeling (ENM) or species distribution modeling is increasingly used in decision-making regarding land use and biodiversity conservation. Model accuracy is essential, but can be affected by modeling choices, including the critical and ubiquitous question of how to define a model training domain. Theories have suggested designing a training domain based on areas accessible to a species for improved model performance (here termed species’ mobility hypothesis). However, we still lack direct quantitative evidence whether this approach leads to optimal model performance. Here I conducted a modeling experiment to investigate the species’ mobility hypothesis. 
Location: North and South America
Taxon: hummingbirds (Aves: Trochilidae)
Methods: The modeling experiment was based on 87 hummingbird species. A series of spatial buffers (from 5 to 5000 km with varying intervals) were created around occurrences, where background points were sampled and used as input for model calibration. The models calibrated with spatial buffers were compared with models calibrated with training domains that considered areas accessible to species, using Boyce index and sensitivity, specificity, and true skill statistics. 
Results: Model performance increased when the size of the training domain was larger, though the model performance reached saturation when size of the training domain passed a certain threshold. The threshold varied by species and evaluation method, and was generally estimated to be below 200km. The model performance based on areas accessible to species was comparable (e.g. non-significant difference in sensitivity) to the saturation performance of models when spatial buffers were used. 
Main conclusions: Positive evidence was found to support the species’ mobility hypothesis that designing a training domain based on areas accessible to species could lead to optimal or near-optimal model performance. When no information of the accessible area is available, modelers may use a tuning strategy to identify the size of the training domain for optimized model performance.