Paintings predict the distribution of species, or the challenge of selecting environmental predictors and evaluation statistics

• Published in: Global ecology and biogeography Vol. 27; no. 1/2; pp. 245 - 256
• Main Authors: Fourcade, Yoan, Besnard, Aurélien G., Secondi, Jean
• Format: Journal Article
• Language: English
• Published: Oxford John Wiley & Sons Ltd 01.02.2018; Wiley Subscription Services, Inc; Wiley
• Subjects: AUC; Biodiversity and Ecology; biogeography; Computation; Ecology; Ekologi; Environment models; environmental factors; environmental predictors; Environmental Sciences; Environmental statistics; environmental variables; Evaluation; Innovations; Macroecological Methods; MaxEnt; model evaluation; model validation; Partitioning; Real variables; Reliability analysis; researchers; ROC curve; Spatial distribution; Species; species distribution modelling; Statistical analysis; Statistical methods; Statistical tests; Statistics; topography; TSS; Variables; environmental predictors; MaxEnt; model evaluation; TSS; environmental variables; ROC curve; species distribution modelling; AUC

Aim: Species distribution modelling, a family of statistical methods that predicts species distributions from a set of occurrences and environmental predictors, is now routinely applied in many macroecological studies. However, the reliability of evaluation metrics usually employed to validate these...