Potential species distribution modeling and the use of principal component analysis as predictor variables

Abstract

Prior to modeling the potential distribution of a species it is recommended to carry out analyses to reduceerrors in the model, especially those caused by the spatial autocorrelation of presence data or the multi-collinearity ofthe environmental predictors used. This paper proposes statistical methods to solve drawbacks frequently disregardedwhen such models are built. We use spatial records of 3 species characteristic of the Mexican humid mountain forestand 2 sets of original variables. The selection of presence-only records with no autocorrelation was made by applyingboth randomness and pattern analyses. Through principal component analysis (PCA) the 2 sets of original variableswere transformed into 4 different sets to produce the species distribution models with the modeling application inMaxent. Model precision was higher than 90% applying a binomial test and was always higher than 0.9 with the areaunder the curve (AUC) and with the partial receiver operating characteristic (ROC). The results show that the recordsselected with the randomness method proposed here and the use of the PCA to select the environmental predictorsgenerated more parsimonious predictive models, with a precision higher than 95%, and in addition, the responsevariables show no spatial autocorrelation.