TY - JOUR
T1 - Selection of environmental predictors for species distribution modeling in Maxent
AU - Cruz-Cárdenas, Gustavo
AU - Villaseñor, José Luis
AU - López-Mata, Lauro
AU - Martínez-Meyer, Enrique
AU - Ortiz, Enrique
N1 - Publisher Copyright:
© 2014, Universidad Autonoma Chapingo. All rights reserved.
PY - 2014/5/1
Y1 - 2014/5/1
N2 - Prior to conducting the modeling of the potential distribution of a species, it is advised to make a pre-selection of covariables because redundancy or irrelevant variables may induce errors in most modeling systems. In this study, we propose an automated method for a priori selection of covariables used in modeling. We used five typical species of the Mexican flora (Catopheria chiapensis, Liquidambar styraciflua, Quercus martinezii, Telanthopora grandifolia and Viburnum acutifolium) and 56 environmental covariables. Presence-absence matrices were generated for each species and were analyzed using logistic regression, and the resulting model of each species was evaluated via a bootstrap resampling. We modeled the distribution of five species using maximum entropy and employed three sets of environmental covariables. The precision of the models generated was evaluated with the confidence intervals for each receiver operating characteristic (ROC) curve. The confidence intervals of the resulting ROC curves showed no significant difference between (P < 0.05) the three predictive models generated; nevertheless, the most parsimonious model was obtained with the proposed method.
AB - Prior to conducting the modeling of the potential distribution of a species, it is advised to make a pre-selection of covariables because redundancy or irrelevant variables may induce errors in most modeling systems. In this study, we propose an automated method for a priori selection of covariables used in modeling. We used five typical species of the Mexican flora (Catopheria chiapensis, Liquidambar styraciflua, Quercus martinezii, Telanthopora grandifolia and Viburnum acutifolium) and 56 environmental covariables. Presence-absence matrices were generated for each species and were analyzed using logistic regression, and the resulting model of each species was evaluated via a bootstrap resampling. We modeled the distribution of five species using maximum entropy and employed three sets of environmental covariables. The precision of the models generated was evaluated with the confidence intervals for each receiver operating characteristic (ROC) curve. The confidence intervals of the resulting ROC curves showed no significant difference between (P < 0.05) the three predictive models generated; nevertheless, the most parsimonious model was obtained with the proposed method.
KW - Automated selection of covariables
KW - Remote sensing data
KW - Soil properties
UR - http://www.scopus.com/inward/record.url?scp=84907818795&partnerID=8YFLogxK
U2 - 10.5154/r.rchscfa.2013.09.034
DO - 10.5154/r.rchscfa.2013.09.034
M3 - Artículo
SN - 2007-3828
VL - 20
SP - 187
EP - 201
JO - Revista Chapingo, Serie Ciencias Forestales y del Ambiente
JF - Revista Chapingo, Serie Ciencias Forestales y del Ambiente
IS - 2
ER -