Algorithm;Acronym;Entry data;Model Overview;Reference
Bioclimatic Envelope Method;BIO;Presences;It uses the logic of the ecological niche through bioclimatic envelopes. The modeled potential distribution of species is obtained from the total set of regions in the geographic area of interest whose environmental characteristics are within the bioclimatic envelope.;Busby 1986, 1991
Maxent with default features;MXD;Presence and background points;A machine learning method based on the principle of maximum entropy that aims to approximate the distribution of a species to a uniform probability distribution from the points of occurrence of a species and environmental variables in a study area.;"Phillips et al. 2006; Phillips and Dudík 2008; Elith et al. 2011"
Simple Maxent Model;MXS;Presence and background points;A machine learning algorithm that uses the principle of maximum entropy to predict the potential distribution of species from presence-only data and environmental variables. This method is efficient to handle complex interactions between response and predictor variables.;"Phillips et al. 2004; Elith et al. 2011"
Support Vector Machine;SVM;Presence and pseudo-absence;A machine learning method that uses maximum margin classifiers that integrate non-linear limits. The environmental variables are projected onto a multidimensional space, in which an estimate of the kernel density is used, in which the ideal hyperplane is subsequently adjusted using an optimization function.;"Tax and Duin 2004; Karatzoglou et al. 2004"
Random Forest;RDF;Presence and pseudo-absence;A machine learning method that incorporates an extensive number of regression trees generated based on randomly chosen subsamples of data.;"Breiman 2001; Liaw and Wiener 2002"
Gaussian Model;GAU;Presence and absence;Gaussian processes provide a flexible approach to fitting complex statistical models. Gaussian process models are fitted via Bayesian inference, typically requiring the use of Markov chain Monte Carlo methods. This Gaussian processes model is most applied to presence/absence data for SDM.;"Rasmussen and Williams 2006; Diggle et al. 2013"