Complex niche models show low performance in identifying the most important range-limiting environmental variables and in transferring habitat suitability to novel environmental conditions (Warren and Seifert, 2011; Warren et al., 2014). This package helps to identify the most important set of uncorrelated variables and to fine-tune Maxent's regularization multiplier. In combination, this allows to constrain complexity and increase performance of Maxent niche models (assessed by information criteria, such as AICc (Akaike, 1974) , and by the area under the receiver operating characteristic (AUC) (Fielding and Bell, 1997). Users of this package should be familiar with Maxent niche modelling.
The R package 'MaxentVariableSelection' helps selecting the most important set of uncorrelated environmental variables along with the optimal regularization multiplier for Maxent Niche Modeling. This allows constrain model complexity, and thus, to increase model peformance and transferability of habitat suitability to novel environmental conditions (e.g. future climate scenarios).
To install and load the package from CRAN, type:
To install and load the package from github, type:
The folder 'vignettes' contains documentation files that show how to use the package. The main function of the package (VariableSelection) and the example datasets in 'inst/extdata' are described in the 'MaxentVariableSelection-manual.pdf'.
Corrected text version of package citation
Updated the citation of the 'MaxentVariableSelection' to Jueterbock A, Smolina I, Coyer JA and Hoarau, G (2016) The fate of the Arctic seaweed Fucus distichus under climate change: an ecological niche modelling approach. Ecology and Evolution 6(6), 1712-1724
Initial release on github while associated paper is submitted to Journal of Biogeogrpahy. The package will be uploaded on CRAN upon acceptance of the manuscript