Species Distribution Model Selection
Description
User-friendly framework that enables the training and the
evaluation of species distribution models (SDMs). The package implements
functions for data driven variable selection and model tuning and includes
numerous utilities to display the results. All the functions used to select
variables or to tune model hyperparameters have an interactive real-time
chart displayed in the 'RStudio' viewer pane during their execution. At the
moment only the maximum entropy method is available using the 'Java'
implementation, Phillips et al. (2006) ,
through the 'dismo' package and the 'R' implementation through the 'maxnet'
package, Phillips et al. (2017) . 'SDMtune' uses its
own script to predict maxent models, resulting in much faster predictions
for large datasets compared to native predictions from the use of the 'Java'
software. This reduces considerably the computation time when tuning the
model using the AICc.