chooseGCM
Selecting General Circulation Models for Species Distribution Modeling
Methods to help selecting General Circulation Models (GCMs)
in the context of projecting models to future scenarios. It is provided
clusterization algorithms, distance and correlation metrics, as well as
a tailor-made algorithm to detect the optimum subset of GCMs that recreate
the environment of all GCMs as proposed in Esser et al. (2025)
chooseGCM: an R package with a toolkit to select General Circulation Models
chooseGCM 
The goal of chooseGCM is to help researchers aiming to project Species
Distribution Models and Ecological Niche Models to future scenarios by
applying a selection routine to the General Circulation Models.
Installation
You can install the development version of chooseGCM from
GitHub with:
install.packages("devtools")
devtools::install_github("luizesser/chooseGCM")
The package is also available on CRAN. Users are able to install it using the following code:
install.packages("chooseGCM")
Other packages
If you liked chooseGCM, get to know our other packages. Currently, we
have also the caretSDM
package, a package to run Species Distribution Modeling, which is also
used in the article
Esser, L.F., Bailly, D., Lima, M.R., Ré, R. 2025. chooseGCM: A Toolkit to Select General Circulation Models in R. Global Change Biology , 31(1), e70008. Available at: https://doi.org/10.1111/gcb.70008.
to test chooseGCM using SDMs.
Three breakthroughs distinguish caretSDM:
-
The strong geoprocessing background that allows for automation on spatial data handling by rescaling data to a common grid, with the possibility to model distributions using river networks (via segmented lines), overcoming limitations for aquatic species, while also enabling interactive data viewing without the use of an external GIS software;
-
The underlying ML tools that allows for the integration of 115+ classification algorithms with automated workflows, from hyperparameter tuning to ensemble prediction, eliminating coding barriers for advanced techniques, while allowing flexibility for experienced users;
-
The use of recyclable objects, designed to track all analysis steps within a single class, enhancing transparency and scientific rigor.
caretSDM is available on both GitHub and CRAN:
install.packages("devtools")
devtools::install_github("luizesser/caretSDM")
install.packages("caretSDM")