Functions provided by this pedagogic package allow to compute models with two popular machine learning approaches, BRT (Boosted Regression Trees) and MaxEnt (Maximum Entropy) applied on sets of marine biological and environmental data. They include the possibility of managing the main parameters for the construction of the models. Classic tools to evaluate model performance are provided (Area Under the Curve, omission rate and confusion matrix, map standard deviation) and are completed with tools to perform null models. The biological dataset includes original occurrences of two species of the class Echinoidea (sea urchins) present on the Kerguelen Plateau and that show contrasted ecological niches. The environmental dataset includes the corresponding statistics for 15 abiotic and biotic descriptors summarized for the Kerguelen Plateau and for different periods in a raster format. The package can be used for practicals to teach and learn the basics of species distribution modelling. Maps of potential distribution can be produced based on the example data included in the package, which brings prior observations of the influence of spatial and temporal heterogeneities on modelling performances. The user can also provide his own datasets to use the modelling functions.
|Author||Guillaumot Charlene [aut, cre], Martin Alexis [aut], Eleaume Marc [aut], Saucede Thomas [aut]|
|Maintainer||Guillaumot Charlene <[email protected]>|
|Package repository||View on CRAN|
Install the latest version of this package by entering the following in R:
Any scripts or data that you put into this service are public.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.