ENMs
Type of resources
Keywords
Contact for the resource
status
Groups

The package provides a single function with all arguments necessary to calculate ENMs: variable collinearity control, bias control, accessible area delimitation, pseudoabsence allocation, data partition, several algorithms, thresholds, evaluation metrics, overprediction, ensemble modelling, and projections over time and space.

A set of functions for preparing data, training and evaluating dismo models, and comparing ecological niches. It complements to dismo. The package includes functions for implementing species distribution models (SDMs) and ecological niche models (ENMs). The heart of the package is a set of "training" functions which automatically tune and parameterize a model based on several popular algorithms (e.g., MaxEnt, GLMs, BRTs, GAMs, etc.). Ancillary tools include estimation of spatial sampling bias, model evaluation, and calculation of biotic velocity (speed and direction at which a species' range moves through time).

The package runs ecological niche models over all combinations of userdefined settings (i.e., tuning), performs cross validation to evaluate models, and returns data tables to aid in selection of optimal model settings that balance goodnessoffit and model complexity. Moreover, it provides functions to partition data spatially (or not) for cross validation, to plot multiple visualizations of results, to run null models to estimate significance and effect sizes of performance metrics, and to calculate niche overlap between model predictions, among others. The package was originally built for Maxent models, but the current version allows possible extensions for any modeling algorithm.

The package allows to map species richness and endemism based on stacked species distribution models (SSDM). Individuals SDMs can be created using a single or multiple algorithms (ensemble SDMs). For each species, a SDM can yield a habitat suitability map, a binary map, a betweenalgorithm variance map, and can assess variable importance, algorithm accuracy, and between algorithm correlation. Methods to stack individual SDMs include summing individual probabilities and thresholding then summing. Thresholding can be based on a specific evaluation metric or by drawing repeatedly from a Bernoulli distribution. The SSDM package also provides a userfriendly interface.

A workflow for ecological niche models based on "dismo". The package include functions for modelling that helps to seamlessly integrate modelling into a pipeline of data manipulation and visualisation.