From 1 - 5 / 5
  • A set of tools helping with the development of critical phases of the ecological niche modeling process in Maxent. Pre-modeling analyses and explorations can be done to prepare data. Model calibration (model selection) can be done by creating and testing several candidate models. Handy options for producing final models, evaluating such models, and assessing extrapolation risks are also included. Tools for post-modeling analyses are implemented to allow for further exploration of results.

  • The package analyses species distribution models and evaluates their performance. It includes functions for variation partitioning, extracting variable importance, computing several metrics of model discrimination and calibration performance, optimizing prediction thresholds based on a number of criteria, performing multivariate environmental similarity surface (MESS) analysis, and displaying various analytical plots.

  • A collection of tools to characterize ecological niches using ellipsoid envelopes. The package inlcudes functions to perform model calibration and selection, prepare model projections to distinct scenarios, assess niche overlap, and produce virtual ecological niches are included as part of this package. Moreover, other implemented functions are useful to perform a series of common pre- and post-modeling analyses. In contrast to other tools for ecological niche and species distribution modeling, this package is the first in presenting a comprehensive set of tools that use ellipsoid envelopes as the theoretical representation of ecological niches.

  • An extensible framework that includes algorithms for presence-background (Maxent) and presence-absence (GAM, GLM, MARS, SVM, RF) for developing species distribution models using individual and community-based approaches, generate ensembles of models, calibrate and evaluate the models, and predict species potential distributions in space and time. For more information, please check the paper Naimi, B., Araujo, M.B. (2016)

  • SDMPlay is a pedagogic package that allows to compute SDMs, to understand the overall method, and to produce model outputs. The package, along with its associated vignettes, highlights the different steps of model calibration and describes how to choose the best methods to generate accurate and relevant outputs. SDMPlay proposes codes to apply a popular machine learning approach, BRT (Boosted Regression Trees) and introduces MaxEnt (Maximum Entropy).