Skip to contents

flexsdm

Overview

Species distribution modeling has become a standard tool in several research areas such as ecology, conservation biology, biogeography, paleobiogeography, and epidemiology. Species distribution modeling is an area of active research in both theoretical and methodological aspects. One of the most exciting features of flexsdm is its high manipulation and parametrization capacity based on different functions and arguments. These attributes enable users to define a complete or partial modeling workflow specific for a modeling situation (e.g., number of variables, number of records, different algorithms, algorithms tuning, ensemble methods).

Structure of flexsdm

The function of flexsdm package are organized into three major modeling steps

1. Pre-modeling functions

Set tools that prepare modeling input data (e.g., species occurrences thinning, sample pseudo-absences or background points, delimitation of calibration area).

2. Modeling functions

It includes functions related to modeling construction and validation. Several of them can be grouped into fit_*, tune_*, and esm_* family functions. fit_* construct and validate models with default hyper-parameter values. tune_* construct and validate models searching for the best hyper-parameter values combination. esm_ construct and validate Ensemble of Small Models.

Model evaluation

  • sdm_eval() Calculate different model performance metrics

fit_* functions family

  • fit_gam() Fit and validate Generalized Additive Models
  • fit_gau() Fit and validate Gaussian Process models
  • fit_gbm() Fit and validate Generalized Boosted Regression models
  • fit_glm() Fit and validate Generalized Linear Models
  • fit_max() Fit and validate Maximum Entropy models
  • fit_net() Fit and validate Neural Networks models
  • fit_raf() Fit and validate Random Forest models
  • fit_svm() Fit and validate Support Vector Machine models

tune_* functions family

  • tune_gbm() Fit and validate Generalized Boosted Regression models with exploration of hyper-parameters
  • tune_max() Fit and validate Maximum Entropy models with exploration of hyper-parameters
  • tune_net() Fit and validate Neural Networks models with exploration of hyper-parameters
  • tune_raf() Fit and validate Random Forest models with exploration of hyper-parameters
  • tune_svm() Fit and validate Support Vector Machine models with exploration of hyper-parameters

Model ensemble

  • fit_ensemble() Fit and validate ensemble models with different ensemble methods

esm_* functions family

  • esm_gam() Fit and validate Generalized Additive Models with Ensemble of Small Model approach
  • esm_gau() Fit and validate Gaussian Process models Models with Ensemble of Small Model approach
  • esm_gbm() Fit and validate Generalized Boosted Regression models with Ensemble of Small Model approach
  • esm_glm() Fit and validate Generalized Linear Models with Ensemble of Small Model approach
  • esm_max() Fit and validate Maximum Entropy models with Ensemble of Small Model approach
  • esm_net() Fit and validate Neural Networks models with Ensemble of Small Model approach
  • esm_svm() Fit and validate Support Vector Machine models with Ensemble of Small Model approach

3. Post-modeling functions

Tools related to models’ geographical predictions, evaluation, and correction.

  • sdm_predict() Spatial predictions of individual and ensemble model
  • sdm_summarize() Merge model performance tables
  • interp() Raster interpolation between two time periods
  • extra_eval() Measure model extrapolation
  • extra_truncate() Constraint suitability values under a given extrapolation value
  • msdm_priori() Create spatial predictor variables to reduce overprediction of species distribution models
  • msdm_posteriori() Methods to correct overprediction of species distribution models based on occurrences and suitability patterns.

4. Graphical model exploration

Useful tools to visually explore models’ geographical and environemtal predictions, model extrapolation, and partial depnendece plot.

  • p_pdp() Create partial dependence plot(s) to explore the marginal effect of predictors on suitability
  • p_bpdp() Create partial dependence surface plot(s) to explore the bivariate marginal effect of predictors on suitability
  • p_extra() Graphical exploration of extrapolation or suitability pattern in the environmental and geographical space
  • data_pdp() Calculate data to construct partial dependence plots
  • data_bpdp() Calculate data to construct partial dependence surface plots

Installation

You can install the development version of flexsdm from github

⚠️ NOTE: The version 1.4-22 of terra package is causing errors when trying to instal flexsdm. Please, first install a version ≥ 1.5-12 of terra package available on CRAN or development version of terra and then flexsdm.

# install.packages("remotes")

# For Windows and Mac OS operating systems
remotes::install_github("sjevelazco/flexsdm")

# For Linux operating system
remotes::install_github("sjevelazco/flexsdm@HEAD")

Package website

See the package website (https://sjevelazco.github.io/flexsdm/) for functions explanation and vignettes.

Package citation

Velazco, S.J.E., Rose, M.B., Andrade, A.F.A., Minoli, I., Franklin, J. (2022). flexsdm: An R package for supporting a comprehensive and flexible species distribution modelling workflow. Methods in Ecology and Evolution, 13(8) 1661–1669. https://doi.org/10.1111/2041-210X.13874

Test the package and give us your feedback here or send an e-mail to .