Species distribution modeling

Robert J. Hijmans and Jane Elith

• Introduction
• Data preparation
  • Species occurrence data
  • Importing occurrence data
  • Data cleaning
  • Duplicate records
  • Cross-checking
  • Georeferencing
  • Sampling bias
• Absence and background points
• Environmental data
  • Raster data
  • Extracting values from rasters
• Model fitting, prediction, and evaluation
  • Model fitting
  • Model prediction
  • Model evaluation
• Modeling methods
  • Types of algorithms and data used in examples
  • Profile methods
    • Bioclim
    • Domain
    • Mahalanobis distance
  • Classical regression models
    • Generalized Linear Models
    • Generalized Additive Models
  • Machine learning methods
    • Maxent
    • Boosted Regression Trees
    • Random Forest
    • Support Vector Machines
  • Combining model predictions
• Geographic Null models
  • Geographic Distance
  • Convex hulls
  • Circles
  • Presence/absence
• References
• Appendix: Boosted regression trees for ecological modeling
  • Introduction
  • Example data
  • Fitting a model
  • Choosing the settings
  • Alternative ways to fit models
  • section{Simplifying the model
  • Plotting the functions and fitted values from the model
  • Interrogate and plot the interactions
  • Predicting to new data
  • Spatial prediction
  • Further reading