The R Script associated with this page is available here. Download this file and open it (or copy-paste into a new script) with RStudio so you can follow along.

1 Setup

library(spocc)
library(raster)

## Loading required package: sp

library(sp)
library(rgdal)

## rgdal: version: 1.4-4, (SVN revision 833)
##  Geospatial Data Abstraction Library extensions to R successfully loaded
##  Loaded GDAL runtime: GDAL 2.1.3, released 2017/20/01
##  Path to GDAL shared files: /Library/Frameworks/R.framework/Versions/3.6/Resources/library/rgdal/gdal
##  GDAL binary built with GEOS: FALSE 
##  Loaded PROJ.4 runtime: Rel. 4.9.3, 15 August 2016, [PJ_VERSION: 493]
##  Path to PROJ.4 shared files: /Library/Frameworks/R.framework/Versions/3.6/Resources/library/rgdal/proj
##  Linking to sp version: 1.3-1

library(ROCR)

## Loading required package: gplots

## 
## Attaching package: 'gplots'

## The following object is masked from 'package:stats':
## 
##     lowess

library(corrplot)

## corrplot 0.84 loaded

library(maxnet)
library(spThin)

## Loading required package: spam

## Loading required package: dotCall64

## Loading required package: grid

## Spam version 2.2-2 (2019-03-07) is loaded.
## Type 'help( Spam)' or 'demo( spam)' for a short introduction 
## and overview of this package.
## Help for individual functions is also obtained by adding the
## suffix '.spam' to the function name, e.g. 'help( chol.spam)'.

## 
## Attaching package: 'spam'

## The following objects are masked from 'package:base':
## 
##     backsolve, forwardsolve

## Loading required package: fields

## Loading required package: maps

## See https://github.com/NCAR/Fields for
##  an extensive vignette, other supplements and source code

## Loading required package: knitr

2 The worst SDM ever

The goal of this section is to use the simplest possible set of operations to build an SDM. There are many packages that will perform much more refined versions of these steps, at the expense that decisions are made behind the scenes, or may be obscure to the user. So before getting into fancier tools, let’s see what the bare minimum looks like.

This is not the simplest possible code, because it requires some familiarity with the internal components of different spatial objects. The tradeoff is that none of the key operations are performed behind the scenes by specialized SDM functions. I realize this is not always pretty, but I hope for that reason it can demonstrate some coding gynmastics for beginners.

2.1 Get presence data

The spocc package allows you to hit a number of the larger databases for presence-only data within R. They provide a number of useful pieces of metadata, if your’e into that sort of this. For this, we’re not; we just want lat and lon.

Decision: You assume the database of choice has sufficiently checked for errors in biology or typos. You know what happens when you assume…

–>

–> –>

–> –> –> –> –> –>

–> –> –> –> –> –> –> –> –> –> –> –> –> –> –> –> –> –>

Introduction to Species Distribution Modeling

Cory Merow

1 Setup

2 The worst SDM ever

2.1 Get presence data