Geospatial analysis tips

The R ecosystem is very well developed for geospatial analyses, with base R including many functions that can be used for reading, visualising, and analysing spatial data, along with a number of excellent packages available to enhance, simplify, and speed up spatial analyses.

Key packages

• sf: The key library for working with spatial objects (other than rasters)
• sp: The predecessor to sf, while largely replaced there are still many situations where this package is useful.
• raster: Raster data is a commonly used spatial data type, and the raster package is the most widely used and useful package for handling data of this type.
• terra: The terra package is currently still in development but is designed to be a replacement to the raster package, offering easier to use and faster functions
• stars: This R package provides classes and methods for reading, manipulating, plotting and writing dense arrays, with space and time being array dimensions, called “data cubes”
• spatstats: An R package for spatial statistics with a strong focus on analysing spatial point patterns in 2D

Tutorials

• Introduction to visualising spatial data in R
  • A detailed demonstration and explanation on how to analyse spatial data with R, focusing on visualisation.
• Spatial data handling
  • An example workflow on how to obtain, explore and visualise spatial data, using abandoned vehicles in Chicago as an example. The code is written more for beginners.
• Intro to spatial analysis with R
  • An easy to follow example focused on handling and analysis remote sensing/satellite data

Useful resources

• CRAN task view: Analysis of spatial data
  • A collated collection of R packages assessed to be useful for spatial analysis
• R special interest group on using geographical data and mapping newsletter
  • A mailing list for discussing the development and use of R functions and packages for handling and analysis of spatial, and particularly geographical, data. The list also covers mapping and cartographic issues, and interfaces between R and geographical information systems.
• Geocomputation with R
  • An excellent comprehensive textbook explainin how to undertake most spatial analyses (or their building blocks) in R.