The defining feature of spatial data analysis is the reference within the data being analyzed to locations on the surface of the earth. This is a very broad subject encompassing distinct areas of expertise such as spatial statistics, geometric computation, and image processing.
In practice, spatial data is commonly stored, viewed, and analyzed in Geographic Information System (GIS) software, of which the most well-known example is ArcGIS. However, most often, menu-based interfaces of GIS software are too narrow in scope to meet specialized demands or too inflexible to feasibly accomplish customized repetitive tasks. Writing scripts rather than using menus or working in combination with external software are two commonly used paths to solve such problems. However, what if we can use a single environment, combining the advantages of programming and spatial data analysis capabilities with a comprehensive ecosystem of computational tools that are readily implementable in customized procedures?
This book will demonstrate that the R programming language is indeed such an environment and teach you how to use it in order to perform various spatial data analysis tasks.
Most currently available books on this subject are focused on advanced applications such as spatial statistics, assuming you have prior knowledge of R and the respective scientific domains. Yet, introductory material on R from the point of view of a spatial data analyst, which is focused on introductory topics such as spatial data handling, computation, and visualization, is scarce. This book aims to fill that gap.
Chapter 1, The R Environment, introduces the R environment, shows how to install R, and how to use it. Some of the basic concepts related to writing R code are introduced.
Chapter 2, Working with Vectors and Time Series, covers the basic data structure in R, which is vector. The main types of vectors (numeric, character, and logical) as well as basic operations on vectors (such as subsetting and summarizing vector properties) are reviewed. Working with dates and displaying a graphical output, two highly relevant abilities commonly applied later in the book, are also introduced in this chapter.
Chapter 3, Working with Tables, focuses on tables and automated calculations in R. This chapter teaches you how tabular data can be handled and how calculations of a repetitive nature based on tabular data can be carried out using loops and conditional statements. Reshaping and joining tables (vital skills for any data analysis) are also covered.
Chapter 4, Working with Rasters, brings the reader into the realm of spatial data analysis in R, starting with the raster data structure. Basic operations such as import and export, visualization and summary, and subsetting and extraction of raster values are covered here. Simple manipulations of raster values, including assignment, raster algebra, and reclassification are also presented.
Chapter 5, Working with Points, Lines, and Polygons, covers the second type of spatial data structures—vector layers. The basic methodology of working with point, line, and polygon layers is reviewed, followed by the coverage of more advanced operations, including reprojection, geometric calculations, spatial querying, and joining new data to existing layers.
Chapter 6, Modifying Rasters and Analyzing Raster Time Series, covers several advanced themes associated with raster data analysis in R. Geometric modifications of raster data, such as cropping, mosaicking, and aggregating are reviewed. Operations related to cell neighborhoods, including focal filtering, clumping, and topography-related calculations are covered next. Additional themes include resampling, reprojection, and handling of spatio-temporal raster data.
Chapter 7, Combining Vector and Raster Datasets, integrates the material presented in Chapter 5, Working with Points, Lines, and Polygons, and Chapter 6, Modifying Rasters and Analyzing Raster Time Series, by demonstrating how rasters and vector layers can be combined in a single analysis. Transformation between raster and vector data structures as well as data extraction from a raster based on vector layers are covered in this chapter.
Chapter 8, Spatial Interpolation of Point Data, presents the subject of spatial interpolation in R from a practical point of view. Using a real-world case study, several common interpolation methods are applied and evaluated. An automated interpolation procedure is then constructed in order to create a series of interpolated maps from point data.
Chapter 9, Advanced Visualization of Spatial Data, shows readers how to produce publication-quality maps mainly using the popular ggplot2 R package.
Appendix A, External Datasets Used in Examples, provides a summary of the datasets used in the examples.
Appendix B, Cited References, lists the cited resources.