Using R for digital soil mapping

This book describes and provides many detailed examples of implementing Digital Soil Mapping (DSM) using R. The work adheres to Digital Soil Mapping theory, and presents a strong focus on how to apply it. DSM exercises are also included and cover procedures for handling and manipulating soil and spa...

Full description

Saved in:
Bibliographic Details
Main Authors Malone, Brendan P. (Author), Minasny, Budiman (Author), McBratney, A. B. (Author)
Format Electronic eBook
LanguageEnglish
Published Switzerland : Springer Nature, [2017]
SeriesProgress in soil science.
Subjects
Digital soil mapping.
R (Computer program language)
elektronické knihy
electronic books
Online AccessFull text
ISBN9783319443270
9783319443256
ISSN2352-4774
Physical Description1 online resource (xvi, 262 pages) : illustrations (some color), color maps

Cover

Table of Contents:
  • Digital soil mapping
  • R literacy for digital soil mapping
  • Getting spatial in R-. Preparatory and exploratory data analysis for digital soil mapping
  • Continuous soil attribute modeling and mapping
  • Categorical soil attribute modeling and mapping
  • Some methods for the quantification of prediction uncertainties for digital soil mapping
  • Using digital soil mapping to update, harmonize and disaggregate legacy soil maps
  • Combining continuous and categorical modeling: Digital soil mapping of soil horizons and their depths
  • Digital soil assessment: A simple enterprise suitability example.
  • Foreword; Preface; Endorsements; Acknowledgements; Contents; 1 Digital Soil Mapping; 1.1 The Fundamentals of Digital Soil Mapping; 1.2 What Is Going to Be Covered in this Book?; References; 2 R Literacy for Digital Soil Mapping; 2.1 Objective; 2.2 Introduction to R; 2.2.1 R Overview and History; 2.2.2 Finding and Installing R; 2.2.3 Running R: GUI and Scripts; 2.2.4 RStudio; 2.2.5 R Basics: Commands, Expressions, Assignments, Operators, Objects; 2.2.6 R Data Types; 2.2.7 R Data Structures; 2.2.8 Missing, Indefinite, and Infinite Values; 2.2.9 Functions, Arguments, and Packages.
  • 2.2.10 Getting Help2.2.11 Exercises; 2.3 Vectors, Matrices, and Arrays; 2.3.1 Creating and Working with Vectors; 2.3.2 Vector Arithmetic, Some Common Functions, and Vectorised Operations; 2.3.3 Matrices and Arrays; 2.3.4 Exercises; 2.4 Data Frames, Data Import, and Data Export; 2.4.1 Reading Data from Files; 2.4.2 Creating Data Frames Manually; 2.4.3 Working with Data Frames; 2.4.4 Writing Data to Files; 2.4.5 Exercises; 2.5 Graphics: The Basics; 2.5.1 Introduction to the Plot Function; 2.5.2 Exercises; 2.6 Manipulating Data; 2.6.1 Modes, Classes, Attributes, Length, and Coercion.
  • 2.6.2 Indexing, Sub-setting, Sorting, and Locating Data2.6.3 Factors; 2.6.4 Combining Data; 2.6.5 Exercises; 2.7 Exploratory Data Analysis; 2.7.1 Summary Statistics; 2.7.2 Histograms and Box Plots; 2.7.3 Normal Quantile and Cumulative Probability Plots; 2.7.4 Exercises; 2.8 Linear Models: The Basics; 2.8.1 The lm Function, Model Formulas, and Statistical Output; 2.8.2 Linear Regression; 2.8.3 Exercises; 2.9 Advanced Work: Developing Algorithms with R; Reference; 3 Getting Spatial in R; 3.1 Basic GIS Operations Using R; 3.1.1 Points; 3.1.2 Rasters.
  • 3.2 Advanced Work: Creating Interactive Maps in R3.3 Some R Packages That Are Useful for Digital Soil Mapping; Reference; 4 Preparatory and Exploratory Data Analysis for Digital Soil Mapping; 4.1 Soil Depth Functions; 4.1.1 Fit Mass Preserving Splines with R; 4.2 Intersecting Soil Point Observations with Environmental Covariates; 4.2.1 Using Rasters from File; 4.3 Some Exploratory Data Analysis; References; 5 Continuous Soil Attribute Modeling and Mapping; 5.1 Model Validation; 5.1.1 Model Goodness of Fit; 5.1.2 Model Validation; 5.2 Multiple Linear Regression.
  • 5.2.1 Applying the Model Spatially5.2.1.1 Covariate Table; 5.2.1.2 Raster Predictions; 5.2.1.3 Directly to Rasters Using Parallel Processing; 5.3 Decision Trees; 5.4 Cubist Models; 5.5 Random Forests; 5.6 Advanced Work: Model Fitting with Caret Package; 5.7 Regression Kriging; 5.7.1 Universal Kriging; 5.7.2 Regression Kriging with Cubist Models; References; 6 Categorical Soil Attribute Modeling and Mapping; 6.1 Model Validation of Categorical Prediction Models; 6.2 Multinomial Logistic Regression; 6.3 C5 Decision Trees; 6.4 Random Forests; References.

Similar Items