Species Distribution Models with GIS and Machine Learning in R

Video description

Implement and interpret common machine learning techniques to build habitat suitability maps for birds in Peninsular Malaysia

About This Video

  • Learn hands-on applications of the most important R concepts with limited mathematical jargon
  • Get started with time series from scratch
  • Explore how to use both GIS and machine learning techniques for spatial data analysis

In Detail

In this course, you’ll work with real-world spatial data from Peninsular Malaysia to gain hands-on experience with mapping habitat suitability in conjunction with classical SDM models, such as MaxENT and Bioclim, and machine learning alternatives, such as random forests. The course will ensure that you are equipped to put spatial data and machine learning analysis into practice right away. You’ll have developed the skills necessary for working with ecological data and impress potential employers with your GIS and machine learning skills in R.

Throughout the course, you’ll learn how to map suitable habitats for species using R. You’ll also explore common ecological modeling techniques and species distribution modeling (SDM) using real-life data. As you advance, the course will guide you in implementing some of the common Geographic Information Systems (GIS) and spatial data analysis techniques in R and use it to access ecological data. You’ll perform common GIS and data analysis tasks related to SDMs, including accessing species-presence data, and get to grips with classical SDM techniques.

Publisher resources

Download Example Code

Table of contents

  1. Chapter 1 : Introduction to the Species Distribution Modelling Course
    1. INTRODUCTION TO THE COURSE: Instructor & Course Details 00:01:09
    2. What is Species Distribution Modelling? 00:05:48
    3. Introduction to R for habitat suitability modelling 00:05:08
    4. Conclusion to Section 1 00:01:09
  2. Chapter 2 : The Basics of GIS for Species Distribution Models (SDMs)-Part 1
    1. Where to Obtain Raster Data for Building SDMs 00:04:31
    2. Accessing and Cleaning GBIF Data 00:08:25
    3. Accessing GBIF Data via R" 00:10:17
    4. Other Sources of Species Geo-location Data 00:03:29
    5. Extract Species Geo-Location Data from Other Sources in R 00:05:33
    6. Access Climate & Other Data via R 00:04:09
    7. Working with Elevation Data in R 00:04:41
    8. Deriving Topographic Products from Elevation Data 00:05:32
    9. Conclusions to Section 2 00:01:39
  3. Chapter 3 : Pre-Processing Raster and Spatial Data for SDMs
    1. Some Prerequisites 00:03:02
    2. CRS of the Data 00:03:53
    3. Clip Raster Data to a Given Extent 00:04:07
    4. Resize the Raster Data 00:03:28
    5. Basic Data Visualization 00:03:40
    6. Conclusions to Section 3 00:01:39
  4. Chapter 4 : Classical SDM Techniques
    1. Underlying Rationale 00:09:32
    2. Bioclim 00:07:31
    3. Model Evaluation 00:04:03
    4. Maxent Interface in R 00:02:49
    5. Maxent SDM in R 00:07:10
    6. Maxent Analysis with the red package 00:04:10
    7. Domain SDM in R 00:08:19
    8. Conclusion to Section 4 00:02:09
  5. Chapter 5 : Machine Learning Models for Habitat Suitability
    1. Machine Learning Modelling 00:10:46
    2. Pre-processing Steps Prior to Modelling with Presence and Absence Data 00:07:44
    3. Prior to Implementing Machine Learning 00:05:32
    4. GLMs for Habitat Suitability 00:13:18
    5. Support Vector Machines 00:07:24
    6. kNN 00:04:33
    7. Random Forest (RF) 00:11:35
    8. Gradient Boosting Machine (GBM) 00:08:28
    9. Further Model Evaluation 00:06:53
    10. Conclusions to Section 5 00:02:18

Product information

  • Title: Species Distribution Models with GIS and Machine Learning in R
  • Author(s): Minerva Singh
  • Release date: December 2019
  • Publisher(s): Packt Publishing
  • ISBN: 9781838982393