Spatial Machine Learning
Spatial Statistics
Preface
Introduction
1
Introduction to spatial mapping
2
Open source spatial software
3
Lab: Spatial data in R
Geostatistics
4
Intro to geostatistical analysis
5
Lab: 1. steps of geostatistical analysis
6
Theory: Stochastic process
7
Variograms and their properties
8
Model for spatial data with trend
9
Model for spatial data with trend (advanced)
10
Selecting a model
11
Kriging predictions
12
Details on kriging predictions
13
Lab: Analysis elevation data (continued)
14
Lab: Variogram properties
15
Special cases in geostatistics
16
Lab: Lognormal kriging and anisotropy
Spatial Machine Learning
17
Introduction to Machine Learning
18
Challenges of geostatistical methods
19
Introduction to Random Forest
20
Spatial correlation in RF
21
Spatial correlation in ML
22
Predictor selection and interpretation
23
Lab: Spatial machine learning – regression
24
Lab: Spatial ML – classification
Model assessment
25
Assessment strategies and metrics
26
Lab: Evaluate model performance
Spatial sampling
27
Sampling for ML and validation
28
Lab: Spatial sampling
Outlook
29
Outlook: more spatial statistics
Spatial Machine Learning
In this section, machine learning methods are introduced for spatial mapping.
16
Lab: Lognormal kriging and anisotropy
17
Introduction to Machine Learning