Program

The course is structured as follows:

Day 1: The New Spatial Stack in R

Introduction to R’s modern spatial ecosystem, focusing on simple features, the DE-9IM spatial framework, and handling vector and raster data. Explore advanced data types, including data cubes and spatial statistics.

Day 2: Spatial Operations

Learn raster-vector and vector-raster operations, including geometry measures, predicates, and transformations. Cover spherical geometry, polygonizing, rasterizing, interpolation, and dasymetric mapping. Master techniques for up- and down-scaling through aggregation, sampling, and area-weighted interpolation.

Day 3: Inference in Spatial Data

Dive into spatial correlation analysis for point patterns, geostatistical, and lattice data. Develop skills in fitting regression models that account for spatial correlation.

Day 4: Prediction and Simulation

Advance to predictive modeling, including density estimation and simulating point patterns. Learn geostatistical methods such as kriging and conditional simulation, along with Gaussian Markov Random Field (GMRF) simulations.

References

Bivand, Roger S., Edzer Pebesma, and Virgilio Gómez-Rubio. 2013. Applied Spatial Data Analysis with R. Second. New York: Springer. https://doi.org/10.1007/978-1-4614-7618-4.
Pebesma, Edzer, and Roger Bivand. 2023. Spatial Data Science: With Applications in R. Boca Raton: Chapman; Hall/CRC. https://doi.org/10.1201/9780429459016.