Spatial Statistics
Lecture slides & Course practicals
Preface
This course material website brings together core methods for spatial data analysis and prediction, with a focus on three complementary pillars: classical geostatistics, spatial machine learning, and sampling design. You will learn how spatial dependence can be quantified and exploited for prediction, how modern machine-learning approaches can be adapted to spatial data, and how thoughtful sampling strategies underpin reliable inference and model evaluation. The materials combine conceptual explanations with hands-on examples using real geospatial data, emphasizing reproducible, open-source workflows. The goal is not only to apply methods, but to develop spatial intuition and critical judgement, so you can choose, justify, and evaluate analytical approaches in realistic scientific and applied contexts.
On the course material
This webpage contains the course materials on spatial statistics. The content is split targeting different topics and learner levels and forms input for different courses.
Lectures
At the top you can download a PDF of the slides. It contains what was shown during the lecture. The present website was compiled from the same document, but also includes in addition references or some additional explanation that were hidden to not clutter the slides
Such text is set in light gray.
Computer practicals
Some chapters contain computer labs that can worked through as individual work.
Software requirements
You need an installation of a recent version of R and an code editor suitable for R such as RStudio Desktop (optional, but recommended). The R packages needed are given at the start of each computer lab.
Source
The part on Geostatistics is based and was expanded on from the course material on Spatial Statistics of Andreas Papritz (retired ETH Zurich). I am grateful to be able to build on these extensive materials.
How done
The course materials were created as a Quarto book, to learn more about Quarto books visit https://quarto.org/docs/books.
Further books and ressources
Spatial data in R
Pebesma, E.; Bivand, R. (2023). Spatial Data Science: With Applications in R (1st ed.). 314 pages. Chapman and Hall/CRC, Boca Raton. https://doi.org/10.1201/9780429459016, https://r-spatial.org/book/
Lovelace, R., Nowosad, J., & Muechnow, J. (2025). Geocomputation with R. CRC Press See also chapter on statistical learning. https://r.geocompx.org/
Dorman, M., Graser, A., Nowosad, J., & Lovelace, R. (2025). Geocomputation with Python. CRC Press https://py.geocompx.org/
Geostatistics
Diggle, P. J., and Jr. P. J. Ribeiro (2007). Model-Based Geostatistics. Springer.
Webster, R., and M. A. Oliver (2007). Geostatistics for Environmental Scientists. 2nd ed. John Wiley & Sons.
Machine learning
Gareth, J., Daniela Witten, Trevor Hastie, and Robert Tibshirani (2023). An Introduction to Statistical Learning: With Applications in R. Springer Texts in Statistics.
Nussbaum, M. (2023). Machine Learning and Processing of Large Data. In Encyclopedia of Soils in the Environment. Elsevier, https://doi.org/10.1016/B978-0-12-822974-3.00065-3.
Spatial sampling
Brus, D. J. (2019). Sampling for digital soil mapping: A tutorial supported by r scripts. Geoderma, 338, 464–480. <https://doi. org/10.1016/j.geoderma.2018.07.036>{target=“_blank”}.
Brus, D. J. (2022). Spatial sampling with R. Taylor & Francis, https://dickbrus.github.io/SpatialSamplingwithR/.
de Gruijter, J. J., Brus, D., Bierkens, M., & Knotters, M. (2006). Sampling for natural resource monitoring. Springer. https://doi.org/10.1007/3-540-33161-1.