Course overview
Data collected across varying spatial locations require specialist statistical techniques to explore. Spatially autocorrelated data appears across a vast array of fields and industries including aerial image processing, astronomy, ecology, engineering, environmental sciences, epidemiology, forestry, energy, spatial economics and transportation, making this course particularly useful for anyone working, or planning across these areas. Spatial data tends to appear in one of three forms: geostatistical data, lattice data and point pattern data. This course will introduce the varying probabilistic and statistical methods used to analyse all three.
- Introduction to spatial data
- Modelling spatial data
- Machine learning for spatial data and applications
Course learning outcomes
- Apply core mathematical and computational techniques for spatially structured data.
- Critique different methods for sampling spatial data.
- Design a spatial analysis and implement in statistical software (R).
- Compare and contrast different spatial statistical approaches.
- Communicate analysis to a range of stakeholders visually, verbally and mathematically.