Spatial Data Analysis

In the last decades the availability of data has increased substantially. Advances in spatial data retrieval
systems (e.g. GPS, satellites,..), and advances in computer power and computer storage capabilities, increased
the demand for efficient computational techniques for spatial data analysis. Spatial data analysis
techniques are becoming essential in many scientific fields like ecology, meteorology, climatology, geology,
geography, and even in some social sciences.
The aim of this course is to present the most popular analysis techniques for different types of spatial
data (spatial statistic and spatial machine learning techniques). Classical methods will be introduces and
subsequently expanded with modern spatial data analysis techniques (Bayesian methods). The course
1 will be divided in four sections; geostatistical data analysis, lattice data analysis and point pattern analysis,
concluding with some popular spatial machine learning techniques (e.g. spatial clustering, spatial
regression methods,...).
The focus of the course will be more on practical aspects of spatial data analysis, as on mathematical
theory. The lab work will be focused on analysis and modelling of spatial data with the R statistical
package. Available libraries for spatial data visualization, analysis and modelling will be used, especially
R–INLA. Students will have to perform some homework and one extensive project.