¹û¶³Ó°Ôº

This term one module introduces the theory, methods, and tools of spatial analysis essential for careers in spatial data analytics. Unlike traditional GIS or Geocomputation courses, this course has a specific focus on the principles, properties and parameters that are part of spatial analysis and how to understand and apply these effectively within geographic and data science-oriented research.

The first half of the module (week 1 to 5) provides a detailed introduction to spatial concepts required to analyse spatial data accurately and effectively. We will introduce students to the foundational concepts of 1.) scale and geography; 2.) spatial dependence & autocorrelation; and 3.) suitability mapping (e.g., Analytic Hierarchy Process (AHP) and Maximum Entropy Modelling (MAXENT)).

The second half (week 6 to 10) then focuses on the applications of different spatial analysis techniques within current data science research such as geodemographic classification, geostatistics and transport network analysis. Lastly, we will introduce students to spatial regression and geographically weighted regression models for evidence-based research and performing inferential statistics on spatial data.

The module will equip students with the foundations of the core principles and tenets underlying the analysis of spatial data and how these principles are currently being applied within spatial data science.

By the end of the module, the student should:

• Possess a good understanding of the principles underlying the analysis of spatial vector and raster data in general and spatial statistics.
• Be able to account for the key properties of spatial data within their analysis techniques and highlight issues of uncertainty with the results of these analyses;
• Be able to examine, analyse and simulate a range of spatial patterns and processes. Be able to use geostatistical tools to analyse and interpolate spatial patterns;
• Be able to understand how different spatial analysis techniques are currently being used within spatial data science, from cluster analysis, network analysis to geodemographic classification;
• Be able to perform inferential statistics on spatial data and carryout hypothesis testing for evidence-based research using the different types of regression-based spatial models.

The course will consist of 10 lectures and 10 practical sessions.Ìý