The aim of this thesis topic is to apply spatial statistics and machine learning to a multi-resolution data cube, into which you will load various environmental, human-centric, and social-economic indicators. Overall, this effort is contributing to developing a Data Observatory for the European Data Spaces (https://digital-strategy.ec.europa.eu/en/policies/data-spaces) and Destination Earth mission. The focus will be on exploring relationships between variables of same and different resolution across local, regional, national and international scales.
The hypothesis is that at larger scales some relationships will be different than at small scales, while others stay stable, but don’t always know which and why. To navigate the modifiable areal unit problem (MAUP), there is also need to systematically evaluate different gridding strategies for the data. Results of the thesis will help to inform dataset and resolution choices for various spatial analysis tasks.
The topic is suitable for master students specialized in geoinformatics. The topic requires Python and SQL scripting and data management skills (LTOM.02.041 Geospatial Analysis with Python and R, and LTOM.02.040 Spatial Databases).
Co-supervisor Evelyn Uuemaa
