Geospatial Analysis with Cloud Computing

In the course, students acquire knowledge of how to apply remote sensing methods for environmental monitoring and modeling of human-environment systems, including the analysis of land surface changes. The course includes theory and concepts, and applies statistical and mathematical methods to analyse geospatial data and environmental data as well as social and socioeconomic data quantitatively. The methods include multivariate statistics, time series analysis, and machine learning, approaches that are computationally demanding, especially when applied to satellite image time series data over large areas, including planetary scale.

Students learn to design methodological frameworks suited to specific application domains and complete a project demonstrating their acquired knowledge. The course uses tools and datasets from multiple sources, including Landsat, MODIS, Sentinel, and VIIRS imagery, processed in Google Earth Engine, a cloud computing platform.

Progressive specialisation: A1F (has second‐cycle course/s as entry requirements)

Education level: Master's level

Admission requirements: 15 credits completed in Geographic Information Technologies at master level and 7.5 credits completed in Java or Python programming. In addition, upper secondary level English 6 or English level 2. An equivalence assessment can be made.

Selection: Selection is usually based on your grade point average from upper secondary school or the number of credit points from previous university studies, or both.