This spatial data science project will use open data, available for the city of Madrid over the past few years, involving:
The problems to be approached may include:
- Are these three variables correlated, and if yes how?
- Can we use these correlations to improve mapping air quality over, say, maps obtained by simple interpolation of the spatially very sparse air quality measurements?
- How can we organize a workflow such that it is easy to understand, easy to manage, and developed collaboratively?
- How can we handle large datasets (several Gb)?
Room No. 255.