In this training session you will learn about the main concepts / aspects related to raster data cubes, cloud-optimized geotiff (COG) and SpatioTemporal Asset Catalog (STAC), working with a practical example in Python. Using the eumap library and the training samples provided in the hackathon, you will perform a complete workflow for spatial predictive mapping, including:  Spacetime overlay (through STAC + COG),  Train a Random Forest classifier (with hyper-parameter optimization),  produce a classification output (also through STAC + COG). All the steps were executed in Google Colab and all the data (points and rasters) accessed directly from the cloud (http://stac.ecodatacube.eu).