About this module
Environmental data are growing exponentially, and Earth Observation has moved from "download the archive" to cloud-native access: search, access and analyse petabytes of satellite imagery without ever storing it locally. This module walks through that shift — the sensors behind the data, the open standards that make cloud-native EO possible, and a complete hands-on workflow in Google Earth Engine, culminating in a real water-quality case study of the Urumea estuary in San Sebastián.
How AI tools fit into how you learn here
Earth Engine's API, STAC queries and xarray/stackstac calls have plenty of syntax that's easy to get wrong. Rather than debugging alone, you'll practise prompting an LLM tutor to explain an error, suggest a fix, or justify why one cloud-masking approach is preferable to another — then verifying that explanation against the notebook's actual output. That prompting-and-verifying loop is itself a skill we build across the course, not a shortcut around learning the material.
Topics covered
- ✓ The environmental data revolution: from Landsat archives to cloud-native EO
- ✓ Types of environmental sensors — passive/active, remote/in-situ, mobile/fixed
- ✓ Choosing the right sensor: spatial, temporal, spectral and radiometric resolution
- ✓ Open standards: STAC (SpatioTemporal Asset Catalog), Cloud-Optimized GeoTIFF, and Zarr
- ✓ Hands-on with Google Earth Engine and Google Colab
- ✓ Case study: monitoring water quality in the Urumea estuary with Sentinel-2
Hands-on notebooks
- Authenticate to Google Earth Engine from Google Colab
- Search Sentinel-2 imagery with an Area of Interest, date range and cloud-cover filter
- Open Sentinel-2 imagery as an xarray Dataset using stackstac
- Visualise imagery with RGB composites and individual spectral bands
- Filter cloud cover using SCL / QA metadata to build cloud-free collections
- Extract features from Earth Observation data for AI models
- Integrate the full cloud-native workflow into one AI-ready environmental dataset
Optional: MATLAB Self-Paced Track
Provided by our technology partner MathWorks as a free, self-paced complement to this week's session. Budget around 20–30% more time than the stated duration.
Deep Learning Onramp — this week's course ~1.5 hMATLAB Online access and GPU credits are provided free to registered participants during the course period (August 2026).
Where to find the rest of the material
The seven Colab notebooks referenced above are distributed through the course platform ahead of the live session. If you can't find them, reach the course team via the enquiries section on the main course page.