Crop Type Classification – Part 2: Notebook and Dependent Resources Added

[suriyahgit]

This PR introduces Part 2 of the Sentinel-2 Crop Type Classification workflow, including the main Jupyter notebook and its required assets.

Related Issues:-

• Crop Type Classification #162
• Kernel crash on JupyterHub environment — Dask graph likely exceeds 2 GB eopf-container-images#34 : Closed this issue as I was able to overcome the kernel crashing issue with the latest changes made to the notebook

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[review-notebook-app]

View / edit / reply to this conversation on ReviewNB

clausmichele commented on 2025-10-27T14:56:02Z
----------------------------------------------------------------

Line #1.    def _raster_bounds_polygon_32631(ds):

This function would work for any UTM projection, it's just creating a polygon. No need to specify 32631 in the name and description

[review-notebook-app]

View / edit / reply to this conversation on ReviewNB

clausmichele commented on 2025-10-27T14:56:03Z
----------------------------------------------------------------

Why climatologies? We are not working with climate data here. Monthly composites?

[review-notebook-app]

View / edit / reply to this conversation on ReviewNB

clausmichele commented on 2025-10-27T14:56:04Z
----------------------------------------------------------------

Line #72.    ds = np.where(np.isin(total_scaled, [1, 2, 4, 8, 16]), total_scaled, 0)

Why are you defining colors for combination of classes if we don't use them?