Machine Learning

Random forests, Segment Anything and U-Nets on satellite imagery: training data, spatially honest validation and inference on full scenes.

Two land cover maps of a 30 km square around Leicester side by side: the U-Net prediction on the left and the reference labels on the right. Both show the city in grey and red in the centre, surrounded by farmland in pale green, woods in dark green and reservoirs in blue. The prediction's city is smoother, with fewer separate red buildings.

Tutorial Python Part 3 of 3

Deep learning inference on large rasters: sliding-window prediction, COGs and polygons in Python

Run a trained PyTorch U-Net over a whole Sentinel-2 scene of a city it has never seen: tiled sliding-window inference on a large GeoTIFF with overlapping, blended windows, a georeferenced Cloud Optimised GeoTIFF of classes and confidence, raster-to-vector polygons with rasterio.features.shapes in a GeoPackage, and an honest check against reference labels.

Advanced 13 min read 19 October 2026

Four rows of Sentinel-2 test chips. Each row shows the image, the reference labels, the U-Net prediction and the disagreement in magenta. The prediction matches rivers, woods and fields closely, but in the city centre it draws buildings as blobs instead of separate roofs.

Tutorial Python Part 2 of 3

U-Net satellite image segmentation in PyTorch: a TorchGeo and Sentinel-2 tutorial on a CPU

Train a U-Net to segment Sentinel-2 imagery into buildings, built-up land, trees, grass and water with PyTorch, segmentation_models_pytorch and TorchGeo's Sentinel-2 pretrained ResNet-18 weights, on a CPU in five minutes. Real loss curves, per-class IoU and F1, a confusion matrix and an honest look at what limits accuracy.

Advanced 12 min read 19 October 2026

Six 128 by 128 pixel Sentinel-2 image chips of Nottingham, each shown above the same chip with its label mask overlaid: a city centre with red buildings and grey streets, a suburb, a forest, farmland, flooded gravel pits in blue and an industrial estate.

Tutorial Python Part 1 of 3

Training data for deep learning on satellite imagery: Sentinel-2 image chips in Python

Build a labelled deep learning dataset from free data: stream a Sentinel-2 L2A composite from the Planetary Computer, rasterise Overture building footprints over ESA WorldCover, cut georeferenced image chips, split them by spatial block so the test set does not leak, check the class balance and load it all as a TorchGeo dataset.

Intermediate 13 min read 19 October 2026

Tutorial Python

Segment Anything on satellite and aerial imagery in Python: a samgeo tutorial

Run Meta's Segment Anything Model on high-resolution aerial imagery with segment-geospatial (samgeo), on a CPU. Generate masks automatically, vectorise them to a GeoPackage, filter them by area, shape and NDVI to find buildings, and prompt SAM with points and boxes, checked against OpenStreetMap.

Intermediate 14 min read 17 October 2026

A land cover map of Sheffield and the Peak District predicted by a random forest: yellow grassland moors in the west, the red built-up area of Sheffield in the centre, pink cropland in the east and green woodland, with a second panel showing scattered red disagreement pixels.

Tutorial Python

Land cover classification in Python: a Sentinel-2 random forest with scikit-learn

Supervised land cover classification in Python: build seasonal Sentinel-2 composites with odc-stac, sample labels from ESA WorldCover, train a scikit-learn random forest, test it with spatial cross-validation and map Sheffield and the Peak District.

Intermediate 14 min read 17 October 2026