Sentinel-1 SAR extraction with AerEO

This chapter extracts Sentinel-1 Ground Range Detected (GRD) radar backscatter (vv and vh polarizations) on the Major TOM grid — using the exact same built-ins as the optical chapters: search_stac, read_odc_stac, reproject_odc, and write_geotiff.

That is the point of the chapter: in AerEO a new sensor is usually just a new STAC collection, not a new plugin. SAR adds all-weather, day-and-night coverage to the same grid-aligned outputs you already know.

The data comes from Microsoft Planetary Computer’s sentinel-1-grd collection, served as Cloud-Optimized GeoTIFFs, so no credentials are required.

Environment setup¶

The first cell installs AerEO and any required plugins. If you are reading the rendered book or running on Binder, where the environment is already prepared, pip will report that the requirements are satisfied and skip the download.

Config files used in this chapter¶

The next cell downloads two files:

1. job_sentinel1.yaml — the AerEO job configuration.

2. chocon.geojson — the AOI over Argentina’s Chocón region.

Two SAR-specific details live in the read section. Planetary Computer’s Sentinel-1 items carry no proj metadata, so odc-stac cannot auto-guess the native grid — we declare it explicitly (crs: "EPSG:32719", UTM 19S, and resolution: 10 meters). And patch_url: planetary_computer.sign signs asset URLs at load time, the same pattern used by the Planetary Computer Sentinel-2 quickstart. Here is the full YAML we are loading:

# Common vars to reuse in the config
target_bands: [vv, vh]
aoi_path: config/aoi/chocon.geojson
# Common Job config, like name, MajorTOM grid distance, etc

name: sentinel1_sample
grid_dist: 10_000
grid_cells_margin: 10
target_aoi: ${aoi_path}
output_uri: /tmp/aereo_extraction_s1
overwrite: false

search:
  _target_: aereo.builtins.search_stac
  _partial_: true
  stac_api_url: "https://planetarycomputer.microsoft.com/api/stac/v1"
  collections:
    sentinel-1-grd: ${target_bands}
  intersects: ${aoi_path}
  start_datetime: "2024-03-20T00:00:00Z"
  end_datetime: "2024-03-31T23:59:59Z"
  pystac_open_params:
    modifier:
      _target_: planetary_computer.sign_inplace

read:
  _partial_: true
  _target_: aereo.builtins.read_odc_stac
  patch_url:
    _target_: planetary_computer.sign
  dtype: "float32"
  # Planetary Computer's sentinel-1-grd items carry no proj metadata, so
  # odc-stac cannot auto-guess the grid. Chocon is UTM 19S; GRD IW is 10 m.
  crs: "EPSG:32719"
  resolution: 10

write:
  _target_: aereo.builtins.write.write_geotiff

Loading the job¶

ExtractionJob.load_from_config() parses the YAML with Hydra, resolves every _target_ callable, and validates the resulting ExtractionJob. The config_name argument is the YAML filename without extension, and config_dir is the folder that contains it.

Search and task building¶

job.search() calls the configured search provider and returns a GeoDataFrame of matched assets. This is a separate step from execution: it only discovers what data is available, without reading or writing anything.

job.build_tasks(assets) turns those assets into a list of ExtractionTask objects. Each task groups the assets needed for one grid cell and time slice.

The executor¶

AerEO separates what to run (the tasks) from how to run them. LocalExecutor runs tasks on the local machine. The workers argument controls parallelism, and use_threads=True uses a threading backend, which is a good default for I/O-bound COG readers.

Running the extraction¶

job.execute(tasks, executor=...) hands the prepared tasks to the executor. Inside every task AerEO performs the pipeline:

read -> preprocess -> reproject -> postprocess -> write

The returned object is a GeoDataFrame of artifacts — one row per output GeoTIFF with its metadata, CRS, and footprint.

Visualizing results¶

plot_artifact_patches renders the extracted patches over the AOI. We plot the vv band in linear backscatter units with a grayscale percentile stretch. Note the classic SAR signature: dark open water in the reservoir against brighter land — acquired regardless of clouds or daylight.