Expand operator hard-negative AOIs

scripts/README.md

@@ -182,13 +182,14 @@ This writes GeoTIFF/GeoJSON pairs and `operator_samples_manifest.json` under
 `/app/storage/operator-data` inside the container, which maps to
 `storage/operator-data` in the Tower appdata checkout. The default corpus
 contains reference AOIs for Geel, Mol, Turnhout, Herentals, Balen, Retie and
-Westerlo plus background candidates for Postel-bos, Lommel-heide and
-Kasterlee-bos. Normal reference AOIs still fail when GRB returns no buildings;
-background candidates are explicitly marked with `sample_role` and may write an
-empty reference FeatureCollection for negative-tile training. The helper fetches
-only the explicit documented AOIs, records Digitaal Vlaanderen attribution and
-reuses existing files by default. Use `--force` only when the local runtime
-artifacts should be regenerated.
+Westerlo plus background candidates for Postel-bos, Lommel-heide,
+Kasterlee-bos, Dessel-heide, Ravels-bos, Meerhout-bos, Geel-Bel,
+Arendonk-heide and Herenthout-bos. Normal reference AOIs still fail when GRB
+returns no buildings; background candidates are explicitly marked with
+`sample_role` and may write an empty reference FeatureCollection for
+negative-tile training. The helper fetches only the explicit documented AOIs,
+records Digitaal Vlaanderen attribution and reuses existing files by default.
+Use `--force` only when the local runtime artifacts should be regenerated.
 
 The real-data smoke is intentionally mutating and refuses to run without
 operator-supplied files. Current V1 upload support expects a georeferenced
@@ -351,6 +352,8 @@ Current Tower audit status:
 - `yolo-building-tile-hardneg160r4` and `yolo-building-tile-hardneg160r8`:
   repeat-heavy hard-negative variants; useful evidence, but add more unique
   background AOIs before training another hard-negative-balanced candidate.
+- Regenerate `operator_samples_manifest.json` after pulling Sprint 147+ so the
+  expanded unique background AOI set is available for the next tile export.
 
 For hard-negative-balanced experiments, repeat only train-split negative tiles
 from samples marked `sample_role=background_candidate`:
@@ -415,7 +418,7 @@ before changing model defaults:
 
 ```bash
 OPERATOR_SAMPLE_MANIFEST_PATH=storage/operator-data/operator_samples_manifest.json \
-OPERATOR_BACKGROUND_SAMPLE_SLUGS="postel_bos lommel_heide kasterlee_bos" \
+OPERATOR_BACKGROUND_SAMPLE_SLUGS="postel_bos lommel_heide kasterlee_bos dessel_heide ravels_bos meerhout_bos geel_bel arendonk_heide herenthout_bos" \
 QUALITY_MODEL_ASSET_IDS="geointel-building-yolov8n-expanded160e50-pt geointel-building-yolov8n-tile30-pt yolov8s-building-segmentation-pt" \
 QUALITY_TILE_SIZES="640" \
 QUALITY_TILE_OVERLAPS="64" \

scripts/prepare_operator_real_data_samples.py

@@ -114,6 +114,60 @@ SAMPLES: dict[str, OperatorSample] = {
         sample_role="background_candidate",
         allow_empty_reference=True,
     ),
+    "dessel_heide": OperatorSample(
+        slug="dessel_heide",
+        display_name="Dessel heath background candidate",
+        center_lon=5.092,
+        center_lat=51.235,
+        half_size_m=260.0,
+        sample_role="background_candidate",
+        allow_empty_reference=True,
+    ),
+    "ravels_bos": OperatorSample(
+        slug="ravels_bos",
+        display_name="Ravels forest background candidate",
+        center_lon=4.977,
+        center_lat=51.384,
+        half_size_m=260.0,
+        sample_role="background_candidate",
+        allow_empty_reference=True,
+    ),
+    "meerhout_bos": OperatorSample(
+        slug="meerhout_bos",
+        display_name="Meerhout forest background candidate",
+        center_lon=5.069,
+        center_lat=51.115,
+        half_size_m=260.0,
+        sample_role="background_candidate",
+        allow_empty_reference=True,
+    ),
+    "geel_bel": OperatorSample(
+        slug="geel_bel",
+        display_name="Geel-Bel rural background candidate",
+        center_lon=5.046,
+        center_lat=51.137,
+        half_size_m=260.0,
+        sample_role="background_candidate",
+        allow_empty_reference=True,
+    ),
+    "arendonk_heide": OperatorSample(
+        slug="arendonk_heide",
+        display_name="Arendonk heath background candidate",
+        center_lon=5.238,
+        center_lat=51.334,
+        half_size_m=260.0,
+        sample_role="background_candidate",
+        allow_empty_reference=True,
+    ),
+    "herenthout_bos": OperatorSample(
+        slug="herenthout_bos",
+        display_name="Herenthout forest background candidate",
+        center_lon=4.781,
+        center_lat=51.143,
+        half_size_m=260.0,
+        sample_role="background_candidate",
+        allow_empty_reference=True,
+    ),
 }