Add fix for poor data coverage granules

intertidal/composites.py

@@ -65,6 +65,20 @@ def tidal_thresholds(
     return tide_thresh_low, tide_thresh_high
 
 
+def filter_granules(dataset):
+    """
+    Return False for any Sentinel-2 dataset with a MGRS
+    granule region code in the list of bad region codes.
+    """
+    drop_list = ["50HKG", "50HNF", "51LWD", "51LXE", "51LZF",
+                 "52LBL", "52LCL", "52LDK", "53HNA", "53LRC",
+                 "54GYU", "54LWR", "54LXR", "54LYR", "55GBP",
+                 "55KEA", "55KFV", "55KGV", "55KHT", "55KHU",
+                 "56KKC", "56KLC", "56KMC", "56KMV", "56KNU",
+                 "54LWQ", "54LWP"]
+    return dataset.metadata.region_code not in drop_list
+
+
 def tidal_composites(
     satellite_ds,
     threshold_lowtide=0.15,
@@ -459,6 +473,8 @@ def tidal_composites_cli(
                 geom = None
 
             # Load satellite data and dataset IDs for metadata
+            # Use `filter_granules` predicate function to drop list of
+            # custom Sentinel-2 MGRS granules with poor data coverage
             satellite_ds, dss_s2, _ = load_data(
                 dc=dc,
                 study_area=study_area,
@@ -476,6 +492,7 @@ def tidal_composites_cli(
                 skip_broken_datasets=True,
                 dataset_maturity="final",
                 dtype="int16",
+                dataset_predicate=filter_granules,
             )
             log.info(
                 f"{run_id}: Found {len(satellite_ds.time)} satellite data timesteps"

tests/README.md

@@ -10,7 +10,7 @@ Integration tests
 
 This directory contains tests that are run to verify that DEA Intertidal code runs correctly. The ``test_intertidal.py`` file runs a small-scale full workflow analysis over an intertidal flat in the Gulf of Carpentaria using the DEA Intertidal [Command Line Interface (CLI) tools](../notebooks/Intertidal_CLI.ipynb), and compares these results against a LiDAR validation DEM to produce some simple accuracy metrics.
 
-The latest integration test completed at **2025-05-02 17:14**. Compared to the previous run, it had an:
+The latest integration test completed at **2025-05-05 11:48**. Compared to the previous run, it had an:
 - RMSE accuracy of **0.14 m ( :heavy_minus_sign: no change)**
 - MAE accuracy of **0.12 m ( :heavy_minus_sign: no change)**
 - Bias of **0.12 m ( :heavy_minus_sign: no change)**

tests/validation.csv

@@ -110,3 +110,4 @@ time,Correlation,RMSE,MAE,R-squared,Bias,Regression slope
 2025-05-02 01:43:13.002005+00:00,0.975,0.145,0.123,0.95,0.117,1.119
 2025-05-02 06:32:51.594612+00:00,0.975,0.145,0.123,0.95,0.117,1.119
 2025-05-02 07:14:19.583638+00:00,0.975,0.145,0.123,0.95,0.117,1.119
+2025-05-05 01:48:26.455865+00:00,0.975,0.145,0.123,0.95,0.117,1.119