⚗️ Increase DBSCAN min_samples from 300 to 320

Reduces the active subglacial lake inventory count from 221 to 204. This gets rid of some most likely false positive lakes, in particular, a large one over the grounding zone of Pine Island Glacier.

Author: weiji14

antarctic_subglacial_lakes_3031.geojson

@@ -191,7 +191,7 @@
 basins: pd.core.indexes.numeric.Int64Index = drainage_basins.index  # run on all basins
 
 eps: int = 3000  # ICESat-2 tracks are separated by ~3 km across track, with each laser pair ~90 m apart
-min_samples: int = 300
+min_samples: int = 320
 for basin_index in tqdm.tqdm(iterable=basins):
     # Initial data cleaning, filter to rows that are in the drainage basin
     basin = drainage_basins.loc[basin_index]
@@ -416,7 +416,7 @@
 
 # %%
 # Generate gridded time-series of ice elevation over lake
-cycles: tuple = (3, 4, 5, 6, 7, 8, 9)
+cycles: tuple = (3, 4, 5, 6, 7, 8, 9, 10, 11, 12)
 os.makedirs(name=f"figures/{placename}", exist_ok=True)
 ds_lake: xr.Dataset = deepicedrain.spatiotemporal_cube(
     table=df_lake.to_pandas(),

antarctic_subglacial_lakes_4326.geojson

@@ -255,69 +255,69 @@ sources:
     metadata:
       lakedict:
         - lakename: Kamb 1
-          ids: [81]
+          ids: [76]
         - lakename: Kamb 34
-          ids: [83]
+          ids: [78]
         # - lakename: Kamb 5
         #   ids: [75]
         - lakename: Kamb 6
-          ids: [79]
+          ids: [74]
         # - lakename: Kamb 7
         #   ids: [67]
         - lakename: Kamb 8
-          ids: [80]
+          ids: [75]
         - lakename: Kamb 10
-          ids: [82]
+          ids: [77]
         - lakename: MacAyeal 1
-          ids: [162]
+          ids: [151]
         # - lakename: MacAyeal 4
         #   ids: [121]
         - lakename: Subglacial Lake Mercer
-          ids: [31, 36]
+          ids: [27, 32]
         # - lakename: Recovery 2
         #   ids: [187, 188]
         - lakename: Recovery IV
-          ids: [211]
+          ids: [195]
         - lakename: Slessor 23
-          ids: [175]
+          ids: [162]
         - lakename: Slessor 45
-          ids: [144]
+          ids: [164]
         - lakename: Subglacial Lake Conway
-          ids: [63, 64]
+          ids: [58, 59]
         - lakename: Subglacial Lake Whillans
-          ids: [70, 71]
+          ids: [65, 66]
           transect: 0989_pt1
         # - lakename: Whillans 6
         #   ids: [46]
         - lakename: Whillans 7
-          ids: [60]
+          ids: [55]
           transect: 0531_pt1
         - lakename: Whillans IX
-          ids: [62]
+          ids: [57]
           transect: 1080_pt3
         # - lakename: Whillans X
         #   ids: [51]
         - lakename: Whillans XI
-          ids: [74, 75]
+          ids: [69, 70]
         - lakename: Subglacial Lake Engelhardt
-          ids: [69]
+          ids: [64]
         # - lakename: Lake 78
         #   ids: [23]
         - lakename: Lake 12
-          ids: [72]
+          ids: [67]
           transect: 0593_pt1
         - lakename: \* 1
-          ids: [66]
+          ids: [60]
         - lakename: \* 2
-          ids: [67]
+          ids: [61]
         - lakename: \* 3
-          ids: [77]
+          ids: [72]
         - lakename: \* 4
-          ids: [97, 98, 110]
+          ids: [92, 93]
         # - lakename: \* 5
         #   ids: [97]
         - lakename: \* 6
-          ids: [200, 203]
+          ids: [186, 189]
   test_data:
     description: 'Sample ICESat-2 datasets for testing purposes'
     args:

atlxi_lake.ipynb

@@ -60,7 +60,9 @@ def find_clusters(
         from sklearn.cluster import DBSCAN
 
     # Run DBSCAN using {eps} m distance, and minimum of {min_samples} points
-    dbscan = DBSCAN(eps=eps, min_samples=min_samples, **kwargs)
+    dbscan = DBSCAN(
+        eps=eps, min_samples=min_samples, calc_core_sample_indices=False, **kwargs
+    )
     dbscan.fit(X=X)
 
     cluster_labels = dbscan.labels_ + 1  # noise points -1 becomes 0