DAS-2292: add SPL2SMAP collection to the SMAP-L2-Gridder (#13)

.gitignore

@@ -1,3 +1,4 @@
 **/__pycache__
 /.coverage
 /reports/
+/workdir/

CHANGELOG.md

@@ -5,6 +5,14 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [v0.1.0] - 2025-01-21
+
+### Added
+
+- Adds support for SPL2SMAP ([SMAP L2 Radar/Radiometer Half-Orbit 9 km EASE-Grid Soil Moisture](https://nsidc.org/data/spl2smap/versions/3)).
+- Removes `tb_time_utc` variables from SPL2SMP_E output.
+
+
 ## [v0.0.4] - 2024-12-04
 
 ### Changed

README.md

@@ -2,7 +2,7 @@
 
 This repository contains the code for the Harmony-SMAP-L2-Gridding-Service, which is a python service that transforms NASA level 2 gridded trajectory data into gridded NetCDF4-CF output files.
 
-This code currently works on `SPL2SMP_E` data and will be adapted for other SMAP collections of gridded trajectory data.
+This code currently works on `SPL2SMP_E`, and `SPL2SMAP` data and will be adapted for other SMAP collections [`SPL2SMP`,`SPL2SMA`] of gridded trajectory data.
 
 
 ## Transforming Data

docker/service_version.txt

@@ -1 +1 @@
-0.0.4
+0.1.0

harmony_service/adapter.py

@@ -50,9 +50,7 @@ def process_item(self, item: Item, source: HarmonySource) -> Item:
                     asset.href, is_regridded=True, ext='.nc'
                 )
 
-                transform_l2g_input(
-                    input_filepath, working_filename, logger=self.logger
-                )
+                transform_l2g_input(input_filepath, working_filename)
 
                 # Stage the transformed output:
                 staged_url = stage(

pip_requirements.txt

@@ -2,4 +2,4 @@ harmony-service-lib==2.3.0
 netcdf4==1.7.2
 pyproj==3.7.0
 pystac==1.11.0
-xarray==2024.10.0
+xarray==2025.1.1

smap_l2_gridder/collections.py

@@ -0,0 +1,126 @@
+"""Collection information.
+
+Defines hierarchies necessary for gridding collections with the SMAP L2 Gridder.
+
+While the input files are hierarchical and in hdf format, they are not fully
+self describing. Each griddable variable is tied to two variables that contain
+the column and row of a grid into which the value should be placed. But these
+column and row indices are not always in the same location.  Additionally,
+there are a number of different resolution grids and coordinate reference
+systems, that here are identified by a gpd file and epsg code that are
+described in the documentation for the dataset but are hard/impossible to
+determine by looking at the files themselves, for this reason we explictly lay
+out this information in this file along with helper routines to ease access.
+
+"""
+
+from .exceptions import InvalidCollectionError
+
+STANDARD_LOCATIONS = {
+    'row': 'Soil_Moisture_Retrieval_Data/EASE_row_index',
+    'col': 'Soil_Moisture_Retrieval_Data/EASE_column_index',
+}
+
+GRIDS = {
+    'M03km': {'gpd': 'EASE2_M03km.gpd', 'epsg': 'EPSG:6933'},
+    'M09km': {'gpd': 'EASE2_M09km.gpd', 'epsg': 'EPSG:6933'},
+    'M36km': {'gpd': 'EASE2_M36km.gpd', 'epsg': 'EPSG:6933'},
+    'N09km': {'gpd': 'EASE2_N09km.gpd', 'epsg': 'EPSG:6931'},
+}
+
+
+COLLECTION_INFORMATION = {
+    'SPL2SMP_E': {
+        'metadata': ['Metadata'],
+        'data_groups': {
+            'Soil_Moisture_Retrieval_Data': {
+                **STANDARD_LOCATIONS,
+                **GRIDS['M09km'],
+                'dropped_variables': ['tb_time_utc'],
+            },
+            'Soil_Moisture_Retrieval_Data_Polar': {
+                'row': 'Soil_Moisture_Retrieval_Data_Polar/EASE_row_index',
+                'col': 'Soil_Moisture_Retrieval_Data_Polar/EASE_column_index',
+                **GRIDS['N09km'],
+                'dropped_variables': ['tb_time_utc'],
+            },
+        },
+    },
+    'SPL2SMAP': {
+        'metadata': ['Metadata'],
+        'data_groups': {
+            'Soil_Moisture_Retrieval_Data': {
+                **STANDARD_LOCATIONS,
+                **GRIDS['M09km'],
+                'dropped_variables': ['spacecraft_overpass_time_utc'],
+            },
+            'Soil_Moisture_Retrieval_Data_3km': {
+                'row': 'Soil_Moisture_Retrieval_Data_3km/EASE_row_index_3km',
+                'col': 'Soil_Moisture_Retrieval_Data_3km/EASE_column_index_3km',
+                **GRIDS['M03km'],
+                'dropped_variables': ['spacecraft_overpass_time_utc'],
+            },
+        },
+    },
+    'SPL2SMA': {
+        'metadata': ['Metadata'],
+        'data_groups': {
+            'Ancillary_Data': {**STANDARD_LOCATIONS, **GRIDS['M03km']},
+            'Radar_Data': {**STANDARD_LOCATIONS, **GRIDS['M03km']},
+            'Soil_Moisture_Retrieval_Data': {**STANDARD_LOCATIONS, **GRIDS['M03km']},
+        },
+    },
+    'SPL2SMP': {
+        'metadata': ['Metadata'],
+        'data_groups': {
+            'Soil_Moisture_Retrieval_Data': {
+                **STANDARD_LOCATIONS,
+                **GRIDS['M36km'],
+            }
+        },
+    },
+}
+
+
+def get_all_information() -> dict:
+    """Returns all known collection information.
+
+    Mostly exists to mock tests.
+    """
+    return COLLECTION_INFORMATION
+
+
+def get_collection_info(short_name: str) -> dict:
+    """Return the configuration information for the short_name's collection."""
+    try:
+        return get_all_information()[short_name]
+    except KeyError as exc:
+        raise InvalidCollectionError(
+            f'No collection information for {short_name}'
+        ) from exc
+
+
+def get_collection_group_info(short_name: str, group: str) -> dict:
+    """Get basic information for a collection's group.
+
+    Helper function to identify which information was incorrect when attempting
+    to retrieve the desired gridding information
+
+    """
+    collection = get_collection_info(short_name)
+    try:
+        group_info = collection['data_groups'][group]
+    except KeyError as exc:
+        raise InvalidCollectionError(f'No group named {group} in {short_name}') from exc
+
+    return group_info
+
+
+def get_dropped_variables(short_name: str, group: str) -> set[str]:
+    """Return a set of variables to be excluded from the processed file."""
+    try:
+        info = get_collection_group_info(short_name, group)
+        dropped_vars = info['dropped_variables']
+        return set(dropped_vars)
+    except KeyError:
+        return set()

smap_l2_gridder/crs.py

@@ -38,15 +38,6 @@ def col_row_to_xy(self, col: int, row: int) -> tuple[np.float64, np.float64]:
         return x, y
 
 
-# NSIDC EASE-Grid 2.0 Global CRS definition
-# from: https://epsg.org/crs/wkt/id/6933
-EPSG_6933_WKT = CRS.from_epsg(6933).to_wkt()
-
-# NSIDC EASE-Grid 2.0 North CRS definition
-# from: https://epsg.org/crs/wkt/id/6931
-EPSG_6931_WKT = CRS.from_epsg(6931).to_wkt()
-
-
 def geotransform_from_target_info(target_info: dict) -> Geotransform:
     """Return a geotransform from the grid_info dict.
 

smap_l2_gridder/exceptions.py

@@ -11,3 +11,7 @@ def __init__(self, message=None):
 
 class InvalidGPDError(SMAPL2GridderError):
     """Raised if an invalid GPD is used."""
+
+
+class InvalidCollectionError(SMAPL2GridderError):
+    """Raised when attempting operations on invalid collections."""