HRRR grib read and memory leak fix

CHANGELOG.md

@@ -15,6 +15,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - Removed AIFS-ENS invariants from model input / outputs and moved into model wrapper
 - CDS and NCAR lexica have been updated with variables for AIFS-ENS
+- Switch grib reads in HRRR data sources from xarray to pygrib to fix memory leak
 
 ### Deprecated
 
@@ -28,6 +29,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Dependencies
 
+- Added pygrib to data dependency group
+
 ## [0.11.0] - 2025-12-19
 
 ### Added

earth2studio/data/hrrr.py

@@ -48,10 +48,12 @@
 from earth2studio.utils.type import LeadTimeArray, TimeArray, VariableArray
 
 try:
+    import pygrib
     import pyproj
 except ImportError:
     OptionalDependencyFailure("data")
     pyproj = None
+    pygrib = None
 
 logger.remove()
 logger.add(lambda msg: tqdm.write(msg, end=""), colorize=True)
@@ -510,11 +512,17 @@ async def fetch_array(
             byte_offset=byte_offset,
             byte_length=byte_length,
         )
-        # Open into xarray data-array
-        da = xr.open_dataarray(
-            grib_file, engine="cfgrib", backend_kwargs={"indexpath": ""}
-        )
-        return modifier(da.values)
+        # Load with pygrib, xarray with cfgrib is 10x slower and leaks memory
+        try:
+            grbs = pygrib.open(grib_file)
+            values = modifier(grbs[1].values)
+        except Exception as e:
+            logger.error(f"Failed to read grib file {grib_file}")
+            raise e
+        finally:
+            grbs.close()
+
+        return values
 
     def _validate_time(self, times: list[datetime]) -> None:
         """Verify if date time is valid for HRRR based on offline knowledge

pyproject.toml

@@ -63,6 +63,7 @@ data = [
     "intake-esgf>=2025.9.26",
     "planetary-computer>=0.5.0",
     "globus-sdk<4.0.0", # TODO: Remove once intake-esgf updates
+    "pygrib",
     "pystac-client>=0.9.0",
     "httpx==0.28.1",
     "rasterio>=1.3.9",