[WIP] Add daymet

recipes/daymet/meta.yaml

@@ -0,0 +1,25 @@
+title: Daymet
+description: >
+  Daily Surface Weather and Climatological Summaries (Daymet) provides
+  long-term, continuous, gridded estimates of daily weather and climatology
+  variables by interpolating and extrapolating ground-based observations through
+  statistical modeling techniques. The Daymet data products provide driver data
+  for biogeochemical terrestrial modeling and have myriad applications in many
+  Earth science, natural resource, biodiversity, and agricultural research
+  areas. Daymet weather variables include daily minimum and maximum temperature,
+  precipitation, vapor pressure, shortwave radiation, snow water equivalent, and
+  day length produced on a 1 km x 1 km gridded surface over continental North
+  America and Hawaii from 1980 and over Puerto Rico from 1950 through the end of
+  the most recent full calendar year.
+pangeo_forge_version: '0.9.0'
+pangeo_notebook_version: '2022.06.02'
+recipes:
+  dict_object: recipe:recipes
+provenance:
+  license: 'No constraints on data access or use.'
+maintainers:
+- name: 'Charles Stern'
+  orcid: '0000-0002-4078-0852'
+  github: cisaacstern
+bakery:
+  id: 'pangeo-ldeo-nsf-earthcube'

recipes/daymet/recipe.py

@@ -0,0 +1,51 @@
+from pangeo_forge_recipes.patterns import pattern_from_file_sequence
+from pangeo_forge_recipes.recipes import XarrayZarrRecipe
+from pangeo_forge_cmr import get_cmr_granule_links
+
+from pangeo_forge_recipes import patterns
+import aiohttp
+import netrc
+
+# We need to provide EarthData credentials to fetch the files.
+# The credentials of the currently logged in user are used, and passed on to the cloud
+# as well when the operation is scaled out. This shall be automated with a machine identity
+# in the future.
+# go here to set up .netrc file: https://disc.gsfc.nasa.gov/data-access
+username, _, password = netrc.netrc().authenticators('urs.earthdata.nasa.gov')
+client_kwargs = {
+    'auth': aiohttp.BasicAuth(username, password),
+    'trust_env': True,
+}
+
+# Get the GPM IMERG Late Precipitation Daily data
+shortname = 'Daymet_Daily_V4_1840'
+
+all_files = get_cmr_granule_links(shortname)
+
+var_files = {}
+
+for f in all_files:
+    region, var, year = f.rsplit("/", 1)[1].rsplit(".", 1)[0].rsplit("_", 3)[1:]
+    var_files.setdefault(var, []).append(f)
+
+
+print(var_files)
+
+recipes = {}
+
+
+for var in var_files:
+    # Use '-' not '_' to be valid dataflow name
+    recipes[var] =  XarrayZarrRecipe(
+        pattern_from_file_sequence(
+            var_files[var],
+            # FIXME: Leap years?!
+            concat_dim='time',
+            nitems_per_file=365,
+            fsspec_open_kwargs=dict(
+                client_kwargs=client_kwargs
+            ),
+        ),
+        inputs_per_chunk=1,
+    )
+