Cmorize cru v4.04 & stn contraint

esmvaltool/cmorizers/obs/cmor_config/CRU.yml

@@ -1,25 +1,37 @@
 ---
 # Filename (will be extended by variable name)
-filename: 'cru_ts4.02.1901.2017.{raw_name}.dat.nc.gz'
+filename: 'cru_ts4.04.1901.2019.{raw_name}.dat.nc.gz'
 
 # Common global attributes for Cmorizer output
 attributes:
   dataset_id: CRU
-  version: 'TS4.02'
+  version: 'TS4.04'
   tier: 2
   modeling_realm: reanaly
   project_id: OBS
-  source: 'https://crudata.uea.ac.uk/cru/data/hrg/cru_ts_4.02/cruts.1811131722.v4.02/'
+  source: 'https://crudata.uea.ac.uk/cru/data/hrg/cru_ts_4.04/cruts.2004151855.v4.04/'
   reference: 'cru'
   comment: ''
 
+attributes_constraint:
+  dataset_id: CRU
+  version: 'TS4.04-stn1'
+  tier: 2
+  modeling_realm: reanaly
+  project_id: OBS
+  source: 'https://crudata.uea.ac.uk/cru/data/hrg/cru_ts_4.04/cruts.2004151855.v4.04/'
+  reference: 'cru'
+  comment: 'contrained on gridpoint values beeing based on at least 1 station'
+
 # Variables to cmorize
 variables:
   tas:
     mip: Amon
     raw: tmp
     raw_units: celsius
+    constraint: stn
   pr:
     mip: Amon
     raw: pre
     raw_units: kg m-2 month-1
+    constraint: stn

esmvaltool/cmorizers/obs/cmorize_obs_cru.py

@@ -4,22 +4,30 @@
     Tier 2: other freely-available dataset.
 
 Source
-    https://crudata.uea.ac.uk/cru/data/hrg/cru_ts_4.02/cruts.1811131722.v4.02/
+    https://crudata.uea.ac.uk/cru/data/hrg/cru_ts_4.04/cruts.2004151855.v4.04/
 
 Last access
-    20190516
+    20210113
 
 Download and processing instructions
     Download the following files:
-        {raw_name}/cru_ts4.02.1901.2017.{raw_name}.dat.nc.gz
+        {raw_name}/cru_ts4.04.1901.2019.{raw_name}.dat.nc.gz
     where {raw_name} is the name of the desired variable(s).
 
+Two files are generated per variable, one with version (i.e. TS4.04),
+one with version + -stn1 (i.e. TS4.04-stn1), which is constrained on holding
+gridpoint values relying on data from at least one station (i.e. removing
+gridpoints solely relying on climatological infilling).
 """
 
 import gzip
 import logging
 import os
 import shutil
+import cftime
+
+import numpy as np
+from cf_units import Unit
 
 import iris
 
@@ -45,13 +53,18 @@ def _extract_variable(short_name, var, cfg, filepath, out_dir):
         cube.units = var['raw_units']
     cmor_info = cfg['cmor_table'].get_variable(var['mip'], short_name)
     cube.convert_units(cmor_info.units)
-    utils.convert_timeunits(cube, 1950)
+    # fix time units
+    cube.coord('time').convert_units(
+        Unit('days since 1950-1-1 00:00:00', calendar='gregorian'))
 
     # Fix coordinates
     utils.fix_coords(cube)
     if 'height2m' in cmor_info.dimensions:
         utils.add_height2m(cube)
 
+    # Fix time coordinate
+    _get_centered_timecoord(cube)
+
     # Fix metadata
     attrs = cfg['attributes']
     attrs['mip'] = var['mip']
@@ -65,6 +78,48 @@ def _extract_variable(short_name, var, cfg, filepath, out_dir):
                         attrs,
                         unlimited_dimensions=['time'])
 
+    # build contrainted cube on stn < 1
+    constraint_var = var.get('constraint', short_name)
+    constr_cube = iris.load_cube(filepath,
+                                 utils.var_name_constraint(constraint_var))
+    utils.fix_coords(constr_cube)
+    cube.data = np.ma.masked_where(constr_cube.data < 1., cube.data)
+
+    # Save variable
+    attrs = cfg['attributes_constraint']
+    attrs['mip'] = var['mip']
+
+    utils.save_variable(cube,
+                        short_name,
+                        out_dir,
+                        attrs,
+                        unlimited_dimensions=['time'])
+
+
+def _get_centered_timecoord(cube):
+    """CRU timepoints are not in the center of the month.
+
+    Added bounds by utils.fix_coords are incorrect.
+    """
+    time = cube.coord('time')
+    times = time.units.num2date(time.points)
+
+    # get bounds
+    starts = [
+        cftime.DatetimeNoLeap(c.year, c.month, 1)
+        for c in times
+    ]
+    ends = [
+        cftime.DatetimeNoLeap(c.year, c.month + 1, 1) if c.month < 12
+        else cftime.DatetimeNoLeap(c.year + 1, 1, 1)
+        for c in times
+    ]
+
+    time.bounds = time.units.date2num(np.stack([starts, ends], -1))
+
+    # get points
+    time.points = [np.mean((t1, t2)) for t1, t2 in time.bounds]
+
 
 def _unzip(short_name, var, raw_filepath, out_dir):
     """Unzip `*.gz` file."""

esmvaltool/recipes/examples/recipe_check_obs.yml

@@ -57,7 +57,9 @@ diagnostics:
       pr:
     additional_datasets:
       - {dataset: CRU, project: OBS, mip: Amon, tier: 2,
-         type: reanaly, version: TS4.02, start_year: 1901, end_year: 2017}
+         type: reanaly, version: TS4.04, start_year: 1901, end_year: 2019}
+      - {dataset: CRU, project: OBS, mip: Amon, tier: 2,
+         type: reanaly, version: TS4.04-stn1, start_year: 1901, end_year: 2019}
     scripts: null
 
 

esmvaltool/references/cru.bibtex

@@ -1,13 +1,13 @@
 @article{cru,
-	doi = {10.1002/joc.3711},
-	url = {https://doi.org/10.1002%2Fjoc.3711},
-	year = 2013,
-	month = {may},
-	publisher = {Wiley},
-	volume = {34},
-	number = {3},
-	pages = {623--642},
-	author = {I. Harris and P.D. Jones and T.J. Osborn and D.H. Lister},
-	title = {Updated high-resolution grids of monthly climatic observations - the {CRU} {TS}3.10 Dataset},
-	journal = {International Journal of Climatology}
+	doi = {10.1038/s41597-020-0453-3},
+	issn = {2052-4463},
+	url = {http://www.nature.com/articles/s41597-020-0453-3},
+	year = 2020,
+	author = {Harris, Ian and Osborn, Timothy J. and Jones, Phil and Lister, David},
+	title = {Version 4 of the CRU TS monthly high-resolution gridded multivariate climate dataset},
+	journal = {Scientific Data},
+	month = {dec},
+	number = {1},
+	pages = {109},
+	volume = {7}
 }