Initial files to cmorise EN4 data

.zenodo.json

@@ -452,6 +452,10 @@
       "affiliation": "ACCESS-NRI, Australia",
       "name": "Chun, Felicity",
       "orcid": "0009-0007-0845-0953"
+    },
+    {
+      "affiliation": "Met Office, UK",
+      "name": "Ellis, Hannah"
     }
   ],
   "description": "ESMValTool: A community diagnostic and performance metrics tool for routine evaluation of Earth system models in CMIP.",

CITATION.cff

@@ -448,6 +448,11 @@ authors:
     family-names: Chun
     given-names: Felicity
     orcid: "https://orcid.org/0009-0007-0845-0953"
+  -
+    affiliation: "Met Office, UK"
+    family-names: Ellis
+    given-names: Hannah
+
 
 cff-version: 1.2.0
 date-released: 2025-09-04

doc/sphinx/source/input.rst

@@ -296,6 +296,8 @@ A list of the datasets for which a CMORizers is available is provided in the fol
 +----------------------------------------+------------------------------------------------------------------------------------------------------+------+-----------------+
 | Duveiller2018                          | albDiffiTr13                                                                                         |   2  | Python          |
 +----------------------------------------+------------------------------------------------------------------------------------------------------+------+-----------------+
+| EN4                                    | tos, thetao, sos, so (Omon)                                                                          |   2  | Python          |
++----------------------------------------+------------------------------------------------------------------------------------------------------+------+-----------------+
 | E-OBS                                  | tas, tasmin, tasmax, pr, psl (day, Amon)                                                             |   2  | Python          |
 +----------------------------------------+------------------------------------------------------------------------------------------------------+------+-----------------+
 | Eppley-VGPM-MODIS                      | intpp (Omon)                                                                                         |   2  | Python          |

esmvaltool/cmorizers/data/cmor_config/EN4.yml

@@ -0,0 +1,26 @@
+---
+
+# Filename
+filename: 'EN.4.2.2.f.analysis.g10.*.nc'
+
+# Common global attributes for Cmorizer output
+attributes:
+  dataset_id: EN4
+  version: '4.2.2'
+  tier: 2
+  modeling_realm: reanaly
+  project_id: OBS6
+  source: 'https://www.metoffice.gov.uk/hadobs/en4/download-en4-2-2.html'
+  reference: 'good2013jgr'
+  comment: 'Uses analyses with Gouretski and Reseghetti (2010) XBT corrections and Gouretski and Cheng (2020) MBT corrections applied.'
+
+# Variables to cmorize
+variables:
+  thetao:
+    mip: Omon
+    raw_var: sea_water_potential_temperature
+    srf_var: tos
+  so:
+    mip: Omon
+    raw_var: sea_water_salinity
+    srf_var: sos

esmvaltool/cmorizers/data/datasets.yml

@@ -332,6 +332,20 @@ datasets:
       - Complete the CMOR-config specifications (see instructions in the file
         itself)
 
+  EN4:
+    tier: 2
+    source: "https://www.metoffice.gov.uk/hadobs/en4/download-en4-2-2.html"
+    last_access: 2025-06-13
+    info: |
+      EN4: quality controlled subsurface ocean temperature and salinity objective analyses.
+      Script tested using analyses with Gouretski and Reseghetti (2010) XBT corrections
+      and Gouretski and Cheng (2020) MBT corrections applied.
+      To download data:
+        - Edit the text file for your chosen years, https://www.metoffice.gov.uk/hadobs/en4/EN.4.2.2.analyses.g10.download-list.txt
+        - Save .txt file in directory for data to be downloaded to.
+        - Run 'wget -i EN.4.2.2.profiles.g10.download-list.txt' in same directory.
+        - Unzip files prior to running the cmorizer script.
+
   E-OBS:
     tier: 2
     source: http://surfobs.climate.copernicus.eu/dataaccess/access_eobs.php#datafiles

esmvaltool/cmorizers/data/formatters/datasets/en4.py

@@ -0,0 +1,128 @@
+"""
+CMORizer for EN4 dataset.
+
+This script processes EN4 ocean temperature and salinity data to CMOR-compliant format for use in ESMValTool.
+
+Tier
+    Tier 2: other freely-available dataset.
+
+Source
+    https://www.metoffice.gov.uk/hadobs/en4/download-en4-2-2.html
+
+Last access
+    2025-06-13
+
+Info
+    EN4: quality controlled subsurface ocean temperature and salinity objective analyses.
+    Script tested using analyses with Gouretski and Reseghetti (2010) XBT corrections
+    and Gouretski and Cheng (2020) MBT corrections applied.
+
+Download instructions
+    - Edit the text file for your chosen years, https://www.metoffice.gov.uk/hadobs/en4/EN.4.2.2.analyses.g10.download-list.txt
+    - Save .txt file in directory for data to be downloaded to.
+    - Run 'wget -i EN.4.2.2.profiles.g10.download-list.txt' in same directory.
+    - Unzip files prior to running the cmorizer script.
+
+"""
+
+import logging
+from pathlib import Path
+
+import iris
+
+from esmvaltool.cmorizers.data import utilities as utils
+
+logger = logging.getLogger(__name__)
+
+
+def load_and_prepare_cube(fullpath, var, var_info, glob_attrs, cmor_table):
+    """
+    Load and prepare a data cube for CMORization. Fix attributes, coordinates, and units.
+
+    Parameters
+    ----------
+    fullpath : str
+        Path to the input file.
+    var : str
+        Name of the variable to save in output cube.
+    var_info : dict
+        Variable information dictionary.
+    glob_attrs : dict
+        Global attributes to set on the cube.
+    cmor_table : object
+        CMOR table.
+
+    Returns
+    -------
+    iris.cube.Cube
+        The prepared data cube.
+    """
+
+    glob_attrs["mip"] = var_info["mip"]
+    raw_var = var_info["raw_var"]
+    cmor_info = cmor_table.get_variable(var_info["mip"], var)
+
+    cubes = iris.load(fullpath, raw_var)
+    iris.util.equalise_attributes(cubes)
+    cube = cubes.concatenate_cube()
+
+    if cube.units == "K":
+        cube.convert_units("degC")
+
+    cube.coord("depth").units = "m"
+    cube = utils.fix_coords(cube)
+    utils.fix_var_metadata(cube, cmor_info)
+    utils.set_global_atts(cube, glob_attrs)
+
+    return cube
+
+
+def extract_surface_var(cube, cmor_info):
+    """
+    Extract the surface level variable from a data cube.
+
+    Parameters
+    ----------
+    cube : iris.cube.Cube
+        Input data cube.
+    cmor_info : object
+        CMOR table object for the surface variable.
+
+    Returns
+    -------
+    iris.cube.Cube
+        The extracted surface level cube.
+    """
+    logger.info("Extracting surface level")
+
+    depth0 = iris.Constraint(depth=cube.coord("depth").points[0])
+    surface_cube = cube.extract(depth0)
+
+    utils.fix_var_metadata(surface_cube, cmor_info)
+
+    return surface_cube
+
+
+def cmorization(in_dir, out_dir, cfg, cfg_user, start_date, end_date):
+    """
+    CMORization main function call.
+    """
+    cmor_table = cfg["cmor_table"]
+    glob_attrs = cfg["attributes"]
+    fullpath = str(Path(in_dir) / cfg["filename"])
+
+    for var, var_info in cfg["variables"].items():
+        logger.info("Loading %s", fullpath)
+
+        srf_var = var_info["srf_var"]
+        cmor_info_srf = cmor_table.get_variable(var_info["mip"], srf_var)
+
+        cube = load_and_prepare_cube(
+            fullpath, var, var_info, glob_attrs, cmor_table
+        )
+        surface_cube = extract_surface_var(cube, cmor_info_srf)
+        logger.info("Saving for %s", var)
+        utils.save_variable(cube, var, out_dir, glob_attrs)
+
+        logger.info("Saving for %s", srf_var)
+        utils.save_variable(surface_cube, srf_var, out_dir, glob_attrs)

esmvaltool/recipes/examples/recipe_check_obs.yml

@@ -3,7 +3,7 @@
 ---
 documentation:
   description: |
-    Test recipe for OBS, no proprocessor or diagnostics are applied,
+    Test recipe for OBS, no preprocessor or diagnostics are applied,
     just to check correct reading of the CMORized data.
 
   title: Recipe to test run all obs cmorizers.
@@ -154,6 +154,17 @@ diagnostics:
          type: clim, version: v2018, start_year: 2010, end_year: 2010}
     scripts: null
 
+  EN4:
+    description: EN4 check
+    variables:
+      thetao:
+      tos:
+      so:
+      sos:
+    additional_datasets:
+      - {dataset: EN4, project: OBS6, mip: Omon, type: reanaly,
+         version: 4.2.2, tier: 2, start_year: 1900, end_year: 2024}
+    scripts: null
 
   E-OBS:
     description: E-OBS check

esmvaltool/references/good2013jgr.bibtex

@@ -0,0 +1,12 @@
+@article{Good2013EN4:Estimates,
+    title = {{EN4: Quality controlled ocean temperature and salinity profiles and monthly objective analyses with uncertainty estimates}},
+    year = {2013},
+    journal = {Journal of Geophysical Research: Oceans},
+    author = {Good, Simon A. and Martin, Matthew J. and Rayner, Nick A.},
+    number = {12},
+    pages = {6704--6716},
+    volume = {118},
+    publisher = {Blackwell Publishing Ltd},
+    doi = {10.1002/2013JC009067},
+    issn = {21699291},
+    keywords = {objective analysis, ocean observations, quality control, uncertainty estimation}