on-the-fly cmoriser for ACCESS native data

.zenodo.json

@@ -204,6 +204,11 @@
         {
             "affiliation": "DLR, Germany",
             "name": "Cammarano, Diego"
+        },
+        {
+            "affiliation": "ACCESS-NRI, Australia",
+            "name": "Yousong, Zeng",
+            "orcid": "0000-0002-8385-5367"
         }
     ],
     "description": "ESMValCore: A community tool for pre-processing data from Earth system models in CMIP and running analysis scripts.",

CITATION.cff

@@ -209,6 +209,11 @@ authors:
     family-names: Cammarano
     given-names: Diego
 
+    affiliation: "ACCESS-NRI, Australia"
+    family-names: Yousong
+    given-names: Zeng
+    orcid: "https://orcid.org/0000-0002-8385-5367"
+
 cff-version: 1.2.0
 date-released: 2024-05-08
 doi: "10.5281/zenodo.3387139"

doc/quickstart/find_data.rst

@@ -564,6 +564,74 @@ explained in :ref:`extra_facets`, and which content is :download:`available here
 </../esmvalcore/config/extra_facets/ipslcm-mappings.yml>`. These multi-variable
 files must also undergo some data selection.
 
+.. _read_access-esm:
+
+ACCESS-ESM
+^^^^^^^^^^
+
+ESMValTool can read native `ACCESS-ESM <https://research.csiro.au/access/about/esm1-5/>`__
+model output.
+
+.. warning::
+
+  This is the first version of ACCESS-ESM CMORizer for ESMValCore Currently, 
+  only two variables (`tas`, and `pr`) are fully supported.
+
+This is an example of the directory file structure in `config_developer.yml`.
+
+.. code-block:: yaml
+
+  ACCESS:
+    cmor_strict: false
+    input_dir:
+      default:
+        - '{institute}/{sub_dataset}/{exp}/{modeling_realm}/netCDF'
+    input_file:
+      default: '{sub_dataset}.{special_attr}-*.nc'
+    output_file: '{sub_dataset}.{special_attr}'
+    cmor_type: 'CMIP6'
+    cmor_default_table_prefix: 'CMIP6_'
+
+.. hint::
+
+  We only provide one default `input_dir` since this is how ACCESS-ESM native data was 
+  stored on NCI. Users can modify this path to match their local file structure.
+
+
+Thus, example dataset entries could look like this:
+
+.. code-block:: yaml
+
+  dataset:
+    - {project: ACCESS, institute: ACCESS-ESM1-5, mip: Amon, dataset:ACCESS_ESM, sub_dataset: HI-CN-05, 
+      exp: history, modeling_realm: atm, special_attr: pa, start_year: 1986, end_year: 1986}
+
+
+`dataset` and `sub_dataset` are not redundant, `dataset` is for ESMValCore to search for CMORizer,
+which is always `ACCESS_ESM`, `sub_dataset` is dataset under root `ACCESS-ESM1-5`.
+
+`special_attr` is a special attribute in the filename `ACCESS-ESM` raw data, it's related to frquency
+of raw data.
+
+`modeling_realm` is a realm attribute, it include `atm`, `ice` and `oce`.
+
+Similar to any other fix, the ACCESS-ESM fix allows the use of :ref:`extra
+facets<extra_facets>`.
+By default, the file :download:`emac-mappings.yml
+</../esmvalcore/config/extra_facets/access-mappings.yml>` is used for that
+purpose.
+For some variables, extra facets are necessary; otherwise ESMValCore cannot
+read them properly.
+Supported keys for extra facets are:
+
+==================== ====================================== =================================
+Key                  Description                            Default value if not specified
+==================== ====================================== =================================
+``raw_name``         Variable name of the variable in the   CMOR variable name of the
+                     raw input file                         corresponding variable
+``modeling_realm``   Realm attribute include `atm`, `ice`   Default realm of this variable 
+                     and `oce`      
+==================== ====================================== =================================
 
 .. _data-retrieval:
 

esmvalcore/cmor/_fixes/access/access_esm.py

@@ -0,0 +1,61 @@
+"""On-the-fly CMORizer for ACCESS-ESM.
+
+Note
+----
+This is the first version of ACCESS-ESM CMORizer in for ESMValCore
+Currently, only two variables (`tas`,`pr`) is fully supported.
+"""
+import logging
+
+from iris.cube import CubeList
+
+from esmvalcore.cmor._fixes.native_datasets import NativeDatasetFix
+
+logger = logging.getLogger(__name__)
+
+
+class AllVars(NativeDatasetFix):
+    """Fixes for all variables."""
+
+    def fix_coord_system(self, cube):
+        """Delete coord_system to make CubeList able to merge."""
+        for dim in cube.dim_coords:
+            if dim.coord_system is not None:
+                cube.coord(dim.standard_name).coord_system = None
+
+    def fix_height_value(self, cube):
+        """Fix height value to make it comparable to other dataset."""
+        if cube.coord('height').points[0] != 2:
+            cube.coord('height').points = [2]
+
+    def fix_metadata(self, cubes):
+        """Fix metadata.
+
+        Fix name of coordinate(height), long name and variable name of
+        variable(tas).
+
+        Parameters
+        ----------
+        cubes : iris.cube.CubeList
+            Input cubes.
+
+        Returns
+        -------
+        iris.cube.CubeList
+        """
+        cube = self.get_cube(cubes)
+
+        # Fix scalar coordinates
+        self.fix_scalar_coords(cube)
+
+        # Fix metadata of variable
+        self.fix_var_metadata(cube)
+
+        if 'height_0' in [var.var_name for var in cube.coords()]:
+            self.fix_height_metadata(cube)
+            self.fix_height_value(cube)
+
+        # Fix coord system
+        self.fix_coord_system(cube)
+
+        return CubeList([cube])

esmvalcore/config-developer.yml

@@ -194,3 +194,14 @@ CESM:
   output_file: '{project}_{dataset}_{case}_{gcomp}_{scomp}_{type}_{mip}_{short_name}'
   cmor_type: 'CMIP6'
   cmor_default_table_prefix: 'CMIP6_'
+
+ACCESS:
+  cmor_strict: false
+  input_dir:
+    default:
+      - '{institute}/{sub_dataset}/{exp}/{modeling_realm}/netCDF'
+  input_file:
+    default: '{sub_dataset}.{special_attr}-*.nc'
+  output_file: '{sub_dataset}.{special_attr}'
+  cmor_type: 'CMIP6'
+  cmor_default_table_prefix: 'CMIP6_'

esmvalcore/config/extra_facets/access-mappings.yml

@@ -0,0 +1,17 @@
+# Extra facets for native ACCESS model output
+
+# A complete list of supported keys is given in the documentation (see
+# ESMValCore/doc/quickstart/find_data.rst).
+---
+
+ACCESS_ESM:
+
+  '*':
+
+    tas:
+      raw_name: fld_s03i236
+      modeling_realm: atm
+
+    pr:
+      raw_name: fld_s05i216
+      modeling_realm: atm