Add CAMS cmorizer

doc/sphinx/source/input.rst

@@ -248,6 +248,8 @@ A list of the datasets for which a CMORizers is available is provided in the fol
 +------------------------------+------------------------------------------------------------------------------------------------------+------+-----------------+
 | CALIPSO-ICECLOUD             | cli (AMon)                                                                                           |   3  | NCL             |
 +------------------------------+------------------------------------------------------------------------------------------------------+------+-----------------+
+| CAMS                         | nbp (Lmon), fgco2 (Omon)                                                                             |   3  | Python          |
++------------------------------+------------------------------------------------------------------------------------------------------+------+-----------------+
 | CDS-SATELLITE-ALBEDO         | bdalb (Lmon), bhalb (Lmon)                                                                           |   3  | Python          |
 +------------------------------+------------------------------------------------------------------------------------------------------+------+-----------------+
 | CDS-SATELLITE-LAI-FAPAR      | fapar (Lmon), lai (Lmon)                                                                             |   3  | Python          |

esmvaltool/cmorizers/data/cmor_config/CAMS-EAC4.yml

@@ -0,0 +1,48 @@
+---
+# Common global attributes for Cmorizer output
+
+
+# Input
+filename: 'CAMS_EAC4_{variable}_{start_year}{end_year}.grib'
+start_year: 2003
+end_year: 2023
+attributes:
+  dataset_id: CAMS-EAC4
+  version: 'v2024'
+  tier: 3
+  modeling_realm: reanaly
+  project_id: OBS6
+  source: "https://ads.atmosphere.copernicus.eu/datasets/cams-global-reanalysis-eac4-monthly?tab=overview"
+  reference: 'cams-eac4'
+  comment: ''
+
+# Variables to cmorize
+variables:
+  zg:
+    mip: Amon
+    varname: 'geopotential' # divide by g_0 = 9.80665 m/s-2
+    unit: 'm2 s-2' # to m
+  oh:
+    mip: Amon
+    varname: 'hydroxyl_radical'
+    unit: 'kg kg-1' # to mol mol-1
+  ch4:
+    mip: Amon
+    varname: 'methane_chemistry'
+    unit: 'kg kg-1' # to mol mol-1
+  co:
+    mip: Amon
+    varname: 'nitrogen_monoxide'
+    unit: 'kg kg-1' # to mol mol-1
+  o3:
+    mip: Amon
+    varname: 'ozone'
+    unit: 'kg kg-1' # to mol mol-1
+  hus:
+    mip: Amon
+    varname: 'specific humidity'
+    unit: 'kg kg-1' # 1
+  wap:
+    mip: Amon
+    varname: 'vertical velocity'
+    unit: 'Pa s-1'

esmvaltool/cmorizers/data/cmor_config/CAMS.yml

@@ -0,0 +1,40 @@
+---
+# Common global attributes for Cmorizer output
+
+
+# Input
+filename: 'cams73_v20r2_co2_flux_surface_mm_{year}{month}.nc'
+start_year: 1979
+end_year: 2020
+attributes:
+  dataset_id: CAMS
+  version: 'v20r2' #'v20r1'
+  tier: 3
+  modeling_realm: reanaly
+  project_id: OBS6
+  source: "https://ads.atmosphere.copernicus.eu/cdsapp#!/dataset/cams-global-greenhouse-gas-inversion"
+  reference: 'cams'
+  comment: ''
+
+# Variables to cmorize
+variables:
+  nbp:
+    mip: Lmon
+    positive: down
+    varname: 'Posterior land surface upward mass flux of carbon for the whole grid box and the whole month without fossile'
+  fgco2:
+    mip: Omon
+    positive: down
+    varname: 'Posterior ocean surface upward mass flux of carbon for the whole grid box and the whole month without fossile'
+  areacella:
+    mip: fx
+    varname: area
+  areacello:
+    mip: Ofx
+    varname: area
+  sftlf:
+    mip: fx
+    varname: lsf
+  sftof:
+    mip: Ofx
+    varname: lsf

esmvaltool/cmorizers/data/datasets.yml

@@ -18,7 +18,6 @@ datasets:
       across Australia for each observed data variable. This accounts for spatial and temporal gaps in observations.
       Where possible, the gridded analysis techniques provide useful estimates in data-sparse regions
       such as central Australia.
-
       Time coverage: Site-based data are used to provide gridded climate data at the monthly timescale for rainfall (1900+).
       Reference: Evans, A., Jones, D.A., Smalley, R., and Lellyett, S. 2020. An enhanced gridded rainfall analysis scheme
       for Australia. Bureau of Meteorology Research Report. No. 41.
@@ -33,11 +32,11 @@ datasets:
     last_access: 2023-11-21
     info: |
       Data from NCI project requiring an NCI account and access to GADI
-
       ANUClimate 2.0 consists of gridded daily and monthly climate variables across the terrestrial landmass of Australia
       from at least 1970 to the present. Rainfall grids are generated from 1900 to the present. The underpinning spatial
       models have been developed at the Fenner School of Environment and Society of the Australian National University.
 
+
   APHRO-MA:
     tier: 3
     source: "http://aphrodite.st.hirosaki-u.ac.jp/download/"
@@ -110,6 +109,24 @@ datasets:
       6) Follow download instructions in email from EarthData and put all
          files in the same directory
 
+  CAMS:
+    tier: 3
+    source: https://ads.atmosphere.copernicus.eu/datasets/cams-global-greenhouse-gas-inversion?tab=overview
+    last_access: 2024-10-28
+    info: |
+      You will need to make an account with the CDS data store to download the data.
+      Then, select carbon dioxide, surface flux, surface air sample, monthly mean,
+      as well as the version and years you require to download.
+
+  CAMS-EAC4:
+    tier: 3
+    source: https://ads.atmosphere.copernicus.eu/datasets/cams-global-reanalysis-eac4-monthly?tab=overview
+    last_access: 2024-09-30
+    info: |
+      Requires ECMWF account for the Atmosphere Data Store.
+      Select your variables, as well as all pressure levels and download either
+        directly or using an API script.
+
   CDS-SATELLITE-ALBEDO:
     tier: 3
     source: https://cds.climate.copernicus.eu/cdsapp#!/dataset/satellite-albedo?tab=form
@@ -888,7 +905,9 @@ datasets:
 
   MERRA2:
     tier: 3
-    source: https://goldsmr4.gesdisc.eosdis.nasa.gov/data/MERRA2_MONTHLY/ https://goldsmr5.gesdisc.eosdis.nasa.gov/data/MERRA2_MONTHLY/
+    source: |
+      https://goldsmr4.gesdisc.eosdis.nasa.gov/data/MERRA2_MONTHLY/
+      https://goldsmr5.gesdisc.eosdis.nasa.gov/data/MERRA2_MONTHLY/
     last_access: 2022-09-13
     info: |
       Use automatic download. That will download monthly data but with

esmvaltool/cmorizers/data/downloaders/datasets/cams.py

@@ -0,0 +1,56 @@
+"""Script to download CAMS data from the Climate Data Store."""
+
+import datetime
+
+from dateutil import relativedelta
+
+from esmvaltool.cmorizers.data.downloaders.cds import CDSDownloader
+from esmvaltool.cmorizers.data.utilities import unpack_files_in_folder
+
+
+def download_dataset(config, dataset, dataset_info, start_date, end_date,
+                     overwrite):
+    """Download dataset.
+
+    Parameters
+    ----------
+    config : dict
+        ESMValTool's user configuration
+    dataset : str
+        Name of the dataset
+    dataset_info : dict
+         Dataset information from the datasets.yml file
+    start_date : datetime
+        Start of the interval to download
+    end_date : datetime
+        End of the interval to download
+    overwrite : bool
+        Overwrite already downloaded files
+    """
+    if start_date is None:
+        start_date = datetime.datetime(1979, 1, 1)
+    if end_date is None:
+        end_date = datetime.datetime(2020, 12, 1)
+        #end_date = datetime.datetime(2022, 12, 1)
+
+    downloader = CDSDownloader(
+        product_name='cams-global-greenhouse-gas-inversion',
+        request_dictionary={
+            'variable': 'carbon_dioxide',
+            'quantity': 'surface_flux',
+            'input_observations': 'surface',
+            'time_aggregation': 'monthly_mean',
+            'version': 'v20r2' #v22r2
+        },
+        config=config,
+        dataset=dataset,
+        dataset_info=dataset_info,
+        overwrite=overwrite,
+    )
+
+    loop_date = start_date
+    while loop_date <= end_date:
+        downloader.download(loop_date.year, loop_date.month, file_format='zip')
+        loop_date += relativedelta.relativedelta(months=1)
+
+    unpack_files_in_folder(downloader.local_folder)

esmvaltool/cmorizers/data/downloaders/datasets/cams_eac4.py

@@ -0,0 +1,68 @@
+"""Script to download CAMS data from the Climate Data Store."""
+
+import datetime
+
+from esmvaltool.cmorizers.data.downloaders.cds import CDSDownloader
+
+
+def download_dataset(config, dataset, dataset_info, start_date, end_date,
+                     overwrite):
+    """Download dataset.
+
+    Parameters
+    ----------
+    config : dict
+        ESMValTool's user configuration
+    dataset : str
+        Name of the dataset
+    dataset_info : dict
+         Dataset information from the datasets.yml file
+    start_date : datetime
+        Start of the interval to download
+    end_date : datetime
+        End of the interval to download
+    overwrite : bool
+        Overwrite already downloaded files
+    """
+    if start_date is None:
+        start_date = datetime.datetime(2003, 1, 1)
+    if end_date is None:
+        end_date = datetime.datetime(2023, 12, 31)
+    #    #end_date = datetime.datetime(2022, 12, 1)
+
+    variables = [
+        'geopotential', 'hydroxyl_radical', 'methane_chemistry', 'ozone',
+        'specific_humidity', 'vertical_velocity', 'nitrogen_monoxide'
+    ]
+
+    for var in variables:
+
+        downloader = CDSDownloader(
+            product_name='cams-global-reanalysis-eac4-monthly',
+            request_dictionary={
+                'variable': [var],
+                'pressure_level': [
+                    "1", "2", "3", "5", "7", "10", "20", "30", "50", "70",
+                    "100", "150", "200", "250", "300", "400", "500", "600",
+                    "700", "800", "850", "900", "925", "950", "1000"
+                ],
+                "product_type": ["monthly_mean"],
+                "year": [
+                    "2003", "2004", "2005", "2006", "2007", "2008", "2009",
+                    "2010", "2011", "2012", "2013", "2014", "2015", "2016",
+                    "2017", "2018", "2019", "2020", "2021", "2022", "2023"
+                ],
+                "month": [
+                    "01", "02", "03", "04", "05", "06", "07", "08", "09", "10",
+                    "11", "12"
+                ],
+                "data_format":
+                'grib'
+            },
+            config=config,
+            dataset=dataset,
+            dataset_info=dataset_info,
+            overwrite=overwrite,
+        )
+
+        downloader.download_request(f"CAMS_EAC4_{var}_2003_2023.grib")