atmosphere.yaml

---
plugins:
  source:
    - module: intake_xarray

sources:
  HadCRUT4:
    description: >-
      Combined land [CRUTEM4] and marine [SST anomalies from HadSST3] temperature
      anomalies on a 5° by 5° grid (Morice et al., 2012)
      Recommended to use HadCRUT5.
    metadata:
      url: https://crudata.uea.ac.uk/cru/data/temperature/
      doi: http://doi.org/10.1029/2011JD017187
    driver: netcdf
    args:
      urlpath: simplecache::https://crudata.uea.ac.uk/cru/data/temperature/HadCRUT.4.6.0.0.median.nc
      chunks: {}
      xarray_kwargs:
        engine: h5netcdf

  HadCRUT5:
    description: >-
      Combined land [CRUTEM5] and marine [HadSST4] temperature anomalies on a 5° by 5°
      grid with greater geographical coverage via statistical infilling (Morice et al.,
      2020)
    metadata:
      url: https://www.metoffice.gov.uk/hadobs/hadcrut5/
      doi: http://doi.org/10.1029/2019JD032361
    driver: netcdf
    args:
      urlpath: simplecache::https://crudata.uea.ac.uk/cru/data/temperature/HadCRUT.5.0.0.0.analysis.anomalies.ensemble_mean.nc
      chunks: {}
      xarray_kwargs:
        engine: h5netcdf


  HadCRUT5_Non-Infilled:
    description: >-
      Combined land CRUTEM5 and marine HadSST4 temperature anomalies on a 5° by 5°
      grid with geographical coverage limited to grid cells close to where we have
      measurements (Morice et al., 2020)
    metadata:
      url: https://www.metoffice.gov.uk/hadobs/hadcrut5/
      doi: http://doi.org/10.1029/2019JD032361
    driver: netcdf
    args:
      urlpath: simplecache::https://crudata.uea.ac.uk/cru/data/temperature/HadCRUT.5.0.0.0.anomalies.ensemble_mean.nc
      chunks: {}
      xarray_kwargs:
        engine: h5netcdf

  GISTEMP:
    description: GISS Surface Temperature Analysis (GISTEMP v4)
    metadata:
      url: https://data.giss.nasa.gov/gistemp/
      doi: http://doi.org/10.1029/2018JD029522
    driver: netcdf
    parameters:
      s_res:
        description: spatial resolution
        type: str
        default: 1200km
        allowed:
          - 1200km
          - 250km
      realm:
        description: data region including or excluding ocean
        type: str
        default: combined
        allowed:
          - landonly
          - combined
      t_res:
        description: time span
        type: str
        default: anom
        allowed:
          - anom
          - ltm  # long-term mean
    args:
      urlpath: simplecache::https://psl.noaa.gov/thredds/fileServer/Datasets/gistemp/{{realm}}/{{s_res}}/air.2x2.{{s_res[:-2]}}.mon.{{t_res}}.{{realm[:4]}}.nc
      chunks: {}

  NOAA_GlobalTemp:
    description: >-
      Monthly gridded anomalies of air temperature from the GHCN-M and the NOAA ERSST
      V4 dataset.
    metadata:
      url: https://www.ncdc.noaa.gov/monitoring-references/faq/anomalies.php
      doi:
        - http://doi.org/10.1175/2007JCLI2100.1
        - http://doi.org/10.1175/BAMS-D-11-00241.1.
    driver: netcdf
    args:
      urlpath: simplecache::https://psl.noaa.gov/thredds/fileServer/Datasets/noaaglobaltemp/air.mon.anom.nc
      chunks: {}

  BerkeleyEarth_land:
    description: Monthly gridded land temperature by BerkeleyEarth
    metadata:
      url: http://berkeleyearth.org/archive/data/
    driver: netcdf
    parameters:
      var:
        description: name of variable
        type: str
        default: TAVG
        allowed:
          - TAVG
          - TMAX
          - TMIN
      s_res:
        description: >-
          spatial resolution; either in 15984 equal-area grid cells or a latitude-
          longitude grid. The equal area grid is the primary data format used in most
          of our analyses and provides generally smaller files; however, that format
          may be less convenient for many users.
        type: str
        default: LatLong1
        allowed:
          - LatLong1
          - EqualArea
    args:
      urlpath: simplecache::https://berkeley-earth-temperature.s3.us-west-1.amazonaws.com/Global/Gridded/Complete_{{var}}_{{s_res}}.nc
      chunks: {}

  BerkeleyEarth_land_and_ocean:
    description: Monthly gridded land and ocean temperature by BerkeleyEarth
    metadata:
      url: http://berkeleyearth.org/archive/data/
    driver: netcdf
    parameters:
      s_res:
        description: >-
          spatial resolution; either in 15984 equal-area grid cells or a latitude-
          longitude grid. The equal area grid is the primary data format used in most
          of our analyses and provides generally smaller files; however, that format
          may be less convenient for many users.
        type: str
        default: LatLong1
        allowed:
          - LatLong1
          - EqualArea
    args:
      urlpath: simplecache::https://berkeley-earth-temperature.s3.us-west-1.amazonaws.com/Global/Gridded/Land_and_Ocean_{{s_res}}.nc
      chunks: {}

  Cowtan_and_Way_Long:
    description: >-
      Monthly gridded land and ocean temperature anomalies by Cowtan and Way.
      1850-present, infilled by kriging. The version 2.0 series are based on a more
      rigorous treatment in which the land and ocean data are reconstructed separately
      and then blended. Version 2.0 data are also based on the full HadCRUT4 ensemble,
      and include ensemble as well as coverage uncertainty estimates. The data are
      described in this update. The land temperature reconstruction is used for air
      temperatures over land and sea ice, and the sea surface temperature
      reconstruction for open sea. Sea ice coverage is fixed for each month of the
      year, and is determined from HadISST using the period 1981-2010. For the long
      reconstruction (i.e. 1850-present) the median ice coverage in the given month of
      the year is used for each cell. Hybrid data use the hybrid approach for air
      temperatures over land or sea ice, and kriging for sea surface temperatures.
    metadata:
      url: https://www-users.york.ac.uk/~kdc3/papers/coverage2013/series.html
      doi: https://doi.org/10.1002/qj.2297
    driver: netcdf
    parameters:
      datasets:
        description: base datasets used
        type: str
        default: had4
        allowed:
          - had4
          - had4sst4
          - cobe2cru
    args:
      urlpath: simplecache::https://www-users.york.ac.uk/~kdc3/papers/coverage2013/{{datasets}}_krig_v2_0_0.nc.gz
      chunks: {}
      storage_options:
        simplecache:
          same_names: true
      xarray_kwargs:
        engine: scipy

  trace_gases_at_stations:
    description: >-
      surface insitu measurements of Carbon Cycle Greenhouse Gases (CCGG), National
      Oceanic and Atmospheric Administration (NOAA), Earth System Research Laboratories
      (ESRL), Global Monitoring Laboratory (GML), defaults to Mauna Loa monthly CO2
      measurements
    metadata:
      url: https://www.esrl.noaa.gov/gmd/ccgg/
      doi: add
      readme: ftp://aftp.cmdl.noaa.gov/data/trace_gases/{{variable}}/in-situ/surface/
    driver: netcdf
    parameters:
      freq:
        description: frequency of the measurements
        type: str
        default: Monthly
        allowed:
          - Hourly
          - Daily
          - Monthly
      station:
        description: location of the measurements
        type: str
        default: mlo
        allowed:
          - mlo  # Mauna LOa
          - brw  # BarRow
          - smo  # American SaMOa
          - spo  # South POle
      variable:
        description: variable
        type: str
        default: co2
        allowed:
          - co2
          - ch4
    args:
      urlpath: ftp://aftp.cmdl.noaa.gov/data/trace_gases/{{variable}}/in-situ/surface/{{station}}/{{variable}}_{{station}}_surface-insitu_1_ccgg_{{freq}}Data.nc
      storage_options:
        simplecache:
          same_names: true
      xarray_kwargs:
        engine: h5netcdf


  NCEP_monthly:
    description: NCEP reanalysis derived monthly
    metadata:
      url: https://psl.noaa.gov/data/reanalysis/reanalysis.shtml
      doi: https://doi.org/10.1175/1520-0477(1996)077<0437:TNYRP>2.0.CO;2
    driver: netcdf
    parameters:
      freq:
        description: frequency
        type: str
        default: mon
        allowed:
          - mon
          - day
          - 4Xday
      time_average:
        description: time_average
        type: str
        default: mean
        allowed:
          - mean
          - ltm
          - 1981-2010.ltm
      var:
        description: variable
        type: str
        default: air
        allowed:
          - air
          - air.sig995
          - lftx
          - pr_wtr.eatm
          - pr_wtr
          - omega.sig995
          - pottmp.sig995
          - pr_wtr.eatm
          - pres
          - rhum
          - rhum.sig995
          - slp
          - uwnd.sig995
          - vwnd.sig995
          - uwnd
          - vwnd
          - wspd
          - wspd.sig995
    args:
      urlpath: simplecache::https://psl.noaa.gov/thredds/fileServer/Datasets/ncep.reanalysis.derived/surface/{{var}}.{{freq}}.{{time_average}}.nc

  NCEP_monthly_gauss:
    description: NCEP reanalysis derived monthly gaussian
    metadata:
      url: https://psl.noaa.gov/data/reanalysis/reanalysis.shtml
      doi: https://doi.org/10.1175/1520-0477(1996)077<0437:TNYRP>2.0.CO;2
    driver: netcdf
    parameters:
      freq:
        description: frequency
        type: str
        default: mon
        allowed:
          - mon
          - day
          - 4Xday
      time_average:
        description: time_average
        type: str
        default: mean
        allowed:
          - mean
          - ltm
          - 1981-2010.ltm
      var:
        description: variable
        type: str
        default: air.2m
        allowed:
          - air.2m
          - cfnlf.sfc
          - cprat.sfc
          - csdlf.sfc
          - csdsf.sfc
          - csusf.sfc
          - dlwrf.sfc
          - dswrf.sfc
          - gflux.sfc
          - icec.sfc
          - lhtfl.sfc
          - nbdsf.sfc
          - nddsf.sfc
          - nlwrf.sfc
          - nswrs.sfc
          - pevpr.sfc
          - prate
          - runof.sfc
          - sfcr.sfc
          - shtfl.sfc
          - shum.2m
          - skt
          - soilw.0-10cm
          - soilw.10-200cm
          - soilw
          - soilw200
          - tmax.2m
          - tmin.2m
          - tmp.0-10cm
          - tmp.10-200cm
          - temp.300cm
          - uflx.sfc
          - ugwd.sfc
          - ulwrf.sfc
          - uswrf.sfc
          - uwnd.10m
          - vwnd.10m
          - vbdsf.sfc
          - vddsf.sfc
          - vflx.sfc
          - vgwd.sfc
          - weasd.sfc
          - wspd
    args:
      urlpath: simplecache::https://psl.noaa.gov/thredds/fileServer/Datasets/ncep.reanalysis.derived/surface_gauss/{{var}}.{{freq}}.{{time_average}}.nc

  fossil_fuel_emissions_gridded:
    description: >-
      daily 1x1 Gridded Fossil Fuel emissions from Open-source Data Inventory for
      Anthropogenic CO2 (ODIAC), Carbon Cycle Greenhouse Gases (CCGG), National Oceanic
      and Atmospheric Administration (NOAA), Earth System Research Laboratories (ESRL),
      Global Monitoring Laboratory (GML)
    metadata:
      url: https://www.odiac.org/index.html
      doi:
        data: 10.17595/20170411.001
        paper:
          - 10.5194/acp-11-543-2011
          - 10.5194/essd-10-87-2018
    driver: netcdf
    parameters:
      date:
        description: distribution of fossil fuel emissions
        type: datetime
        default: 2000.01.01
        min: 2000.01.01
      version:
        description: release, version of the ODIAC emissions
        type: str
        default: 2018
        allowed:
          - 2015a
          - 2016
          - 2017
          - 2018
      variable:
        description: variable
        type: str
        default: co2
        allowed:
          - co2
          - ch4
    args:
      urlpath: ftp://aftp.cmdl.noaa.gov/data/ccgg/ODIAC/{{version}}/distrib/{{date.strftime("%Y")}}/{{date.strftime("%m")}}/fossil_fuel_1x1_{{date.strftime("%Y%m%d")}}.nc
      storage_options:
        simplecache:
          same_names: true
      xarray_kwargs:
        engine: h5netcdf

  NOAA_carbon_tracker:
    description: >-
      CarbonTracker is a CO2 measurement and modeling system developed by NOAA to keep
      track of sources (emissions to the atmosphere) and sinks (removal from the
      atmosphere) of carbon dioxide around the world.
    metadata:
      url: https://www.esrl.noaa.gov/gmd/ccgg/carbontracker
    driver: netcdf
    parameters:
      date:
        description: date of measurements
        type: datetime
        default: 2018.01.01
        min: 2000.01.01
      version:
        description: release, version of the ODIAC emissions
        type: str
        default: CT2019B
        allowed:
          - CT-NRT.v2015-1
          - CT-NRT.v2017-1
          - CT-NRT.v2018-1
          - CT-NRT.v2019-1
          - CT-NRT.v2020-1
          - CT2019B
          - CT2019
          - CT2017
          - CT2016
          - CT2015
      variable:
        description: variable
        type: str
        default: co2
        allowed:
          - co2
          - ch4
    args:
      urlpath: simplecache::ftp://aftp.cmdl.noaa.gov/products/carbontracker/co2/{{version}}/molefractions/co2_total_monthly/{{version}}.molefrac_glb3x2_{{date.strftime("%Y-%m")}}.nc
      storage_options:
        simplecache:
          same_names: true
      xarray_kwargs:
        engine: h5netcdf

  xco2_v4:
    description: >-
      XCO2_OBS4MIPS_2x2 v4 2003-2019 monthly on a 2x2 degree grid for obs4mip
      column-average dry-air mole fraction of atmospheric carbon dioxide
    metadata:
      tag:
        - cmor
        - obs4mip
      readme: https://www.iup.uni-bremen.de/carbon_ghg/data/Satellite_XCO2_OBS4MIPS_v4p2_2x2_4C_TN_v1.pdf
    driver: netcdf
    args:
      urlpath: simplecache::https://www.iup.uni-bremen.de/carbon_ghg/data/xco2_c3s_l3_v42_200301_201912_2x2.nc
      chunks: auto

  pr_GPCP:
    description: >-
      Precipitation NASA-GSFC GPCP V2.3 for obs4mip
    metadata:
      tag:
        - cmor
        - obs4mip
      readme: https://esgf.nccs.nasa.gov/esgdoc/GPCP_precip_SG-V2.3_TechNote_180510.pdf
      id: obs4MIPs.NASA-GSFC.GPCP-V2.3.atmos.mon.v20180519|dpesgf03.nccs.nasa.gov
    driver: netcdf
    args:
      urlpath: simplecache::https://dpesgf03.nccs.nasa.gov/thredds/fileServer/obs4MIPs/observations/NASA-GSFC/Obs-GPCP/GPCP/V2.3/atmos/pr/pr_GPCP-SG_L3_v2.3_197901-201710.nc
      chunks: {}

  pr_TRMM:
    description: >-
      Precipitation NASA-GSFC TRMM for obs4mip
    metadata:
      tag:
        - cmor
        - obs4mip
      readme: https://esgf.nccs.nasa.gov/esgdoc/TMPA_precip_mon_Tech_Note.pdf
      id: obs4MIPs.NASA-GSFC.TRMM.atmos.mon.v20160613|dpesgf03.nccs.nasa.gov
    driver: netcdf
    args:
      urlpath: simplecache::https://dpesgf03.nccs.nasa.gov/thredds/fileServer/obs4MIPs/NASA-GSFC/TRMM/observations/atmos/pr/mon/NASA-GSFC/TRMM/pr_TRMM-L3_v7-7A_199801-201312.nc
      chunks: {}