Lecture 13: Cloud computing¶

Reference: https://github.com/pangeo-gallery/cmip6

Install python packages: zarr, fsspec, gcsfs, nc-time-axis

In [ ]:

from matplotlib import pyplot as plt
import numpy as np
import pandas as pd
import xarray as xr
import zarr
import fsspec

from matplotlib import pyplot as plt import numpy as np import pandas as pd import xarray as xr import zarr import fsspec

Browse Catalog¶

The data catatalog is stored as a CSV file. Here we read it with Pandas.

In [3]:

df = pd.read_csv('https://storage.googleapis.com/cmip6/cmip6-zarr-consolidated-stores.csv')
df.head()

df = pd.read_csv('https://storage.googleapis.com/cmip6/cmip6-zarr-consolidated-stores.csv') df.head()

Out[3]:

	activity_id	institution_id	source_id	experiment_id	member_id	table_id	variable_id	grid_label	zstore	dcpp_init_year	version
0	HighResMIP	CMCC	CMCC-CM2-HR4	highresSST-present	r1i1p1f1	Amon	ps	gn	gs://cmip6/CMIP6/HighResMIP/CMCC/CMCC-CM2-HR4/...	NaN	20170706
1	HighResMIP	CMCC	CMCC-CM2-HR4	highresSST-present	r1i1p1f1	Amon	rsds	gn	gs://cmip6/CMIP6/HighResMIP/CMCC/CMCC-CM2-HR4/...	NaN	20170706
2	HighResMIP	CMCC	CMCC-CM2-HR4	highresSST-present	r1i1p1f1	Amon	rlus	gn	gs://cmip6/CMIP6/HighResMIP/CMCC/CMCC-CM2-HR4/...	NaN	20170706
3	HighResMIP	CMCC	CMCC-CM2-HR4	highresSST-present	r1i1p1f1	Amon	rlds	gn	gs://cmip6/CMIP6/HighResMIP/CMCC/CMCC-CM2-HR4/...	NaN	20170706
4	HighResMIP	CMCC	CMCC-CM2-HR4	highresSST-present	r1i1p1f1	Amon	psl	gn	gs://cmip6/CMIP6/HighResMIP/CMCC/CMCC-CM2-HR4/...	NaN	20170706

In [4]:

df['source_id'].unique()

df['source_id'].unique()

Out[4]:

array(['CMCC-CM2-HR4', 'EC-Earth3P-HR', 'HadGEM3-GC31-MM',
       'HadGEM3-GC31-HM', 'HadGEM3-GC31-LM', 'EC-Earth3P', 'ECMWF-IFS-HR',
       'ECMWF-IFS-LR', 'HadGEM3-GC31-LL', 'CMCC-CM2-VHR4', 'GFDL-CM4',
       'GFDL-AM4', 'IPSL-CM6A-LR', 'E3SM-1-0', 'CNRM-CM6-1', 'GFDL-ESM4',
       'GFDL-ESM2M', 'GFDL-CM4C192', 'GFDL-OM4p5B', 'GISS-E2-1-G',
       'GISS-E2-1-H', 'CNRM-ESM2-1', 'BCC-CSM2-MR', 'BCC-ESM1', 'MIROC6',
       'AWI-CM-1-1-MR', 'EC-Earth3-LR', 'IPSL-CM6A-ATM-HR', 'CESM2',
       'CESM2-WACCM', 'CNRM-CM6-1-HR', 'MRI-ESM2-0', 'CanESM5',
       'SAM0-UNICON', 'GISS-E2-1-G-CC', 'UKESM1-0-LL', 'EC-Earth3',
       'EC-Earth3-Veg', 'FGOALS-f3-L', 'CanESM5-CanOE', 'INM-CM4-8',
       'INM-CM5-0', 'NESM3', 'MPI-ESM-1-2-HAM', 'CAMS-CSM1-0',
       'MPI-ESM1-2-LR', 'MPI-ESM1-2-HR', 'MRI-AGCM3-2-H', 'MRI-AGCM3-2-S',
       'MCM-UA-1-0', 'INM-CM5-H', 'KACE-1-0-G', 'NorESM2-LM',
       'FGOALS-f3-H', 'FGOALS-g3', 'MIROC-ES2L', 'FIO-ESM-2-0', 'NorCPM1',
       'NorESM1-F', 'MPI-ESM1-2-XR', 'CESM1-1-CAM5-CMIP5', 'E3SM-1-1',
       'KIOST-ESM', 'ACCESS-CM2', 'NorESM2-MM', 'ACCESS-ESM1-5',
       'IITM-ESM', 'GISS-E2-2-G', 'CESM2-FV2', 'GISS-E2-2-H',
       'CESM2-WACCM-FV2', 'CIESM', 'E3SM-1-1-ECA', 'TaiESM1',
       'AWI-ESM-1-1-LR', 'EC-Earth3-Veg-LR', 'CMCC-ESM2', 'CAS-ESM2-0',
       'CMCC-CM2-SR5', 'EC-Earth3-AerChem', 'IPSL-CM6A-LR-INCA',
       'IPSL-CM5A2-INCA', 'BCC-CSM2-HR', 'EC-Earth3P-VHR',
       'CESM1-WACCM-SC', 'EC-Earth3-CC', 'MIROC-ES2H', 'ICON-ESM-LR'],
      dtype=object)

In [5]:

df['experiment_id'].unique()

df['experiment_id'].unique()

Out[5]:

array(['highresSST-present', 'piControl', 'control-1950', 'hist-1950',
       'historical', 'amip', 'abrupt-4xCO2', 'abrupt-2xCO2',
       'abrupt-0p5xCO2', '1pctCO2', 'ssp585', 'esm-piControl', 'esm-hist',
       'hist-piAer', 'histSST-1950HC', 'ssp245', 'hist-1950HC', 'histSST',
       'piClim-2xVOC', 'piClim-2xNOx', 'piClim-2xdust', 'piClim-2xss',
       'piClim-histall', 'hist-piNTCF', 'histSST-piNTCF',
       'aqua-control-lwoff', 'piClim-lu', 'histSST-piO3', 'piClim-CH4',
       'piClim-NTCF', 'piClim-NOx', 'piClim-O3', 'piClim-HC',
       'faf-heat-NA0pct', 'ssp370SST-lowCH4', 'piClim-VOC',
       'ssp370-lowNTCF', 'piClim-control', 'piClim-aer', 'hist-aer',
       'faf-heat', 'faf-heat-NA50pct', 'ssp370SST-lowNTCF',
       'ssp370SST-ssp126Lu', 'ssp370SST', 'ssp370pdSST', 'histSST-piAer',
       'piClim-ghg', 'piClim-anthro', 'faf-all', 'hist-nat', 'hist-GHG',
       'ssp119', 'piClim-histnat', 'piClim-4xCO2', 'ssp370',
       'piClim-histghg', 'highresSST-future', 'esm-ssp585-ssp126Lu',
       'ssp126-ssp370Lu', 'ssp370-ssp126Lu', 'land-noLu', 'histSST-piCH4',
       'ssp126', 'esm-pi-CO2pulse', 'amip-hist', 'piClim-histaer',
       'amip-4xCO2', 'faf-water', 'faf-passiveheat', '1pctCO2-rad',
       'faf-stress', '1pctCO2-bgc', 'aqua-control', 'amip-future4K',
       'amip-p4K', 'aqua-p4K', 'amip-lwoff', 'amip-m4K', 'aqua-4xCO2',
       'amip-p4K-lwoff', 'hist-noLu', '1pctCO2-cdr',
       'land-hist-altStartYear', 'land-hist', 'omip1', 'esm-pi-cdr-pulse',
       'esm-ssp585', 'abrupt-solp4p', 'piControl-spinup', 'hist-stratO3',
       'abrupt-solm4p', 'midHolocene', 'lig127k', 'aqua-p4K-lwoff',
       'esm-piControl-spinup', 'ssp245-GHG', 'ssp245-nat',
       'dcppC-amv-neg', 'dcppC-amv-ExTrop-neg', 'dcppC-atl-control',
       'dcppC-amv-pos', 'dcppC-ipv-NexTrop-neg', 'dcppC-ipv-NexTrop-pos',
       'dcppC-atl-pacemaker', 'dcppC-amv-ExTrop-pos',
       'dcppC-amv-Trop-neg', 'dcppC-pac-control', 'dcppC-ipv-pos',
       'dcppC-pac-pacemaker', 'dcppC-ipv-neg', 'dcppC-amv-Trop-pos',
       'piClim-BC', 'piClim-2xfire', 'piClim-SO2', 'piClim-OC',
       'piClim-N2O', 'piClim-2xDMS', 'ssp460', 'ssp434', 'ssp534-over',
       'deforest-globe', 'historical-cmip5', 'hist-bgc',
       'piControl-cmip5', 'rcp26-cmip5', 'rcp45-cmip5', 'rcp85-cmip5',
       'pdSST-piArcSIC', 'pdSST-piAntSIC', 'piSST-piSIC', 'piSST-pdSIC',
       'ssp245-stratO3', 'hist-sol', 'hist-CO2', 'hist-volc',
       'hist-totalO3', 'hist-nat-cmip5', 'hist-aer-cmip5',
       'hist-GHG-cmip5', 'pdSST-futAntSIC', 'futSST-pdSIC', 'pdSST-pdSIC',
       'ssp245-aer', 'pdSST-futArcSIC', 'dcppA-hindcast', 'dcppA-assim',
       'dcppC-hindcast-noPinatubo', 'dcppC-hindcast-noElChichon',
       'dcppC-hindcast-noAgung', 'hist-resIPO', 'ssp245-cov-modgreen',
       'ssp245-cov-fossil', 'ssp245-cov-strgreen', 'ssp245-covid', 'lgm',
       'ssp585-bgc', '1pctCO2to4x-withism', '1pctCO2-4xext', 'past1000',
       'pa-futArcSIC', 'pa-pdSIC', 'historical-ext', 'pdSST-futArcSICSIT',
       'pdSST-futOkhotskSIC', 'pdSST-futBKSeasSIC', 'pa-piArcSIC',
       'pa-piAntSIC', 'pa-futAntSIC', 'pdSST-pdSICSIT'], dtype=object)

In [6]:

df['institution_id'].unique()

df['institution_id'].unique()

Out[6]:

array(['CMCC', 'EC-Earth-Consortium', 'MOHC', 'ECMWF', 'NOAA-GFDL',
       'IPSL', 'E3SM-Project', 'CNRM-CERFACS', 'NASA-GISS', 'BCC',
       'MIROC', 'AWI', 'NCAR', 'MRI', 'CCCma', 'SNU', 'CAS', 'INM',
       'NUIST', 'HAMMOZ-Consortium', 'CAMS', 'MPI-M', 'DKRZ', 'DWD', 'UA',
       'NIMS-KMA', 'NCC', 'FIO-QLNM', 'KIOST', 'CSIRO-ARCCSS', 'CSIRO',
       'CCCR-IITM', 'THU', 'AS-RCEC', 'NERC', 'RUBISCO'], dtype=object)

The columns of the dataframe correspond to the CMI6 controlled vocabulary. A beginners' guide to these terms is available in this document.

Here we filter the data to find monthly surface air temperature for historical experiments.

In [7]:

df_ta = df.query("activity_id=='CMIP' & table_id == 'Amon' & variable_id == 'tas' & experiment_id == 'historical'")
df_ta

df_ta = df.query("activity_id=='CMIP' & table_id == 'Amon' & variable_id == 'tas' & experiment_id == 'historical'") df_ta

Out[7]:

	activity_id	institution_id	source_id	experiment_id	member_id	table_id	variable_id	grid_label	zstore	dcpp_init_year	version
973	CMIP	NOAA-GFDL	GFDL-ESM4	historical	r3i1p1f1	Amon	tas	gr1	gs://cmip6/CMIP6/CMIP/NOAA-GFDL/GFDL-ESM4/hist...	NaN	20180701
1766	CMIP	NOAA-GFDL	GFDL-ESM4	historical	r2i1p1f1	Amon	tas	gr1	gs://cmip6/CMIP6/CMIP/NOAA-GFDL/GFDL-ESM4/hist...	NaN	20180701
8074	CMIP	NOAA-GFDL	GFDL-CM4	historical	r1i1p1f1	Amon	tas	gr1	gs://cmip6/CMIP6/CMIP/NOAA-GFDL/GFDL-CM4/histo...	NaN	20180701
22185	CMIP	IPSL	IPSL-CM6A-LR	historical	r8i1p1f1	Amon	tas	gr	gs://cmip6/CMIP6/CMIP/IPSL/IPSL-CM6A-LR/histor...	NaN	20180803
22298	CMIP	IPSL	IPSL-CM6A-LR	historical	r2i1p1f1	Amon	tas	gr	gs://cmip6/CMIP6/CMIP/IPSL/IPSL-CM6A-LR/histor...	NaN	20180803
...	...	...	...	...	...	...	...	...	...	...	...
522952	CMIP	MRI	MRI-ESM2-0	historical	r7i1p1f1	Amon	tas	gn	gs://cmip6/CMIP6/CMIP/MRI/MRI-ESM2-0/historica...	NaN	20210813
523274	CMIP	MRI	MRI-ESM2-0	historical	r6i1p1f1	Amon	tas	gn	gs://cmip6/CMIP6/CMIP/MRI/MRI-ESM2-0/historica...	NaN	20210907
523712	CMIP	CMCC	CMCC-CM2-SR5	historical	r3i1p2f1	Amon	tas	gn	gs://cmip6/CMIP6/CMIP/CMCC/CMCC-CM2-SR5/histor...	NaN	20211108
523721	CMIP	CMCC	CMCC-CM2-SR5	historical	r2i1p2f1	Amon	tas	gn	gs://cmip6/CMIP6/CMIP/CMCC/CMCC-CM2-SR5/histor...	NaN	20211109
523769	CMIP	EC-Earth-Consortium	EC-Earth3-Veg	historical	r1i1p1f1	Amon	tas	gr	gs://cmip6/CMIP6/CMIP/EC-Earth-Consortium/EC-E...	NaN	20211207

635 rows × 11 columns

Now we do further filtering to find just the models from NOAA-GFDL.

In [17]:

df_ta_gfdl = df_ta.query('institution_id == "NOAA-GFDL"')
df_ta_gfdl

df_ta_gfdl = df_ta.query('institution_id == "NOAA-GFDL"') df_ta_gfdl

Out[17]:

	activity_id	institution_id	source_id	experiment_id	member_id	table_id	variable_id	grid_label	zstore	dcpp_init_year	version
973	CMIP	NOAA-GFDL	GFDL-ESM4	historical	r3i1p1f1	Amon	tas	gr1	gs://cmip6/CMIP6/CMIP/NOAA-GFDL/GFDL-ESM4/hist...	NaN	20180701
1766	CMIP	NOAA-GFDL	GFDL-ESM4	historical	r2i1p1f1	Amon	tas	gr1	gs://cmip6/CMIP6/CMIP/NOAA-GFDL/GFDL-ESM4/hist...	NaN	20180701
8074	CMIP	NOAA-GFDL	GFDL-CM4	historical	r1i1p1f1	Amon	tas	gr1	gs://cmip6/CMIP6/CMIP/NOAA-GFDL/GFDL-CM4/histo...	NaN	20180701
244695	CMIP	NOAA-GFDL	GFDL-ESM4	historical	r1i1p1f1	Amon	tas	gr1	gs://cmip6/CMIP6/CMIP/NOAA-GFDL/GFDL-ESM4/hist...	NaN	20190726

Load Data¶

Now we will load a single store using fsspec, zarr, and xarray.

In [18]:

df_ta_gfdl

df_ta_gfdl

Out[18]:

	activity_id	institution_id	source_id	experiment_id	member_id	table_id	variable_id	grid_label	zstore	dcpp_init_year	version
973	CMIP	NOAA-GFDL	GFDL-ESM4	historical	r3i1p1f1	Amon	tas	gr1	gs://cmip6/CMIP6/CMIP/NOAA-GFDL/GFDL-ESM4/hist...	NaN	20180701
1766	CMIP	NOAA-GFDL	GFDL-ESM4	historical	r2i1p1f1	Amon	tas	gr1	gs://cmip6/CMIP6/CMIP/NOAA-GFDL/GFDL-ESM4/hist...	NaN	20180701
8074	CMIP	NOAA-GFDL	GFDL-CM4	historical	r1i1p1f1	Amon	tas	gr1	gs://cmip6/CMIP6/CMIP/NOAA-GFDL/GFDL-CM4/histo...	NaN	20180701
244695	CMIP	NOAA-GFDL	GFDL-ESM4	historical	r1i1p1f1	Amon	tas	gr1	gs://cmip6/CMIP6/CMIP/NOAA-GFDL/GFDL-ESM4/hist...	NaN	20190726

In [19]:

# get the path to a specific zarr store (the first one from the dataframe above)
zstore = df_ta_gfdl.zstore.values[-1]
print(zstore)

# create an interface to the store
mapper = fsspec.get_mapper(zstore)

# open it using xarray and zarr
ds = xr.open_zarr(mapper, consolidated=True)
ds

# get the path to a specific zarr store (the first one from the dataframe above) zstore = df_ta_gfdl.zstore.values[-1] print(zstore) # create an interface to the store mapper = fsspec.get_mapper(zstore) # open it using xarray and zarr ds = xr.open_zarr(mapper, consolidated=True) ds

gs://cmip6/CMIP6/CMIP/NOAA-GFDL/GFDL-ESM4/historical/r1i1p1f1/Amon/tas/gr1/v20190726/

Out[19]:

<xarray.Dataset>
Dimensions:    (bnds: 2, lat: 180, lon: 288, time: 1980)
Coordinates:
  * bnds       (bnds) float64 1.0 2.0
    height     float64 ...
  * lat        (lat) float64 -89.5 -88.5 -87.5 -86.5 ... 86.5 87.5 88.5 89.5
    lat_bnds   (lat, bnds) float64 dask.array<chunksize=(180, 2), meta=np.ndarray>
  * lon        (lon) float64 0.625 1.875 3.125 4.375 ... 355.6 356.9 358.1 359.4
    lon_bnds   (lon, bnds) float64 dask.array<chunksize=(288, 2), meta=np.ndarray>
  * time       (time) object 1850-01-16 12:00:00 ... 2014-12-16 12:00:00
    time_bnds  (time, bnds) object dask.array<chunksize=(1980, 2), meta=np.ndarray>
Data variables:
    tas        (time, lat, lon) float32 dask.array<chunksize=(600, 180, 288), meta=np.ndarray>
Attributes: (12/49)
    Conventions:            CF-1.7 CMIP-6.0 UGRID-1.0
    activity_id:            CMIP
    branch_method:          standard
    branch_time_in_child:   0.0
    branch_time_in_parent:  36500.0
    comment:                <null ref>
    ...                     ...
    variable_id:            tas
    variant_info:           N/A
    variant_label:          r1i1p1f1
    status:                 2019-09-10;created;by nhn2@columbia.edu
    netcdf_tracking_ids:    hdl:21.14100/75e5c5a7-d7c4-4860-beb1-db454f25f13a...
    version_id:             v20190726

xarray.Dataset

• Dimensions:
  • bnds: 2
  • lat: 180
  • lon: 288
  • time: 1980
• Coordinates: (8)
  • bnds
    (bnds)
    float64
    1.0 2.0

    long_name :

    vertex number

    array([1., 2.])

  • height
    ()
    float64
    ...

    axis :

    Z

    cell_methods :

    time: point

    description :

    ~2 m standard surface air temperature and surface humidity height

    long_name :

    height

    positive :

    up

    standard_name :

    height

    units :

    m

    [1 values with dtype=float64]

  • lat
    (lat)
    float64
    -89.5 -88.5 -87.5 ... 88.5 89.5

    axis :

    Y

    bounds :

    lat_bnds

    cell_methods :

    time: point

    long_name :

    latitude

    standard_name :

    latitude

    units :

    degrees_north

    array([-89.5, -88.5, -87.5, -86.5, -85.5, -84.5, -83.5, -82.5, -81.5, -80.5,
           -79.5, -78.5, -77.5, -76.5, -75.5, -74.5, -73.5, -72.5, -71.5, -70.5,
           -69.5, -68.5, -67.5, -66.5, -65.5, -64.5, -63.5, -62.5, -61.5, -60.5,
           -59.5, -58.5, -57.5, -56.5, -55.5, -54.5, -53.5, -52.5, -51.5, -50.5,
           -49.5, -48.5, -47.5, -46.5, -45.5, -44.5, -43.5, -42.5, -41.5, -40.5,
           -39.5, -38.5, -37.5, -36.5, -35.5, -34.5, -33.5, -32.5, -31.5, -30.5,
           -29.5, -28.5, -27.5, -26.5, -25.5, -24.5, -23.5, -22.5, -21.5, -20.5,
           -19.5, -18.5, -17.5, -16.5, -15.5, -14.5, -13.5, -12.5, -11.5, -10.5,
            -9.5,  -8.5,  -7.5,  -6.5,  -5.5,  -4.5,  -3.5,  -2.5,  -1.5,  -0.5,
             0.5,   1.5,   2.5,   3.5,   4.5,   5.5,   6.5,   7.5,   8.5,   9.5,
            10.5,  11.5,  12.5,  13.5,  14.5,  15.5,  16.5,  17.5,  18.5,  19.5,
            20.5,  21.5,  22.5,  23.5,  24.5,  25.5,  26.5,  27.5,  28.5,  29.5,
            30.5,  31.5,  32.5,  33.5,  34.5,  35.5,  36.5,  37.5,  38.5,  39.5,
            40.5,  41.5,  42.5,  43.5,  44.5,  45.5,  46.5,  47.5,  48.5,  49.5,
            50.5,  51.5,  52.5,  53.5,  54.5,  55.5,  56.5,  57.5,  58.5,  59.5,
            60.5,  61.5,  62.5,  63.5,  64.5,  65.5,  66.5,  67.5,  68.5,  69.5,
            70.5,  71.5,  72.5,  73.5,  74.5,  75.5,  76.5,  77.5,  78.5,  79.5,
            80.5,  81.5,  82.5,  83.5,  84.5,  85.5,  86.5,  87.5,  88.5,  89.5])

  • lat_bnds
    (lat, bnds)
    float64
    dask.array<chunksize=(180, 2), meta=np.ndarray>

    axis :

    Y

    long_name :

    latitude bounds

    units :

    degrees_north

    Array Chunk Bytes 2.81 kiB 2.81 kiB Shape (180, 2) (180, 2) Dask graph 1 chunks in 2 graph layers Data type float64 numpy.ndarray

  • lon
    (lon)
    float64
    0.625 1.875 3.125 ... 358.1 359.4

    axis :

    X

    bounds :

    lon_bnds

    cell_methods :

    time: point

    long_name :

    longitude

    standard_name :

    longitude

    units :

    degrees_east

    array([  0.625,   1.875,   3.125, ..., 356.875, 358.125, 359.375])

  • lon_bnds
    (lon, bnds)
    float64
    dask.array<chunksize=(288, 2), meta=np.ndarray>

    axis :

    X

    long_name :

    longitude bounds

    units :

    degrees_east

    Array Chunk Bytes 4.50 kiB 4.50 kiB Shape (288, 2) (288, 2) Dask graph 1 chunks in 2 graph layers Data type float64 numpy.ndarray

  • time
    (time)
    object
    1850-01-16 12:00:00 ... 2014-12-...

    axis :

    T

    bounds :

    time_bnds

    calendar_type :

    noleap

    description :

    Temporal mean

    long_name :

    time

    standard_name :

    time

    array([cftime.DatetimeNoLeap(1850, 1, 16, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(1850, 2, 15, 0, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(1850, 3, 16, 12, 0, 0, 0, has_year_zero=True),
           ...,
           cftime.DatetimeNoLeap(2014, 10, 16, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2014, 11, 16, 0, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2014, 12, 16, 12, 0, 0, 0, has_year_zero=True)],
          dtype=object)

  • time_bnds
    (time, bnds)
    object
    dask.array<chunksize=(1980, 2), meta=np.ndarray>

    long_name :

    time axis boundaries

    Array Chunk Bytes 30.94 kiB 30.94 kiB Shape (1980, 2) (1980, 2) Dask graph 1 chunks in 2 graph layers Data type object numpy.ndarray

• Data variables: (1)
  • tas
    (time, lat, lon)
    float32
    dask.array<chunksize=(600, 180, 288), meta=np.ndarray>

    cell_measures :

    area: areacella

    cell_methods :

    area: time: mean

    interp_method :

    conserve_order2

    long_name :

    Near-Surface Air Temperature

    original_name :

    tas

    standard_name :

    air_temperature

    units :

    K

    Array Chunk Bytes 391.55 MiB 118.65 MiB Shape (1980, 180, 288) (600, 180, 288) Dask graph 4 chunks in 2 graph layers Data type float32 numpy.ndarray

• Indexes: (4)
  • bnds
    PandasIndex

    PandasIndex(Index([1.0, 2.0], dtype='float64', name='bnds'))

  • lat
    PandasIndex

    PandasIndex(Index([-89.5, -88.5, -87.5, -86.5, -85.5, -84.5, -83.5, -82.5, -81.5, -80.5,
           ...
            80.5,  81.5,  82.5,  83.5,  84.5,  85.5,  86.5,  87.5,  88.5,  89.5],
          dtype='float64', name='lat', length=180))

  • lon
    PandasIndex

    PandasIndex(Index([             0.625, 1.8749999999999998,              3.125,
                        4.375,              5.625,              6.875,
                        8.125,              9.375,             10.625,
                       11.875,
           ...
                      348.125,            349.375,            350.625,
                      351.875,            353.125,            354.375,
                      355.625,            356.875,            358.125,
                      359.375],
          dtype='float64', name='lon', length=288))

  • time
    PandasIndex

    PandasIndex(CFTimeIndex([1850-01-16 12:00:00, 1850-02-15 00:00:00, 1850-03-16 12:00:00,
                 1850-04-16 00:00:00, 1850-05-16 12:00:00, 1850-06-16 00:00:00,
                 1850-07-16 12:00:00, 1850-08-16 12:00:00, 1850-09-16 00:00:00,
                 1850-10-16 12:00:00,
                 ...
                 2014-03-16 12:00:00, 2014-04-16 00:00:00, 2014-05-16 12:00:00,
                 2014-06-16 00:00:00, 2014-07-16 12:00:00, 2014-08-16 12:00:00,
                 2014-09-16 00:00:00, 2014-10-16 12:00:00, 2014-11-16 00:00:00,
                 2014-12-16 12:00:00],
                dtype='object', length=1980, calendar='noleap', freq='None'))

• Attributes: (49)

  Conventions :

  CF-1.7 CMIP-6.0 UGRID-1.0

  activity_id :

  CMIP

  branch_method :

  standard

  branch_time_in_child :

  0.0

  branch_time_in_parent :

  36500.0

  comment :

  <null ref>

  contact :

  gfdl.climate.model.info@noaa.gov

  creation_date :

  2019-07-26T20:13:55Z

  data_specs_version :

  01.00.27

  experiment :

  all-forcing simulation of the recent past

  experiment_id :

  historical

  external_variables :

  areacella

  forcing_index :

  1

  frequency :

  mon

  further_info_url :

  https://furtherinfo.es-doc.org/CMIP6.NOAA-GFDL.GFDL-ESM4.historical.none.r1i1p1f1

  grid :

  atmos data regridded from Cubed-sphere (c96) to 180,288; interpolation method: conserve_order2

  grid_label :

  gr1

  history :

  File was processed by fremetar (GFDL analog of CMOR). TripleID: [exper_id_MFLg3OOf97,realiz_id_6UiFuoEKMa,run_id_eWiWnwFCM2]

  initialization_index :

  1

  institution :

  National Oceanic and Atmospheric Administration, Geophysical Fluid Dynamics Laboratory, Princeton, NJ 08540, USA

  institution_id :

  NOAA-GFDL

  license :

  CMIP6 model data produced by NOAA-GFDL is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License (https://creativecommons.org/licenses/). Consult https://pcmdi.llnl.gov/CMIP6/TermsOfUse for terms of use governing CMIP6 output, including citation requirements and proper acknowledgment. Further information about this data, including some limitations, can be found via the further_info_url (recorded as a global attribute in this file). The data producers and data providers make no warranty, either express or implied, including, but not limited to, warranties of merchantability and fitness for a particular purpose. All liabilities arising from the supply of the information (including any liability arising in negligence) are excluded to the fullest extent permitted by law.

  mip_era :

  CMIP6

  nominal_resolution :

  100 km

  parent_activity_id :

  CMIP

  parent_experiment_id :

  piControl

  parent_mip_era :

  CMIP6

  parent_source_id :

  GFDL-ESM4

  parent_time_units :

  days since 0001-1-1

  parent_variant_label :

  r1i1p1f1

  physics_index :

  1

  product :

  model-output

  realization_index :

  1

  realm :

  atmos

  references :

  see further_info_url attribute

  source :

  GFDL-ESM4 (2018): atmos: GFDL-AM4.1 (Cubed-sphere (c96) - 1 degree nominal horizontal resolution; 360 x 180 longitude/latitude; 49 levels; top level 1 Pa) ocean: GFDL-OM4p5 (GFDL-MOM6, tripolar - nominal 0.5 deg; 720 x 576 longitude/latitude; 75 levels; top grid cell 0-2 m) seaIce: GFDL-SIM4p5 (GFDL-SIS2.0, tripolar - nominal 0.5 deg; 720 x 576 longitude/latitude; 5 layers; 5 thickness categories) land: GFDL-LM4.1 aerosol: interactive atmosChem: GFDL-ATMCHEM4.1 (full atmospheric chemistry) ocnBgchem: GFDL-COBALTv2 landIce: GFDL-LM4.1 (GFDL ID: 2019_0334)

  source_id :

  GFDL-ESM4

  source_type :

  AOGCM AER CHEM BGC

  sub_experiment :

  none

  sub_experiment_id :

  none

  table_id :

  Amon

  title :

  NOAA GFDL GFDL-ESM4 model output prepared for CMIP6 all-forcing simulation of the recent past

  tracking_id :

  hdl:21.14100/75e5c5a7-d7c4-4860-beb1-db454f25f13a hdl:21.14100/a54fe2f4-0a68-4420-8702-36750bde9b05

  variable_id :

  tas

  variant_info :

  N/A

  variant_label :

  r1i1p1f1

  status :

  2019-09-10;created;by nhn2@columbia.edu

  netcdf_tracking_ids :

  hdl:21.14100/75e5c5a7-d7c4-4860-beb1-db454f25f13a hdl:21.14100/a54fe2f4-0a68-4420-8702-36750bde9b05

  version_id :

  v20190726

Plot a map from a specific date.

In [20]:

ds.tas.sel(time='1950-01').plot()

ds.tas.sel(time='1950-01').plot()

Out[20]:

<matplotlib.collections.QuadMesh at 0x7fb548d59790>

Create a timeseries of global-average surface air temperature. For this we need the area weighting factor for each gridpoint.

In [22]:

df_area = df.query("variable_id == 'areacella' & source_id == 'GFDL-ESM4'")
ds_area = xr.open_zarr(fsspec.get_mapper(df_area.zstore.values[0]), consolidated=True)
ds_area

df_area = df.query("variable_id == 'areacella' & source_id == 'GFDL-ESM4'") ds_area = xr.open_zarr(fsspec.get_mapper(df_area.zstore.values[0]), consolidated=True) ds_area

Out[22]:

<xarray.Dataset>
Dimensions:    (lat: 180, lon: 288, bnds: 2)
Coordinates:
  * bnds       (bnds) float64 1.0 2.0
  * lat        (lat) float64 -89.5 -88.5 -87.5 -86.5 ... 86.5 87.5 88.5 89.5
    lat_bnds   (lat, bnds) float64 dask.array<chunksize=(180, 2), meta=np.ndarray>
  * lon        (lon) float64 0.625 1.875 3.125 4.375 ... 355.6 356.9 358.1 359.4
    lon_bnds   (lon, bnds) float64 dask.array<chunksize=(288, 2), meta=np.ndarray>
Data variables:
    areacella  (lat, lon) float32 dask.array<chunksize=(180, 288), meta=np.ndarray>
Attributes: (12/48)
    Conventions:            CF-1.7 CMIP-6.0 UGRID-1.0
    activity_id:            CMIP
    branch_method:          standard
    branch_time_in_child:   0.0
    branch_time_in_parent:  36500.0
    comment:                <null ref>
    ...                     ...
    tracking_id:            hdl:21.14100/deeb5d3d-bbcc-464c-bb7d-ade2ac4d7ed0
    variable_id:            areacella
    variant_info:           N/A
    variant_label:          r1i1p1f1
    netcdf_tracking_ids:    hdl:21.14100/deeb5d3d-bbcc-464c-bb7d-ade2ac4d7ed0
    version_id:             v20180701

xarray.Dataset

• Dimensions:
  • lat: 180
  • lon: 288
  • bnds: 2
• Coordinates: (5)
  • bnds
    (bnds)
    float64
    1.0 2.0

    long_name :

    vertex number

    array([1., 2.])

  • lat
    (lat)
    float64
    -89.5 -88.5 -87.5 ... 88.5 89.5

    axis :

    Y

    bounds :

    lat_bnds

    cell_methods :

    time: point

    long_name :

    latitude

    standard_name :

    latitude

    units :

    degrees_north

    array([-89.5, -88.5, -87.5, -86.5, -85.5, -84.5, -83.5, -82.5, -81.5, -80.5,
           -79.5, -78.5, -77.5, -76.5, -75.5, -74.5, -73.5, -72.5, -71.5, -70.5,
           -69.5, -68.5, -67.5, -66.5, -65.5, -64.5, -63.5, -62.5, -61.5, -60.5,
           -59.5, -58.5, -57.5, -56.5, -55.5, -54.5, -53.5, -52.5, -51.5, -50.5,
           -49.5, -48.5, -47.5, -46.5, -45.5, -44.5, -43.5, -42.5, -41.5, -40.5,
           -39.5, -38.5, -37.5, -36.5, -35.5, -34.5, -33.5, -32.5, -31.5, -30.5,
           -29.5, -28.5, -27.5, -26.5, -25.5, -24.5, -23.5, -22.5, -21.5, -20.5,
           -19.5, -18.5, -17.5, -16.5, -15.5, -14.5, -13.5, -12.5, -11.5, -10.5,
            -9.5,  -8.5,  -7.5,  -6.5,  -5.5,  -4.5,  -3.5,  -2.5,  -1.5,  -0.5,
             0.5,   1.5,   2.5,   3.5,   4.5,   5.5,   6.5,   7.5,   8.5,   9.5,
            10.5,  11.5,  12.5,  13.5,  14.5,  15.5,  16.5,  17.5,  18.5,  19.5,
            20.5,  21.5,  22.5,  23.5,  24.5,  25.5,  26.5,  27.5,  28.5,  29.5,
            30.5,  31.5,  32.5,  33.5,  34.5,  35.5,  36.5,  37.5,  38.5,  39.5,
            40.5,  41.5,  42.5,  43.5,  44.5,  45.5,  46.5,  47.5,  48.5,  49.5,
            50.5,  51.5,  52.5,  53.5,  54.5,  55.5,  56.5,  57.5,  58.5,  59.5,
            60.5,  61.5,  62.5,  63.5,  64.5,  65.5,  66.5,  67.5,  68.5,  69.5,
            70.5,  71.5,  72.5,  73.5,  74.5,  75.5,  76.5,  77.5,  78.5,  79.5,
            80.5,  81.5,  82.5,  83.5,  84.5,  85.5,  86.5,  87.5,  88.5,  89.5])

  • lat_bnds
    (lat, bnds)
    float64
    dask.array<chunksize=(180, 2), meta=np.ndarray>

    axis :

    Y

    long_name :

    latitude bounds

    units :

    degrees_north

    Array Chunk Bytes 2.81 kiB 2.81 kiB Shape (180, 2) (180, 2) Dask graph 1 chunks in 2 graph layers Data type float64 numpy.ndarray

  • lon
    (lon)
    float64
    0.625 1.875 3.125 ... 358.1 359.4

    axis :

    X

    bounds :

    lon_bnds

    cell_methods :

    time: point

    long_name :

    longitude

    standard_name :

    longitude

    units :

    degrees_east

    array([  0.625,   1.875,   3.125, ..., 356.875, 358.125, 359.375])

  • lon_bnds
    (lon, bnds)
    float64
    dask.array<chunksize=(288, 2), meta=np.ndarray>

    axis :

    X

    long_name :

    longitude bounds

    units :

    degrees_east

    Array Chunk Bytes 4.50 kiB 4.50 kiB Shape (288, 2) (288, 2) Dask graph 1 chunks in 2 graph layers Data type float64 numpy.ndarray

• Data variables: (1)
  • areacella
    (lat, lon)
    float32
    dask.array<chunksize=(180, 288), meta=np.ndarray>

    cell_methods :

    area: sum

    interp_method :

    conserve_order1

    long_name :

    Grid-Cell Area for Atmospheric Variables

    original_name :

    areacella

    standard_name :

    cell_area

    units :

    m2

    Array Chunk Bytes 202.50 kiB 202.50 kiB Shape (180, 288) (180, 288) Dask graph 1 chunks in 2 graph layers Data type float32 numpy.ndarray

• Indexes: (3)
  • bnds
    PandasIndex

    PandasIndex(Index([1.0, 2.0], dtype='float64', name='bnds'))

  • lat
    PandasIndex

    PandasIndex(Index([-89.5, -88.5, -87.5, -86.5, -85.5, -84.5, -83.5, -82.5, -81.5, -80.5,
           ...
            80.5,  81.5,  82.5,  83.5,  84.5,  85.5,  86.5,  87.5,  88.5,  89.5],
          dtype='float64', name='lat', length=180))

  • lon
    PandasIndex

    PandasIndex(Index([  0.625,   1.875,   3.125,   4.375,   5.625,   6.875,   8.125,   9.375,
            10.625,  11.875,
           ...
           348.125, 349.375, 350.625, 351.875, 353.125, 354.375, 355.625, 356.875,
           358.125, 359.375],
          dtype='float64', name='lon', length=288))

• Attributes: (48)

  Conventions :

  CF-1.7 CMIP-6.0 UGRID-1.0

  activity_id :

  CMIP

  branch_method :

  standard

  branch_time_in_child :

  0.0

  branch_time_in_parent :

  36500.0

  comment :

  <null ref>

  contact :

  gfdl.climate.model.info@noaa.gov

  creation_date :

  2019-05-21T04:16:30Z

  data_specs_version :

  01.00.27

  experiment :

  1 percent per year increase in CO2

  experiment_id :

  1pctCO2

  forcing_index :

  1

  frequency :

  fx

  further_info_url :

  https://furtherinfo.es-doc.org/CMIP6.NOAA-GFDL.GFDL-ESM4.1pctCO2.none.r1i1p1f1

  grid :

  atmos data regridded from Cubed-sphere (c96) to 180,288; interpolation method: conserve_order1

  grid_label :

  gr1

  history :

  File was processed by fremetar (GFDL analog of CMOR). TripleID: [exper_id_B87UgqxI9B,realiz_id_fN7PwOvCuS,run_id_w2CeZpk80Y]

  initialization_index :

  1

  institution :

  National Oceanic and Atmospheric Administration, Geophysical Fluid Dynamics Laboratory, Princeton, NJ 08540, USA

  institution_id :

  NOAA-GFDL

  license :

  CMIP6 model data produced by NOAA-GFDL is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License (https://creativecommons.org/licenses/). Consult https://pcmdi.llnl.gov/CMIP6/TermsOfUse for terms of use governing CMIP6 output, including citation requirements and proper acknowledgment. Further information about this data, including some limitations, can be found via the further_info_url (recorded as a global attribute in this file). The data producers and data providers make no warranty, either express or implied, including, but not limited to, warranties of merchantability and fitness for a particular purpose. All liabilities arising from the supply of the information (including any liability arising in negligence) are excluded to the fullest extent permitted by law.

  mip_era :

  CMIP6

  nominal_resolution :

  100 km

  parent_activity_id :

  CMIP

  parent_experiment_id :

  piControl

  parent_mip_era :

  CMIP6

  parent_source_id :

  GFDL-ESM4

  parent_time_units :

  days since 0001-1-1

  parent_variant_label :

  r1i1p1f1

  physics_index :

  1

  product :

  model-output

  realization_index :

  1

  realm :

  atmos land

  references :

  see further_info_url attribute

  source :

  GFDL-ESM4 (2018): atmos: GFDL-AM4.1 (Cubed-sphere (c96) - 1 degree nominal horizontal resolution; 360 x 180 longitude/latitude; 49 levels; top level 1 Pa) ocean: GFDL-OM4p5 (GFDL-MOM6, tripolar - nominal 0.5 deg; 720 x 576 longitude/latitude; 75 levels; top grid cell 0-2 m) seaIce: GFDL-SIM4p5 (GFDL-SIS2.0, tripolar - nominal 0.5 deg; 720 x 576 longitude/latitude; 5 layers; 5 thickness categories) land: GFDL-LM4.1 aerosol: interactive atmosChem: GFDL-ATMCHEM4.1 (full atmospheric chemistry) ocnBgchem: GFDL-COBALTv2 landIce: GFDL-LM4.1 (GFDL ID: 2019_0277)

  source_id :

  GFDL-ESM4

  source_type :

  AOGCM AER CHEM BGC

  status :

  2020-09-09;created; by gcs.cmip6.ldeo@gmail.com

  sub_experiment :

  none

  sub_experiment_id :

  none

  table_id :

  fx

  title :

  NOAA GFDL GFDL-ESM4 model output prepared for CMIP6 1 percent per year increase in CO2

  tracking_id :

  hdl:21.14100/deeb5d3d-bbcc-464c-bb7d-ade2ac4d7ed0

  variable_id :

  areacella

  variant_info :

  N/A

  variant_label :

  r1i1p1f1

  netcdf_tracking_ids :

  hdl:21.14100/deeb5d3d-bbcc-464c-bb7d-ade2ac4d7ed0

  version_id :

  v20180701

In [23]:

total_area = ds_area.areacella.sum(dim=['lon', 'lat'])
ta_timeseries = (ds.tas * ds_area.areacella).sum(dim=['lon', 'lat']) / total_area
ta_timeseries

total_area = ds_area.areacella.sum(dim=['lon', 'lat']) ta_timeseries = (ds.tas * ds_area.areacella).sum(dim=['lon', 'lat']) / total_area ta_timeseries

Out[23]:

<xarray.DataArray (time: 1980)>
dask.array<truediv, shape=(1980,), dtype=float32, chunksize=(600,), chunktype=numpy.ndarray>
Coordinates:
  * time     (time) object 1850-01-16 12:00:00 ... 2014-12-16 12:00:00
    height   float64 ...

xarray.DataArray

• time: 1980

• dask.array<chunksize=(600,), meta=np.ndarray>

  Array Chunk Bytes 7.73 kiB 2.34 kiB Shape (1980,) (600,) Dask graph 4 chunks in 22 graph layers Data type float32 numpy.ndarray

• Coordinates: (2)
  • time
    (time)
    object
    1850-01-16 12:00:00 ... 2014-12-...

    axis :

    T

    bounds :

    time_bnds

    calendar_type :

    noleap

    description :

    Temporal mean

    long_name :

    time

    standard_name :

    time

    array([cftime.DatetimeNoLeap(1850, 1, 16, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(1850, 2, 15, 0, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(1850, 3, 16, 12, 0, 0, 0, has_year_zero=True),
           ...,
           cftime.DatetimeNoLeap(2014, 10, 16, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2014, 11, 16, 0, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2014, 12, 16, 12, 0, 0, 0, has_year_zero=True)],
          dtype=object)

  • height
    ()
    float64
    ...

    axis :

    Z

    cell_methods :

    time: point

    description :

    ~2 m standard surface air temperature and surface humidity height

    long_name :

    height

    positive :

    up

    standard_name :

    height

    units :

    m

    [1 values with dtype=float64]

• Indexes: (1)
  • time
    PandasIndex

    PandasIndex(CFTimeIndex([1850-01-16 12:00:00, 1850-02-15 00:00:00, 1850-03-16 12:00:00,
                 1850-04-16 00:00:00, 1850-05-16 12:00:00, 1850-06-16 00:00:00,
                 1850-07-16 12:00:00, 1850-08-16 12:00:00, 1850-09-16 00:00:00,
                 1850-10-16 12:00:00,
                 ...
                 2014-03-16 12:00:00, 2014-04-16 00:00:00, 2014-05-16 12:00:00,
                 2014-06-16 00:00:00, 2014-07-16 12:00:00, 2014-08-16 12:00:00,
                 2014-09-16 00:00:00, 2014-10-16 12:00:00, 2014-11-16 00:00:00,
                 2014-12-16 12:00:00],
                dtype='object', length=1980, calendar='noleap', freq='None'))

• Attributes: (0)

By default the data are loaded lazily, as Dask arrays. Here we trigger computation explicitly.

In [24]:

%time ta_timeseries.load()

%time ta_timeseries.load()

CPU times: user 6.3 s, sys: 1.56 s, total: 7.87 s
Wall time: 40.4 s

Out[24]:

<xarray.DataArray (time: 1980)>
array([224.00783, 224.21144, 224.76314, ..., 226.22311, 225.26149,
       224.80829], dtype=float32)
Coordinates:
  * time     (time) object 1850-01-16 12:00:00 ... 2014-12-16 12:00:00
    height   float64 2.0

xarray.DataArray

• time: 1980

• 224.0 224.2 224.8 225.6 226.3 226.9 ... 227.7 227.1 226.2 225.3 224.8

  array([224.00783, 224.21144, 224.76314, ..., 226.22311, 225.26149,
         224.80829], dtype=float32)

• Coordinates: (2)
  • time
    (time)
    object
    1850-01-16 12:00:00 ... 2014-12-...

    axis :

    T

    bounds :

    time_bnds

    calendar_type :

    noleap

    description :

    Temporal mean

    long_name :

    time

    standard_name :

    time

    array([cftime.DatetimeNoLeap(1850, 1, 16, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(1850, 2, 15, 0, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(1850, 3, 16, 12, 0, 0, 0, has_year_zero=True),
           ...,
           cftime.DatetimeNoLeap(2014, 10, 16, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2014, 11, 16, 0, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2014, 12, 16, 12, 0, 0, 0, has_year_zero=True)],
          dtype=object)

  • height
    ()
    float64
    2.0

    axis :

    Z

    cell_methods :

    time: point

    description :

    ~2 m standard surface air temperature and surface humidity height

    long_name :

    height

    positive :

    up

    standard_name :

    height

    units :

    m

    array(2.)

• Indexes: (1)
  • time
    PandasIndex

    PandasIndex(CFTimeIndex([1850-01-16 12:00:00, 1850-02-15 00:00:00, 1850-03-16 12:00:00,
                 1850-04-16 00:00:00, 1850-05-16 12:00:00, 1850-06-16 00:00:00,
                 1850-07-16 12:00:00, 1850-08-16 12:00:00, 1850-09-16 00:00:00,
                 1850-10-16 12:00:00,
                 ...
                 2014-03-16 12:00:00, 2014-04-16 00:00:00, 2014-05-16 12:00:00,
                 2014-06-16 00:00:00, 2014-07-16 12:00:00, 2014-08-16 12:00:00,
                 2014-09-16 00:00:00, 2014-10-16 12:00:00, 2014-11-16 00:00:00,
                 2014-12-16 12:00:00],
                dtype='object', length=1980, calendar='noleap', freq='None'))

• Attributes: (0)

In [25]:

ta_timeseries.plot(label='monthly')
ta_timeseries.rolling(time=12).mean().plot(label='12 month rolling mean')
plt.legend()
plt.title('Global Mean Surface Air Temperature')

ta_timeseries.plot(label='monthly') ta_timeseries.rolling(time=12).mean().plot(label='12 month rolling mean') plt.legend() plt.title('Global Mean Surface Air Temperature')

Out[25]:

Text(0.5, 1.0, 'Global Mean Surface Air Temperature')

In [ ]:

In [ ]: