Regridding using the grid-weights library

import astropy.coordinates
import cdshealpix.nested
import cf_xarray  # noqa: F401
import geoarrow.rust.core as geoarrow
import grid_weights.api as grid_weights
import numpy as np
import xarray as xr
import xdggs  # noqa: F401
from grid_indexing import infer_cell_geometries

xr.set_options(keep_attrs=True, display_expand_attrs=False, display_expand_data=False)

<xarray.core.options.set_options at 0x7f982f795f40>

from distributed import Client

client = Client()
client

Client

Client-de0671eb-689c-11f0-90e0-6045bd3360ad

Connection method: Cluster object	Cluster type: distributed.LocalCluster
Dashboard: http://127.0.0.1:8787/status

Launch dashboard in JupyterLab

Cluster Info

LocalCluster

be30efe8

Dashboard: http://127.0.0.1:8787/status	Workers: 4
Total threads: 4	Total memory: 15.62 GiB
Status: running	Using processes: True

Scheduler Info

Scheduler

Scheduler-7deb0528-5674-41ff-ae55-4b3f3ccf25da

Comm: tcp://127.0.0.1:36779	Workers: 4
Dashboard: http://127.0.0.1:8787/status	Total threads: 4
Started: Just now	Total memory: 15.62 GiB

Workers

Worker: 0

Comm: tcp://127.0.0.1:37037	Total threads: 1
Dashboard: http://127.0.0.1:39655/status	Memory: 3.91 GiB
Nanny: tcp://127.0.0.1:33157
Local directory: /tmp/dask-scratch-space/worker-s3vz2suq

Worker: 1

Comm: tcp://127.0.0.1:40095	Total threads: 1
Dashboard: http://127.0.0.1:36205/status	Memory: 3.91 GiB
Nanny: tcp://127.0.0.1:42849
Local directory: /tmp/dask-scratch-space/worker-urnw2cet

Worker: 2

Comm: tcp://127.0.0.1:42329	Total threads: 1
Dashboard: http://127.0.0.1:44067/status	Memory: 3.91 GiB
Nanny: tcp://127.0.0.1:45661
Local directory: /tmp/dask-scratch-space/worker-9xcyw8rq

Worker: 3

Comm: tcp://127.0.0.1:40219	Total threads: 1
Dashboard: http://127.0.0.1:46081/status	Memory: 3.91 GiB
Nanny: tcp://127.0.0.1:35239
Local directory: /tmp/dask-scratch-space/worker-dd4vcn2h

rectilinear grid: the air_temperature example dataset

ds = xr.tutorial.open_dataset("air_temperature", chunks={"time": 20}).isel(
    time=slice(None, 400)
)
ds

<xarray.Dataset> Size: 4MB
Dimensions:  (lat: 25, time: 400, lon: 53)
Coordinates:
  * lat      (lat) float32 100B 75.0 72.5 70.0 67.5 65.0 ... 22.5 20.0 17.5 15.0
  * lon      (lon) float32 212B 200.0 202.5 205.0 207.5 ... 325.0 327.5 330.0
  * time     (time) datetime64[ns] 3kB 2013-01-01 ... 2013-04-10T18:00:00
Data variables:
    air      (time, lat, lon) float64 4MB dask.array<chunksize=(20, 25, 53), meta=np.ndarray>
Attributes: (5)

xarray.Dataset

• Dimensions:
  • lat: 25
  • time: 400
  • lon: 53
• Coordinates: (3)
  • lat
    (lat)
    float32
    75.0 72.5 70.0 ... 20.0 17.5 15.0

    standard_name :

    latitude

    long_name :

    Latitude

    units :

    degrees_north

    axis :

    Y

    array([75. , 72.5, 70. , 67.5, 65. , 62.5, 60. , 57.5, 55. , 52.5, 50. , 47.5,
           45. , 42.5, 40. , 37.5, 35. , 32.5, 30. , 27.5, 25. , 22.5, 20. , 17.5,
           15. ], dtype=float32)

  • lon
    (lon)
    float32
    200.0 202.5 205.0 ... 327.5 330.0

    standard_name :

    longitude

    long_name :

    Longitude

    units :

    degrees_east

    axis :

    X

    array([200. , 202.5, 205. , 207.5, 210. , 212.5, 215. , 217.5, 220. , 222.5,
           225. , 227.5, 230. , 232.5, 235. , 237.5, 240. , 242.5, 245. , 247.5,
           250. , 252.5, 255. , 257.5, 260. , 262.5, 265. , 267.5, 270. , 272.5,
           275. , 277.5, 280. , 282.5, 285. , 287.5, 290. , 292.5, 295. , 297.5,
           300. , 302.5, 305. , 307.5, 310. , 312.5, 315. , 317.5, 320. , 322.5,
           325. , 327.5, 330. ], dtype=float32)

  • time
    (time)
    datetime64[ns]
    2013-01-01 ... 2013-04-10T18:00:00

    standard_name :

    time

    long_name :

    Time

    array(['2013-01-01T00:00:00.000000000', '2013-01-01T06:00:00.000000000',
           '2013-01-01T12:00:00.000000000', ..., '2013-04-10T06:00:00.000000000',
           '2013-04-10T12:00:00.000000000', '2013-04-10T18:00:00.000000000'],
          shape=(400,), dtype='datetime64[ns]')

• Data variables: (1)
  • air
    (time, lat, lon)
    float64
    dask.array<chunksize=(20, 25, 53), meta=np.ndarray>

    long_name :

    4xDaily Air temperature at sigma level 995

    units :

    degK

    precision :

    2

    GRIB_id :

    11

    GRIB_name :

    TMP

    var_desc :

    Air temperature

    dataset :

    NMC Reanalysis

    level_desc :

    Surface

    statistic :

    Individual Obs

    parent_stat :

    Other

    actual_range :

    [185.16 322.1 ]

    Array Chunk Bytes 4.04 MiB 207.03 kiB Shape (400, 25, 53) (20, 25, 53) Dask graph 20 chunks in 3 graph layers Data type float64 numpy.ndarray

• Indexes: (3)
  • lat
    PandasIndex

    PandasIndex(Index([75.0, 72.5, 70.0, 67.5, 65.0, 62.5, 60.0, 57.5, 55.0, 52.5, 50.0, 47.5,
           45.0, 42.5, 40.0, 37.5, 35.0, 32.5, 30.0, 27.5, 25.0, 22.5, 20.0, 17.5,
           15.0],
          dtype='float32', name='lat'))

  • lon
    PandasIndex

    PandasIndex(Index([200.0, 202.5, 205.0, 207.5, 210.0, 212.5, 215.0, 217.5, 220.0, 222.5,
           225.0, 227.5, 230.0, 232.5, 235.0, 237.5, 240.0, 242.5, 245.0, 247.5,
           250.0, 252.5, 255.0, 257.5, 260.0, 262.5, 265.0, 267.5, 270.0, 272.5,
           275.0, 277.5, 280.0, 282.5, 285.0, 287.5, 290.0, 292.5, 295.0, 297.5,
           300.0, 302.5, 305.0, 307.5, 310.0, 312.5, 315.0, 317.5, 320.0, 322.5,
           325.0, 327.5, 330.0],
          dtype='float32', name='lon'))

  • time
    PandasIndex

    PandasIndex(DatetimeIndex(['2013-01-01 00:00:00', '2013-01-01 06:00:00',
                   '2013-01-01 12:00:00', '2013-01-01 18:00:00',
                   '2013-01-02 00:00:00', '2013-01-02 06:00:00',
                   '2013-01-02 12:00:00', '2013-01-02 18:00:00',
                   '2013-01-03 00:00:00', '2013-01-03 06:00:00',
                   ...
                   '2013-04-08 12:00:00', '2013-04-08 18:00:00',
                   '2013-04-09 00:00:00', '2013-04-09 06:00:00',
                   '2013-04-09 12:00:00', '2013-04-09 18:00:00',
                   '2013-04-10 00:00:00', '2013-04-10 06:00:00',
                   '2013-04-10 12:00:00', '2013-04-10 18:00:00'],
                  dtype='datetime64[ns]', name='time', length=400, freq=None))

• Attributes: (5)

  Conventions :

  COARDS

  title :

  4x daily NMC reanalysis (1948)

  description :

  Data is from NMC initialized reanalysis (4x/day). These are the 0.9950 sigma level values.

  platform :

  Model

  references :

  http://www.esrl.noaa.gov/psd/data/gridded/data.ncep.reanalysis.html

upscaled = (
    ds.interp(lon=np.linspace(200, 330, 530), lat=np.linspace(15, 76, 250))
    .assign_coords(lon=lambda ds: (ds["lon"] + 180) % 360 - 180)
    .chunk({"lon": 265, "lat": 125})
)
upscaled

<xarray.Dataset> Size: 424MB
Dimensions:  (time: 400, lat: 250, lon: 530)
Coordinates:
  * time     (time) datetime64[ns] 3kB 2013-01-01 ... 2013-04-10T18:00:00
  * lat      (lat) float64 2kB 15.0 15.24 15.49 15.73 ... 75.27 75.51 75.76 76.0
  * lon      (lon) float64 4kB -160.0 -159.8 -159.5 ... -30.49 -30.25 -30.0
Data variables:
    air      (time, lat, lon) float64 424MB dask.array<chunksize=(20, 125, 265), meta=np.ndarray>
Attributes: (5)

xarray.Dataset

• Dimensions:
  • time: 400
  • lat: 250
  • lon: 530
• Coordinates: (3)
  • time
    (time)
    datetime64[ns]
    2013-01-01 ... 2013-04-10T18:00:00

    standard_name :

    time

    long_name :

    Time

    array(['2013-01-01T00:00:00.000000000', '2013-01-01T06:00:00.000000000',
           '2013-01-01T12:00:00.000000000', ..., '2013-04-10T06:00:00.000000000',
           '2013-04-10T12:00:00.000000000', '2013-04-10T18:00:00.000000000'],
          shape=(400,), dtype='datetime64[ns]')

  • lat
    (lat)
    float64
    15.0 15.24 15.49 ... 75.76 76.0

    standard_name :

    latitude

    long_name :

    Latitude

    units :

    degrees_north

    axis :

    Y

    array([15.     , 15.24498, 15.48996, ..., 75.51004, 75.75502, 76.     ],
          shape=(250,))

  • lon
    (lon)
    float64
    -160.0 -159.8 ... -30.25 -30.0

    standard_name :

    longitude

    long_name :

    Longitude

    units :

    degrees_east

    axis :

    X

    array([-160.      , -159.754253, -159.508507, ...,  -30.491493,  -30.245747,
            -30.      ], shape=(530,))

• Data variables: (1)
  • air
    (time, lat, lon)
    float64
    dask.array<chunksize=(20, 125, 265), meta=np.ndarray>

    long_name :

    4xDaily Air temperature at sigma level 995

    units :

    degK

    precision :

    2

    GRIB_id :

    11

    GRIB_name :

    TMP

    var_desc :

    Air temperature

    dataset :

    NMC Reanalysis

    level_desc :

    Surface

    statistic :

    Individual Obs

    parent_stat :

    Other

    actual_range :

    [185.16 322.1 ]

    Array Chunk Bytes 404.36 MiB 5.05 MiB Shape (400, 250, 530) (20, 125, 265) Dask graph 80 chunks in 20 graph layers Data type float64 numpy.ndarray

• Indexes: (3)
  • time
    PandasIndex

    PandasIndex(DatetimeIndex(['2013-01-01 00:00:00', '2013-01-01 06:00:00',
                   '2013-01-01 12:00:00', '2013-01-01 18:00:00',
                   '2013-01-02 00:00:00', '2013-01-02 06:00:00',
                   '2013-01-02 12:00:00', '2013-01-02 18:00:00',
                   '2013-01-03 00:00:00', '2013-01-03 06:00:00',
                   ...
                   '2013-04-08 12:00:00', '2013-04-08 18:00:00',
                   '2013-04-09 00:00:00', '2013-04-09 06:00:00',
                   '2013-04-09 12:00:00', '2013-04-09 18:00:00',
                   '2013-04-10 00:00:00', '2013-04-10 06:00:00',
                   '2013-04-10 12:00:00', '2013-04-10 18:00:00'],
                  dtype='datetime64[ns]', name='time', length=400, freq=None))

  • lat
    PandasIndex

    PandasIndex(Index([              15.0, 15.244979919678714,  15.48995983935743,
           15.734939759036145,  15.97991967871486, 16.224899598393574,
            16.46987951807229, 16.714859437751002,  16.95983935742972,
           17.204819277108435,
           ...
            73.79518072289156,  74.04016064257027,    74.285140562249,
            74.53012048192771,  74.77510040160642,  75.02008032128514,
            75.26506024096386,  75.51004016064257,  75.75502008032129,
                         76.0],
          dtype='float64', name='lat', length=250))

  • lon
    PandasIndex

    PandasIndex(Index([             -160.0, -159.75425330812857, -159.50850661625708,
            -159.2627599243856, -159.01701323251416, -158.77126654064273,
            -158.5255198487713,  -158.2797731568998, -158.03402646502832,
            -157.7882797731569,
           ...
            -32.21172022684311,  -31.96597353497168, -31.720226843100193,
           -31.474480151228704, -31.228733459357272,  -30.98298676748584,
            -30.73724007561441,  -30.49149338374292,  -30.24574669187143,
                         -30.0],
          dtype='float64', name='lon', length=530))

• Attributes: (5)

  Conventions :

  COARDS

  title :

  4x daily NMC reanalysis (1948)

  description :

  Data is from NMC initialized reanalysis (4x/day). These are the 0.9950 sigma level values.

  platform :

  Model

  references :

  http://www.esrl.noaa.gov/psd/data/gridded/data.ncep.reanalysis.html

level = 7
lon = astropy.coordinates.Longitude(
    [200, 225, 250, 275, 300, 330, 330, 300, 275, 250, 225, 200], unit="degree"
)
lat = astropy.coordinates.Latitude(
    [15, 15, 15, 15, 15, 15, 75, 75, 75, 75, 75, 75], unit="degree"
)
cell_ids, _, _ = cdshealpix.nested.polygon_search(lon, lat, depth=level, flat=True)

target_grid = (
    xr.Dataset(coords={"cell_ids": ("cells", cell_ids)})
    .dggs.decode({"grid_name": "healpix", "level": level, "indexing_scheme": "nested"})
    .dggs.assign_latlon_coords()
)
target_grid

<xarray.Dataset> Size: 610kB
Dimensions:    (cells: 25400)
Coordinates:
  * cell_ids   (cells) uint64 203kB 33629 33630 33631 ... 131069 131070 131071
    latitude   (cells) float64 203kB 15.09 15.09 15.4 ... 41.01 41.01 41.41
    longitude  (cells) float64 203kB 229.6 228.9 229.2 ... 270.4 269.6 270.0
Dimensions without coordinates: cells
Data variables:
    *empty*
Indexes:
    cell_ids  HealpixIndex(level=7, indexing_scheme=nested)

xarray.Dataset

• Dimensions:
  • cells: 25400
• Coordinates: (3)
  • cell_ids
    (cells)
    uint64
    33629 33630 33631 ... 131070 131071

    grid_name :

    healpix

    level :

    7

    indexing_scheme :

    nested

    array([ 33629,  33630,  33631, ..., 131069, 131070, 131071],
          shape=(25400,), dtype=uint64)

  • latitude
    (cells)
    float64
    15.09 15.09 15.4 ... 41.01 41.41

    array([15.0947871 , 15.0947871 , 15.4040937 , ..., 41.01449967,
           41.01449967, 41.41118864], shape=(25400,))

  • longitude
    (cells)
    float64
    229.6 228.9 229.2 ... 269.6 270.0

    array([229.5703125, 228.8671875, 229.21875  , ..., 270.3515625,
           269.6484375, 270.       ], shape=(25400,))

• Data variables: (0)
• Indexes: (1)
  • cell_ids
    HealpixIndex(level=7, indexing_scheme=nested)

    <xdggs.healpix.HealpixIndex object at 0x7f98945d0d10>

• Attributes: (0)

source_geoms_ = geoarrow.to_shapely(infer_cell_geometries(upscaled)).reshape((530, 250))
source_geoms = xr.DataArray(
    source_geoms_, dims=["lon", "lat"], coords=upscaled[["lon", "lat"]].coords
).chunk({"lon": 265, "lat": 125})
source_geoms

<xarray.DataArray (lon: 530, lat: 250)> Size: 1MB
dask.array<chunksize=(265, 125), meta=np.ndarray>
Coordinates:
  * lon      (lon) float64 4kB -160.0 -159.8 -159.5 ... -30.49 -30.25 -30.0
  * lat      (lat) float64 2kB 15.0 15.24 15.49 15.73 ... 75.27 75.51 75.76 76.0

xarray.DataArray

• lon: 530
• lat: 250

• dask.array<chunksize=(265, 125), meta=np.ndarray>

  Array Chunk Bytes 1.01 MiB 258.79 kiB Shape (530, 250) (265, 125) Dask graph 4 chunks in 1 graph layer Data type object numpy.ndarray

• Coordinates: (2)
  • lon
    (lon)
    float64
    -160.0 -159.8 ... -30.25 -30.0

    standard_name :

    longitude

    long_name :

    Longitude

    units :

    degrees_east

    axis :

    X

    array([-160.      , -159.754253, -159.508507, ...,  -30.491493,  -30.245747,
            -30.      ], shape=(530,))

  • lat
    (lat)
    float64
    15.0 15.24 15.49 ... 75.76 76.0

    standard_name :

    latitude

    long_name :

    Latitude

    units :

    degrees_north

    axis :

    Y

    array([15.     , 15.24498, 15.48996, ..., 75.51004, 75.75502, 76.     ],
          shape=(250,))

• Indexes: (2)
  • lat
    PandasIndex

    PandasIndex(Index([              15.0, 15.244979919678714,  15.48995983935743,
           15.734939759036145,  15.97991967871486, 16.224899598393574,
            16.46987951807229, 16.714859437751002,  16.95983935742972,
           17.204819277108435,
           ...
            73.79518072289156,  74.04016064257027,    74.285140562249,
            74.53012048192771,  74.77510040160642,  75.02008032128514,
            75.26506024096386,  75.51004016064257,  75.75502008032129,
                         76.0],
          dtype='float64', name='lat', length=250))

  • lon
    PandasIndex

    PandasIndex(Index([             -160.0, -159.75425330812857, -159.50850661625708,
            -159.2627599243856, -159.01701323251416, -158.77126654064273,
            -158.5255198487713,  -158.2797731568998, -158.03402646502832,
            -157.7882797731569,
           ...
            -32.21172022684311,  -31.96597353497168, -31.720226843100193,
           -31.474480151228704, -31.228733459357272,  -30.98298676748584,
            -30.73724007561441,  -30.49149338374292,  -30.24574669187143,
                         -30.0],
          dtype='float64', name='lon', length=530))

• Attributes: (0)

target_geoms = target_grid.dggs.cell_boundaries().chunk({"cells": 5100}).dggs.decode()
target_geoms

<xarray.DataArray (cells: 25400)> Size: 203kB
dask.array<chunksize=(5100,), meta=np.ndarray>
Coordinates:
  * cell_ids  (cells) uint64 203kB dask.array<chunksize=(5100,), meta=np.ndarray>
Dimensions without coordinates: cells
Indexes:
    cell_ids  HealpixIndex(level=7, indexing_scheme=nested)

xarray.DataArray

• cells: 25400

• dask.array<chunksize=(5100,), meta=np.ndarray>

  Array Chunk Bytes 198.44 kiB 39.84 kiB Shape (25400,) (5100,) Dask graph 5 chunks in 1 graph layer Data type object numpy.ndarray

• Coordinates: (1)
  • cell_ids
    (cells)
    uint64
    dask.array<chunksize=(5100,), meta=np.ndarray>

    grid_name :

    healpix

    level :

    7

    indexing_scheme :

    nested

    Array Chunk Bytes 198.44 kiB 39.84 kiB Shape (25400,) (5100,) Dask graph 5 chunks in 1 graph layer Data type uint64 numpy.ndarray

• Indexes: (1)
  • cell_ids
    HealpixIndex(level=7, indexing_scheme=nested)

    <xdggs.healpix.HealpixIndex object at 0x7f981c3103e0>

• Attributes: (0)

%%time
algorithms = grid_weights.Algorithms.by_variable(upscaled, default="conservative")
indexed_cells = grid_weights.create_index(source_geoms).query(
    target_geoms, methods=algorithms.unique()
)
weights = grid_weights.weights(source_geoms, target_geoms, indexed_cells)
weights

/home/runner/work/regridding-ecosystem-overview/regridding-ecosystem-overview/.pixi/envs/default/lib/python3.12/site-packages/distributed/client.py:3383: UserWarning: Sending large graph of size 12.89 MiB.
This may cause some slowdown.
Consider loading the data with Dask directly
 or using futures or delayed objects to embed the data into the graph without repetition.
See also https://docs.dask.org/en/stable/best-practices.html#load-data-with-dask for more information.
  warnings.warn(

CPU times: user 3.33 s, sys: 135 ms, total: 3.46 s
Wall time: 5.7 s

<xarray.Dataset> Size: 27GB
Dimensions:          (target_cells: 25400, source_lon: 530, source_lat: 250)
Coordinates:
  * source_lon       (source_lon) float64 4kB -160.0 -159.8 ... -30.25 -30.0
  * source_lat       (source_lat) float64 2kB 15.0 15.24 15.49 ... 75.76 76.0
  * target_cell_ids  (target_cells) uint64 203kB dask.array<chunksize=(5100,), meta=np.ndarray>
Dimensions without coordinates: target_cells
Data variables:
    conservative     (target_cells, source_lon, source_lat) float64 27GB dask.array<chunksize=(5100, 265, 125), meta=np.ndarray>
Indexes:
    target_cell_ids  HealpixIndex(level=7, indexing_scheme=nested)
Attributes: (1)

xarray.Dataset

• Dimensions:
  • target_cells: 25400
  • source_lon: 530
  • source_lat: 250
• Coordinates: (3)
  • source_lon
    (source_lon)
    float64
    -160.0 -159.8 ... -30.25 -30.0

    standard_name :

    longitude

    long_name :

    Longitude

    units :

    degrees_east

    axis :

    X

    array([-160.      , -159.754253, -159.508507, ...,  -30.491493,  -30.245747,
            -30.      ], shape=(530,))

  • source_lat
    (source_lat)
    float64
    15.0 15.24 15.49 ... 75.76 76.0

    standard_name :

    latitude

    long_name :

    Latitude

    units :

    degrees_north

    axis :

    Y

    array([15.     , 15.24498, 15.48996, ..., 75.51004, 75.75502, 76.     ],
          shape=(250,))

  • target_cell_ids
    (target_cells)
    uint64
    dask.array<chunksize=(5100,), meta=np.ndarray>

    grid_name :

    healpix

    level :

    7

    indexing_scheme :

    nested

    Array Chunk Bytes 198.44 kiB 39.84 kiB Shape (25400,) (5100,) Dask graph 5 chunks in 1 graph layer Data type uint64 numpy.ndarray

• Data variables: (1)
  • conservative
    (target_cells, source_lon, source_lat)
    float64
    dask.array<chunksize=(5100, 265, 125), meta=np.ndarray>

    Array Chunk Bytes 25.07 GiB 1.26 GiB Shape (25400, 530, 250) (5100, 265, 125) Dask graph 20 chunks in 63 graph layers Data type float64 numpy.ndarray

• Indexes: (3)
  • source_lon
    PandasIndex

    PandasIndex(Index([             -160.0, -159.75425330812857, -159.50850661625708,
            -159.2627599243856, -159.01701323251416, -158.77126654064273,
            -158.5255198487713,  -158.2797731568998, -158.03402646502832,
            -157.7882797731569,
           ...
            -32.21172022684311,  -31.96597353497168, -31.720226843100193,
           -31.474480151228704, -31.228733459357272,  -30.98298676748584,
            -30.73724007561441,  -30.49149338374292,  -30.24574669187143,
                         -30.0],
          dtype='float64', name='source_lon', length=530))

  • source_lat
    PandasIndex

    PandasIndex(Index([              15.0, 15.244979919678714,  15.48995983935743,
           15.734939759036145,  15.97991967871486, 16.224899598393574,
            16.46987951807229, 16.714859437751002,  16.95983935742972,
           17.204819277108435,
           ...
            73.79518072289156,  74.04016064257027,    74.285140562249,
            74.53012048192771,  74.77510040160642,  75.02008032128514,
            75.26506024096386,  75.51004016064257,  75.75502008032129,
                         76.0],
          dtype='float64', name='source_lat', length=250))

  • target_cell_ids
    HealpixIndex(level=7, indexing_scheme=nested)

    <xdggs.healpix.HealpixIndex object at 0x7f97f49f1370>

• Attributes: (1)

  source_dims :

  ['source_lon', 'source_lat']

%%time
regridded = algorithms.regrid(upscaled, weights)
regridded

CPU times: user 31.7 ms, sys: 977 μs, total: 32.7 ms
Wall time: 31.9 ms

<xarray.Dataset> Size: 81MB
Dimensions:   (time: 400, cells: 25400)
Coordinates:
  * cell_ids  (cells) uint64 203kB dask.array<chunksize=(5100,), meta=np.ndarray>
  * time      (time) datetime64[ns] 3kB 2013-01-01 ... 2013-04-10T18:00:00
Dimensions without coordinates: cells
Data variables:
    air       (time, cells) float64 81MB dask.array<chunksize=(20, 5100), meta=np.ndarray>
Indexes:
    cell_ids  HealpixIndex(level=7, indexing_scheme=nested)
Attributes: (5)

xarray.Dataset

• Dimensions:
  • time: 400
  • cells: 25400
• Coordinates: (2)
  • cell_ids
    (cells)
    uint64
    dask.array<chunksize=(5100,), meta=np.ndarray>

    grid_name :

    healpix

    level :

    7

    indexing_scheme :

    nested

    Array Chunk Bytes 198.44 kiB 39.84 kiB Shape (25400,) (5100,) Dask graph 5 chunks in 1 graph layer Data type uint64 numpy.ndarray

  • time
    (time)
    datetime64[ns]
    2013-01-01 ... 2013-04-10T18:00:00

    standard_name :

    time

    long_name :

    Time

    array(['2013-01-01T00:00:00.000000000', '2013-01-01T06:00:00.000000000',
           '2013-01-01T12:00:00.000000000', ..., '2013-04-10T06:00:00.000000000',
           '2013-04-10T12:00:00.000000000', '2013-04-10T18:00:00.000000000'],
          shape=(400,), dtype='datetime64[ns]')

• Data variables: (1)
  • air
    (time, cells)
    float64
    dask.array<chunksize=(20, 5100), meta=np.ndarray>

    long_name :

    4xDaily Air temperature at sigma level 995

    units :

    degK

    precision :

    2

    GRIB_id :

    11

    GRIB_name :

    TMP

    var_desc :

    Air temperature

    dataset :

    NMC Reanalysis

    level_desc :

    Surface

    statistic :

    Individual Obs

    parent_stat :

    Other

    actual_range :

    [185.16 322.1 ]

    Array Chunk Bytes 77.51 MiB 796.88 kiB Shape (400, 25400) (20, 5100) Dask graph 100 chunks in 87 graph layers Data type float64 numpy.ndarray

• Indexes: (2)
  • cell_ids
    HealpixIndex(level=7, indexing_scheme=nested)

    <xdggs.healpix.HealpixIndex object at 0x7f97f49ae9f0>

  • time
    PandasIndex

    PandasIndex(DatetimeIndex(['2013-01-01 00:00:00', '2013-01-01 06:00:00',
                   '2013-01-01 12:00:00', '2013-01-01 18:00:00',
                   '2013-01-02 00:00:00', '2013-01-02 06:00:00',
                   '2013-01-02 12:00:00', '2013-01-02 18:00:00',
                   '2013-01-03 00:00:00', '2013-01-03 06:00:00',
                   ...
                   '2013-04-08 12:00:00', '2013-04-08 18:00:00',
                   '2013-04-09 00:00:00', '2013-04-09 06:00:00',
                   '2013-04-09 12:00:00', '2013-04-09 18:00:00',
                   '2013-04-10 00:00:00', '2013-04-10 06:00:00',
                   '2013-04-10 12:00:00', '2013-04-10 18:00:00'],
                  dtype='datetime64[ns]', name='time', length=400, freq=None))

• Attributes: (5)

  Conventions :

  COARDS

  title :

  4x daily NMC reanalysis (1948)

  description :

  Data is from NMC initialized reanalysis (4x/day). These are the 0.9950 sigma level values.

  platform :

  Model

  references :

  http://www.esrl.noaa.gov/psd/data/gridded/data.ncep.reanalysis.html

%%time
computed = regridded.compute()
computed

/home/runner/work/regridding-ecosystem-overview/regridding-ecosystem-overview/.pixi/envs/default/lib/python3.12/site-packages/distributed/client.py:3383: UserWarning: Sending large graph of size 16.22 MiB.
This may cause some slowdown.
Consider loading the data with Dask directly
 or using futures or delayed objects to embed the data into the graph without repetition.
See also https://docs.dask.org/en/stable/best-practices.html#load-data-with-dask for more information.
  warnings.warn(

CPU times: user 6.72 s, sys: 320 ms, total: 7.04 s
Wall time: 22.9 s

<xarray.Dataset> Size: 81MB
Dimensions:   (time: 400, cells: 25400)
Coordinates:
  * cell_ids  (cells) uint64 203kB 33629 33630 33631 ... 131069 131070 131071
  * time      (time) datetime64[ns] 3kB 2013-01-01 ... 2013-04-10T18:00:00
Dimensions without coordinates: cells
Data variables:
    air       (time, cells) float64 81MB 294.9 295.0 294.7 ... 288.9 288.4 286.9
Indexes:
    cell_ids  HealpixIndex(level=7, indexing_scheme=nested)
Attributes: (5)

xarray.Dataset

• Dimensions:
  • time: 400
  • cells: 25400
• Coordinates: (2)
  • cell_ids
    (cells)
    uint64
    33629 33630 33631 ... 131070 131071

    grid_name :

    healpix

    level :

    7

    indexing_scheme :

    nested

    array([ 33629,  33630,  33631, ..., 131069, 131070, 131071],
          shape=(25400,), dtype=uint64)

  • time
    (time)
    datetime64[ns]
    2013-01-01 ... 2013-04-10T18:00:00

    standard_name :

    time

    long_name :

    Time

    array(['2013-01-01T00:00:00.000000000', '2013-01-01T06:00:00.000000000',
           '2013-01-01T12:00:00.000000000', ..., '2013-04-10T06:00:00.000000000',
           '2013-04-10T12:00:00.000000000', '2013-04-10T18:00:00.000000000'],
          shape=(400,), dtype='datetime64[ns]')

• Data variables: (1)
  • air
    (time, cells)
    float64
    294.9 295.0 294.7 ... 288.4 286.9

    long_name :

    4xDaily Air temperature at sigma level 995

    units :

    degK

    precision :

    2

    GRIB_id :

    11

    GRIB_name :

    TMP

    var_desc :

    Air temperature

    dataset :

    NMC Reanalysis

    level_desc :

    Surface

    statistic :

    Individual Obs

    parent_stat :

    Other

    actual_range :

    [185.16 322.1 ]

    array([[294.9412305 , 295.00101231, 294.71774912, ..., 269.42707554,
            268.81954532, 268.02878478],
           [295.12782896, 295.15806036, 294.90695285, ..., 265.06073882,
            264.4017425 , 263.36126139],
           [294.77256114, 294.7199228 , 294.49422394, ..., 260.42605338,
            259.72163198, 259.14633728],
           ...,
           [295.78893843, 295.9341553 , 295.62583661, ..., 286.27145934,
            286.31478493, 284.5352808 ],
           [295.0501987 , 295.1379342 , 294.817473  , ..., 287.08690091,
            286.83070332, 285.15925723],
           [295.4012504 , 295.40234008, 295.13013297, ..., 288.8550473 ,
            288.40162839, 286.8644898 ]], shape=(400, 25400))

• Indexes: (2)
  • cell_ids
    HealpixIndex(level=7, indexing_scheme=nested)

    <xdggs.healpix.HealpixIndex object at 0x7f97f49af350>

  • time
    PandasIndex

    PandasIndex(DatetimeIndex(['2013-01-01 00:00:00', '2013-01-01 06:00:00',
                   '2013-01-01 12:00:00', '2013-01-01 18:00:00',
                   '2013-01-02 00:00:00', '2013-01-02 06:00:00',
                   '2013-01-02 12:00:00', '2013-01-02 18:00:00',
                   '2013-01-03 00:00:00', '2013-01-03 06:00:00',
                   ...
                   '2013-04-08 12:00:00', '2013-04-08 18:00:00',
                   '2013-04-09 00:00:00', '2013-04-09 06:00:00',
                   '2013-04-09 12:00:00', '2013-04-09 18:00:00',
                   '2013-04-10 00:00:00', '2013-04-10 06:00:00',
                   '2013-04-10 12:00:00', '2013-04-10 18:00:00'],
                  dtype='datetime64[ns]', name='time', length=400, freq=None))

• Attributes: (5)

  Conventions :

  COARDS

  title :

  4x daily NMC reanalysis (1948)

  description :

  Data is from NMC initialized reanalysis (4x/day). These are the 0.9950 sigma level values.

  platform :

  Model

  references :

  http://www.esrl.noaa.gov/psd/data/gridded/data.ncep.reanalysis.html

computed["air"].dggs.explore(alpha=0.8)