Load ARCO-ERA5 data from Google Cloud

load_era5.py

# Loads cloud-friendly Zarr format Analysis-Ready, Cloud Optimized ERA5 data from Google Cloud.
# Available: https://github.com/google-research/arco-era5


import xarray
import gcsfs
import odc.geo.xr
from odc.geo.geom import BoundingBox

def load_era5(
    x=None,
    y=None,
    crs="EPSG:4326",
    time=None,
    bands=None,
    chunks=None,
    path="gs://gcp-public-data-arco-era5/ar/full_37-1h-0p25deg-chunk-1.zarr-v3",
):
    # Lazily load Zarr from Google Cloud Platform
    era5_ds = xarray.open_zarr(path, chunks=chunks, storage_options=dict(token="anon"))

    # Select bands
    era5_ds = era5_ds[bands] if bands is not None else era5_ds

    # Clip to extent
    if x is not None:
        bbox = BoundingBox.from_xy(x, y, crs=crs).to_crs("EPSG:4326")
        era5_ds = era5_ds.sel(
            longitude=slice(bbox.left, bbox.right),
            latitude=slice(bbox.top, bbox.bottom),
        )
        
    # Select time
    if time is not None:
        era5_ds = era5_ds.sel(time=slice(time[0], time[-1]))

    return era5_ds.odc.assign_crs("EPSG:4326")


# Lazily load Zarr from Google Cloud Platform to inspect data
era5_ds = xarray.open_zarr(
    "gs://gcp-public-data-arco-era5/ar/full_37-1h-0p25deg-chunk-1.zarr-v3",
    chunks=None,
    storage_options=dict(token="anon"))
era5_ds

# Load a small portion and time period
x = (100, 150)
y = (0, -50)
time = ("2024-05-01", "2024-05-02")

era5_subset_ds = load_era5(
    x=x,
    y=y,
    crs="EPSG:4326",
    time=time,
    bands=["temperature"],
    path="gs://gcp-public-data-arco-era5/ar/full_37-1h-0p25deg-chunk-1.zarr-v3",
)
era5_subset_ds

# Animate
# pip install dea-tools
from dea_tools.plotting import xr_animation

xr_animation(
    era5_subset_ds,
    bands=["total_precipitation"],
    imshow_kwargs={"cmap": "viridis"},
    interval=50,
)

animation.2.mp4