AWS S3

This example demonstrates how to use the Earth Data Kit to stitch together a collection of S3 files.

import earth_data_kit as edk
import geopandas as gpd
import datetime

# Initialize the Dataset using the S3 engine.
dataset_id = "example_s3_dataset"
# Replace the bucket name and path with your actual S3 location.
source = "s3://your-bucket-name/path/to/data"
engine = "s3"

ds = edk.stitching.Dataset(dataset_id, source, engine)

# Set the temporal bounds for the dataset (e.g., using January 2017 as an example)
start_date = datetime.datetime(2017, 1, 1)
end_date = datetime.datetime(2017, 1, 31)
ds.set_timebounds(start_date, end_date)

# Define the spatial bounding box (min_lon, min_lat, max_lon, max_lat)
bbox = (19.3044861183, 39.624997667, 21.0200403175, 42.6882473822)
# Specify the grid file that maps the dataset's grid system (e.g., a KML file)
grid_file = "path/to/grid/file.kml"
grid_df = gpd.read_file(grid_file)

ds.set_spacebounds(bbox, grid_df)

# Discover the available scene files within the defined spatial and temporal bounds.
ds.discover()

# Retrieve and display the list of available bands from the dataset.
available_bands = ds.get_bands()
print("Discovered bands:", available_bands)

# Optionally, configure GDAL options (e.g., setting the target spatial reference).
ds.set_target_options({
    "-t_srs": "EPSG:3857",
})

# Define the ordered list of band descriptions you wish to stitch together.
bands = ["red", "green", "blue"]

# Create the stitched VRTs from the provided S3 data.
ds.mosaic(bands)

# This returns a dataarray with the stitched bands
da = ds.to_dataarray()