Query open satellite data

Tilebox indexes searchable metadata for public Earth observation catalogs. Use metadata queries to find relevant observations before reading or downloading their image assets.

Prerequisites

• You have a Tilebox API key.
• You have installed the Python SDK.

uv add tilebox shapely

Copy

Select the Sentinel-2 catalog

Open the Sentinel-2 dataset and its Level-2A collection:

Python

from tilebox.datasets import Client, field

client = Client()
sentinel2 = client.dataset("open_data.aws_earth.sentinel2")
collection = sentinel2.collection("L2A")

Copy

You can browse other open datasets and inspect their schemas in the Tilebox Console.

Query observation metadata

Query by time and area of interest. The result contains metadata and asset references, but does not download image bytes.

Python

from shapely import box

area = box(-109.05, 37.0, -102.05, 41.0)

scenes = collection.query(
    temporal_extent=("2025-10-01", "2025-11-01"),
    spatial_extent=area,
    filter=field("cloud_cover") < 10,
    show_progress=True,
)

print(scenes[["stac_id", "cloud_cover", "platform"]])

Copy

The result is an xarray.Dataset. Use regular xarray operations to sort or select observations:

Python

latest = scenes.sortby("time").isel(time=-1)

print(latest.stac_id.item())
print(latest.cloud_cover.item())

Copy

Next steps

Create a Sentinel-2 RGB image

Read three COG windows and combine them into an RGB image.

Querying data

Learn more dataset query patterns.