# ESA WorldCover 10 m 2021 Global Land Cover Map, Version 200 (v200)

## Facts

- Provider: European Space Agency (ESA) WorldCover consortium
- License: CC-BY-4.0 (https://esa-worldcover.org/en/data-access)
- Stored at: Amazon S3, s3://esa-worldcover/v200 (eu-central-1)
- Access: public, readable without an account
- DOI: https://doi.org/10.5281/zenodo.7254221
- Category: Earth Observation & Geospatial
- Source: https://doi.org/10.5281/zenodo.7254221
- Page: https://scigantic.com/archive/5abe8a55-debc-546d-ae11-f55fc6976a7e
- Keywords: Earth Observation & Geospatial, image segmentation, satellite imagery, AWS Open Data

## About

The second ESA WorldCover release: a global 10 m land cover map for 2021 (version 200), produced from Sentinel-1 radar and Sentinel-2 optical data by the ESA WorldCover consortium. It keeps the 11-class legend of the 2020 map; overall accuracy reported by ESA rises to 76.7 percent. Tiles are 3 by 3 degree Cloud Optimized GeoTIFFs in EPSG:4326 under v200/2021/, with a Map layer and an InputQuality layer per tile. The 2020 v100 map is the sibling folder v100/; the two are separate versions, so differences between them can mix real change with method change. Used as a reference land cover layer for biodiversity, carbon, agriculture and hydrology models and as training or validation labels for Sentinel-2 segmentation. Cite ESA WorldCover 10 m 2021 v200, doi:10.5281/zenodo.7254221. Read with rioxarray or GDAL (/vsis3/ with AWS_NO_SIGN_REQUEST=YES); a tile grid is at the bucket root (esa_worldcover_grid.geojson / .fgb). Bucket region eu-central-1. Licensed CC BY 4.0 by ESA; attribution '© ESA WorldCover project / Contains modified Copernicus Sentinel data processed by ESA WorldCover consortium'.

## Load the data

```python
import boto3
from botocore import UNSIGNED
from botocore.client import Config
s3 = boto3.client('s3', region_name='eu-central-1', config=Config(signature_version=UNSIGNED))
s3.list_objects_v2(Bucket='esa-worldcover', Prefix='v200/', Delimiter='/')
```

Lists the files with anonymous access. Runs on any machine, with no cloud account.

## Data structure

Example file: `v200/2021/docs/`

Path pattern: `{id}/{YYYY}/{seg2}/{object}`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/5abe8a55-debc-546d-ae11-f55fc6976a7e
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/5abe8a55-debc-546d-ae11-f55fc6976a7e
- Over MCP: `get_schema_card` with id `5abe8a55-debc-546d-ae11-f55fc6976a7e` at https://api.scigantic.com/mcp

## Related topics

- [Earth Observation & Geospatial datasets](https://scigantic.com/topics/earth-observation-and-geospatial)
- [Satellite imagery datasets](https://scigantic.com/topics/satellite-imagery)
- [Image segmentation datasets](https://scigantic.com/topics/image-segmentation)
