ESA WorldCover

Date modified: 02 February 2022

Product Overview


The ESA WorldCover product is a freely accessible global land cover map at 10m resolution for the year 2020, based on both Sentinel-1 and Sentinel-2 data. The discrete classification map provides 11 land cover/land use classes and is defined using the Land Cover Classification System (LCCS) developed by the United Nations (UN) Food and Agricultre Organization (FAO).

Digital Earth Africa provides free and open access to a copy of the ESA WorldCover 10m 2020 product over Africa. For more information on the ESA WorldCover product, see the ESA WorldCover website and the Product User Manual.

A Jupyter Notebook which demonstrates loading and using landcover datasets in the Sandbox is also available.


Spatial and temporal coverage

Relevant metadata for the ESA WorldCover product can be viewed on the DE Africa Metadata Explorer.

Table 1: ESA WorldCover product specifications


Product name


Cell size - X (degrees)

0.000083° (~10m)

Cell size - Y (degrees)

0.000083° (~10m)

Coordinate reference system


Temporal resolution


Temporal range


Update frequency


The specific temporal and geographic extents for the product can be explored as an interactive map on the Metadata Explorer. Data is available for the region shaded in blue.

Figure 1: ESA WorldCover product geographic extent

ESA WorldCover Geographic Extent


Table 2: ESA WorldCover product measurements

Band ID



Data type

No data\(^\dagger\)


Land cover classification





The ESA WorldCover global land cover product was generated using both Sentinel-2 multi-spectral imagery and Sentinel-1 C-band Synthetic Aperture Radar (SAR) imagery. The algorithm used to generate the product is based on the algorithm used to produce the dynamic annual Copernicus Global Land Service Land Cover map at 100m resolution (CGLS_LC100m). A summary of the algorithm is presented in the Product User Manual.

Media and example images

Figure 2: ESA WorldCover 2020 land cover classification data for Madagascar

ESA Worldcover Madagascar 2020

© ESA WorldCover project 2020 / Contains modified Copernicus Sentinel data (2020) processed by ESA WorldCover consortium


Zanaga, D., Van De Kerchove, R., De Keersmaecker, W., Souverijns, N., Brockmann, C., Quast, R., Wevers, J., Grosu, A., Paccini, A., Vergnaud, S., Cartus, O., Santoro, M., Fritz, S., Georgieva, I., Lesiv, M., Carter, S., Herold, M., Li, Linlin, Tsendbazar, N.E., Ramoino, F., Arino, O., 2021. ESA WorldCover 10 m 2020 v100.

License and Acknowledgements

The ESA WorldCover product is provided free of charge, without restriction of use. For the full license information see the Creative Commons Attribution 4.0 International License.

Data Acess

Amazon Web Service

The ESA WorldCover 10m 2020 product is avaliable in AWS S3.

Table 3: AWS data acess details.

AWS S3 details

Bucket ARD




The products are hosted on the esa-worldcover S3 bucket in the AWS eu-central-1 region.

The file paths follow the format:

OGC Web Services (OWS)

The ESA WorldCover 10m 2020 product esa_worldcover is available through the Digital Earth Africa’s OWS.

Table 4: OWS data access details.

OWS details


DE Africa Services

Web Map Services (WMS) URL

Web Coverage Service (WCS) URL

Layer name


Digital Earth Africa OWS details can be found at

For instructions on how to connect to OWS, see this tutorial.

Open Data Cube (ODC)

The ESA WorldCover product can be accessed through the Digital Earth Africa ODC API, which is available through the Digital Earth Africa Sandbox.

ODC product name: esa_worldcover

The esa_worldcover product has only one specific band of data which can be called by using the default name, classification, as listed in the table below. ODC Datacube.load commands without specified bands will load the classification band.

Table 5: ODC product esa_worldcover band names.

Band name

Alternative names

Fill value




Technical information

The ESA WorldCover product was independently validated with a global overall accuracy of 74.4% ±0.1% for 2020 and a continental level accuracy of 73.6% ±0.2% for Africa. In terms of land cover types, tree cover and snow/ice, cropland, water body, and bare/sparse vegetation classes had high accuracies, while shrubs, herbaceous wetland, and moss/lichen classes were mapped with lower accuracies. The validation dataset used was the multi-purpose Global Land Cover Validation dataset developed for Copernicus Global Land Service- Land Cover 100 product which was updated for the reference year 2020 by revisiting random and targeted (for land cover change) subsets.

A detailed explanation of the validation results of the ESA WorldCover 10m 2020 product is presented in the Product Validation Report.