Digital Earth Africa Sentinel-2 Rolling Three-Month Geomedian (GeoMAD), 10 m
- Provider
- Digital Earth Africa
- License
- CC-BY-4.0 (source)
- Format
- JSON, TIFF (in sampled files)
- Stored at
- Amazon S3, s3://deafrica-services/gm_s2_rolling (af-south-1)
- Access
- Free and public. No account with the data provider is needed.
- Category
- Earth Observation & Geospatial
- Source
- https://docs.digitalearthafrica.org/en/latest/data_specs/GeoMAD_specs.html
About Digital Earth Africa Sentinel-2 Rolling Three-Month Geomedian (GeoMAD), 10 m
Cloud-free Sentinel-2 surface reflectance composites of Africa summarised over rolling three-month windows that start on the first day of every month (Jan-Mar, Feb-Apr, Mar-May and so on), so a new composite appears each month. Built by Digital Earth Africa from Sentinel-2 Level-2A with the geometric median (geomedian) plus three median absolute deviations (GeoMAD): 10 spectral bands (B02 to B08, B8A, B11, B12) at 10 m, Euclidean (EMAD), spectral (SMAD) and Bray-Curtis (BCMAD) deviations, and a COUNT of clear observations, in EPSG:6933. It complements the annual and semiannual GeoMAD products when crop calendars, wet and dry seasons or flood events need sub-annual resolution. Checked 2026-11-17: the DE Africa STAC collection gm_s2_rolling lists 409,328 items from January 2019; files are Cloud Optimized GeoTIFFs at gm_s2_rolling/ /x /y / --P3M/, one per band. Load with odc-stac via https://explorer.digitalearth.africa/stac or datacube.load in the DE Africa Sandbox. Bucket region af-south-1. Licensed CC BY 4.0 by Digital Earth Africa; credit contains modified Copernicus Sentinel data processed by Digital Earth Africa.
How to access this dataset in Python
import boto3
from botocore import UNSIGNED
from botocore.client import Config
s3 = boto3.client('s3', region_name='af-south-1', config=Config(signature_version=UNSIGNED))
s3.list_objects_v2(Bucket='deafrica-services', Prefix='gm_s2_rolling/', Delimiter='/')Lists the files with anonymous access. Runs on any machine, with no cloud account.
Data structure
File types in sampled files: JSON, TIFF
Files
Example file: gm_s2_rolling/0-0-1/x153/y097/2025-11--P3M/gm_s2_rolling_x153y097_2025-11--P3M.sha1
Analyze this dataset without downloading it
On Scigantic, Digital Earth Africa Sentinel-2 Rolling Three-Month Geomedian (GeoMAD), 10 m opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.
This page is also available as Markdown and as JSON.
Related Earth Observation & Geospatial datasets
- NASA / USGS Europa Controlled Observation Mosaics
- DOE Open Energy Data Initiative: NREL's Annual Technology Baseline (ATB)
- JMA Himawari-8/9
- NREL Wind Integration National Dataset
- MODIS/Terra Surface Reflectance Daily L2G Global 250m SIN Grid V061
- Global Risk/Resilience Index - Supporting Data
- MMFlood: Multimodal Dataset for Flood Delineation from Satellite Imagery
- NASA PACE-PAX Project