Earth Data School
About
Full catalog/LULC_Nigeria_Ethiopia_SAfrica_2367
LULC_Nigeria_Ethiopia_SAfrica_2367·v1·dataset

Yearly land use and city growth in three African nations

Annual Land Use and Urban Land Cover: Ethiopia, Nigeria, and South Africa, 2016-2020
land NASA ORNL_CLOUD Level 4 COG
In plain English

What it measures. Yearly maps of land use and urban land cover for Ethiopia, Nigeria, and South Africa from 2016 to 2020, including 30-meter land-use maps and finer 10-meter maps of city areas.

How it's made. Created with machine-learning (Random Forest) models trained on reference data, using Landsat imagery for the broad land-use maps and Sentinel-2 imagery for the detailed urban maps, plus climate, terrain, and other data.

How & where you'd use it. Useful for tracking how cities are growing and how land is being used across these countries, with reported accuracy of roughly 60-80%. Delivered as GeoTIFF files.

What's measured

LAND SURFACE › LAND USE/LAND COVER › LAND USE/LAND COVER CLASSIFICATIONHUMAN DIMENSIONS › ENVIRONMENTAL GOVERNANCE/MANAGEMENT › LAND MANAGEMENT › LAND USE/LAND COVER CLASSIFICATIONBIOSPHERE › ECOSYSTEMS › ANTHROPOGENIC/HUMAN INFLUENCED ECOSYSTEMS › URBAN LANDS

Coverage & cadence

  • Time span2016-01-01 → 2020-12-31
  • Measured byLANDSAT (ETM+, OLI) · Sentinel-1A (SENTINEL-1 C-SAR) · Sentinel-2A (Sentinel-2 MSI)
  • Processing levelLevel 4
  • Spatial extent2.5725, -35.3369, 49.6875, 16.2061
  • FormatsCOG
  • StatusCOMPLETE

What you can do with it

  • Track deforestation, fire scars and land-cover change
  • Monitor crop and vegetation health (NDVI/EVI)
  • Map how built-up vs. green an area is over time
Official description

This dataset provides a two-tier annual Land Use (LU) and Urban Land Cover (LC) product suite over three African countries, Ethiopia, Nigeria, and South Africa, across a 5-year period of 2016-2020. Remote sensing data sources were used to create 30-m resolution LU maps (Tier-1), which were then utilized to delineate urban boundaries for 10-m resolution LC classes (Tier-2). Random Forest machine learning classifier models were trained on reference data for each tier and country (but one model was trained across all years); models were validated using a separate reference data set for each tier and country. Tier-1 LU maps were based on the 30-m Landsat time series, and Tier-2 urban LC maps were based on the 10-m Sentinel-2 time series. Additional data sources included climate, topography, night-time light, and soils. The overall map accuracy was 65-80% for Tier-1 maps and 60-80% for Tier-2 maps, depending on the year and country. The data are provided in cloud optimized GeoTIFF (COG) format.

Get the data

lulc_nigeria_ethiopia_safrica_2367_access.py
import earthaccess
earthaccess.login(strategy="netrc")          # free Earthdata Login

results = earthaccess.search_data(
    short_name="LULC_Nigeria_Ethiopia_SAfrica_2367",
    version="1",
    bounding_box=(-122.5, 37.2, -121.8, 37.9),  # your area (W,S,E,N)
    temporal=("2024-01-01", "2024-12-31"),       # your dates
)
files = earthaccess.open(results)   # stream straight from ORNL_CLOUD
Browsing CMR needs no login. Downloading or streaming bytes needs a free Earthdata Login + the earthaccess package.