Land Use Land Cover

Two-class Land Use Land Cover

---

What is the "Land Use Land Cover" layer?

The Land Use Land Cover layer is a simple 2-class lulc product reporting the presence of vegetation and water from annual composites of Sentinel 2 imagery. It’s core advantages include:
(1) the speed of computation (single-scan through the raster space)
(2) the unsupervised nature of its computation (no training data needed)
(3) the lack of generalization; i.e. each pixel is classified individually and is not aggregated spatially.

The layer is available for the five focus countries in East Africa for the Rockefeller Foundation's Interconnected Pathways to Development (RF IPD) project.

What is the spatial and temporal resolution of the Land Use Land Cover layer?

Temporal Extent	2021
Temporal Resolution	Annual
Spatial Coverage	RF IPD Focus Countries (Rwanda, Uganda, Nigeria, Ethiopia and Kenya)
Spatial Resolution	10m x 10m

We produce the Cropland layer for for 2021. Datasets are available in raster format (.tif) at a maximum spatial resolution of 10 m x 10 m in a systematic grid.

What are the units of measurement for Land Use Land Cover?

The Land Use Land Cover dataset is a 3-band raster with water, vegetation, and everything else.

How do we estimate Land Use Land Cover at a 10m resolution?

The method builds internal rules based on the radiometric signatures of self-identified water & vegetation-covered regions and uses these for pixel-based classification of the test image.

What are the main data sources we use?

We use the following publicly available data sources for model inputs, ground truthing, and model calibration. The primary input data for the cropland layer comes from Sentinel-2 annual composite.

If you have any questions, please reach out to RF IPD Project Manager, Emily Logan