Agriculture
Probability of cropland
What is the "Cropland" layer?
The Cropland layer estimates the probability of cropland at scale.
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 Cropland layer?
| Temporal Extent | 2016 - 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 every year from 2016 to 2021, inclusive. 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 Cropland?
Probabilty of cropland (0-100)
How do we estimate Cropland at a 10m resolution?
The cropland maps were created by combining various earth observation (EO) datasets with land cover type labels in order to train a random forest model that predicts the probability that a pixel is cropped or not. The EO data sources used to create independent variables were Sentinel-2 for multispectral reflectances (10 m resolution) and Shuttle Radar Topography Mission (30 m resolution) for topography features, including elevation, slope, and aspect.
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 for multispectral reflectances (10 m resolution) and Shuttle Radar Topography Mission (30 m resolution) for topography features, including elevation, slope, and aspect.
If you have any questions, please reach out to RF IPD Project Manager, Emily Logan