Remote Sensing for large-scale agricultural investment areas in Ethiopia – agricultural monitoring based on Earth observation time-series

Ethiopia is known to be currently food insecure and suffering from considerable food deficits. The Government of Ethiopia strives to increase the agricultural production and its efficiency. Therefore, Ethiopia has been promoting large-scale agricultural investment (LSAI) to transform the agricultural sector. However, the progress by agricultural development has been limited. Investors only developed a small fraction of the transferred land. Therefore, there is a great need for monitoring of the implementation and actual state of land use of every LSAI project. The use of remote sensing can substantially support agricultural monitoring. In this study, Earth observation time series are analyzed to examine the land used for agricultural production and to differentiate crop types grown within the three study areas. Current land use/land cover (LULC) is analyzed using Sentinel-2 time series to identify cropland areas. In a second step, remote-sensing time-series of Sentinel-1 and Sentinel-2 are used to differentiate among 20 different crop types grown in the region. The developed classification methods have been applied to derive information products for three study regions in Ethiopia including the LSAI areas within the provinces of Amhara, Benishangul, and Gambella. The methods and derived information products on LULC and crop types will be made available to GIZ and regional experts to support agricultural monitoring of developed land in Ethiopia.