The national-scale wheat area dataset of Ethiopia for the 2020/21 rainfed cropping seasons shows the spatial distribution and density of rainfed wheat at 10 m spatial resolution for the 2020 Belg and 2020/21 Meher seasons at the national scale. The binary dataset depicts whether a pixel is classified as wheat or non-wheat (labeled as "1" and "0", respectively) during the period ranging from April to December 2020.
For datatset generation, state-of-the-art, efficient satellite data pre-processing, in-depth in situ data cleaning, and Random Forest classification methods have been applied to a multispectral, gap-filled Sentinel-2 satellite time series from April to December 2020 and the multi-source Ethiopian Crop Type 2020 (EthCT2020) ground reference dataset (Blasch et al., 2024).
This dataset with a classification overall accuracy of 80% was developed with the goal to complement the Ethiopian Wheat Rust Early Warning and Advisory System’s baseline data for the disease dispersal and environmentally suitability forecast models as well as building the basis for new information layers regarding the host susceptibility.
Overall, the dataset can serve as a baseline input parameter for crop models, climate models, crop disease and pest surveillance and forecasting, and agricultural monitoring in the smallholder cropping systems of Ethiopia.
