Mapping Crop Types and Cropping Systems in Nigeria with Sentinel-2 Imagery

Reliable crop type maps from satellite data are an essential prerequisite for quantifying growth, health, and yields. However, such do not exist most parts of Africa, where smallholder farming is the dominant system. Prevalent cloud cover, small farm sizes, mixed cropping systems pose substantial challenges when creating sub-Saharan Africa. In this study, we provide a mapping scheme based on freely available Sentinel-2A/B (S2) time series very high-resolution SkySat to map main crops—maize potato—and intercropping including these two crops Jos Plateau, Nigeria. We analyzed spectral-temporal behavior classes improve our understanding inter-class spectral mixing. Building Framework Operational Radiometric Correction Environmental monitoring (FORCE), preprocessed S2 derived metrics bands temporal windows. These STMs were used as input features in hierarchical random forest classification. Our results first wall-to-wall key agricultural region cropland identification had overall accuracy 84%, while achieved average 72% five relevant classes. shows distinctive regional variations distribution types. Maize crop, followed by systems, maize–cereals potato–maize cropping; potato was found be least prevalent class. Plot analyses sample 1166 fields revealed largely homogeneous patterns, demonstrating effectiveness classification system also intercropped classes, which temporally spatially highly heterogeneous. Moreover, that field sizes all types, regardless whether or used. Maize–legume maize exhibited largest plots, with area up 3 ha slightly more than 10 ha, respectively; mainly cultivated smaller 0.5 only few plots larger 1 ha. Besides providing explicit practices core production Nigeria, study offers guidance creation smallholder-dominated intercropping. Critical windows differentiation will enable approaches support future smart aspects food security, early warning policies, extension services.