The DeepCube Africa Minicubes dataset has been desinged for prototyping models for forecasting drought impacts in Africa. It pairs high resolution remotely sensed spectral bands with weather observations into sparsely sampled minicubes of 3.84x3.84Km. Deep Cube Forecasting Drought and Heat Impacts in Africa: Questions to be tackled using this dataset Can we predict localized impacts of meteorological drought and heat waves in sub-Saharan Africa based on multivariate Earth Observation and meteorological historical data analysis? What are the anticipated long-term effects of drought and heat, i.e. memory and lag effects? The data is shaped into minicubes in order to facilitate the training of deep learning spatio-temporal models that make use of both spatial and temporal dependencies (convolutions and recurrency, e.g., video prediction models). This release contains 2.859 demonstrator minicubes out of a parent set of 50.000 cubes that have been smart sampled in the African continent. Find more on DeepCube data cubes