In this paper, we present the DeepStat framework that aims to simplify the use of deep learning and remote sensing data for official statistics. While already a large body of research has been done in the remote sensing community, remote sensing data has not found widespread adoption in official statistics. In a large part, this can be explained by the remote sensing data itself that needs new ways of data processing. The DeepStat framework supports statistical researchers through the use of remote sensing, so that they can focus on the creation of new statistical products based on remote sensing data.