DeepSatData: Building large scale datasets of satellite images for training machine learning models

This paper presents DeepSatData a free and open source pipeline for automatically generating satellite imagery datasets for training machine learning models. The implementation presented can be used to query, download and process freely available Sentinel-2 data for the generation of large scale datasets required for training deep neural networks (DNN). We discuss design considerations faced from the point of view of DNN training and evaluation such as checking the quality of ground truth data and assessing the scalability of the approach. Accompanying code is made publicly available in https://github.com/michaeltrs/DeepSatData.