geospatial-machine-learning

Why we included this project

Anyone getting started with deep learning on satellite or aerial imagery will find this curated index a quick way to get oriented, since it pulls together code projects, datasets, papers, books, and courses that would otherwise take hours of searching to collect. Entries cover semantic segmentation, object detection, and land-cover classification, and each one is annotated with its author and source, which makes it easy to tell a hands-on tutorial from a research paper at a glance. Datasets like SpaceNet and DeepSat are listed too, so the collection doubles as a starting point for finding labeled imagery to train on. One honest caveat: the list was last updated in 2018, so the material skews older, but for a field that moves fast it still works well as a reading list and bibliography for teams evaluating approaches. It is a discovery resource rather than something you deploy, and for that purpose it does the job.