Mapping human settlements with Sentinel-2 imagery and deep neural networks.

Abstract

This paper explores the potential of multi-spectral Sentinel-2 imagery for human settlement mapping, using deep learning based methods. We show first results of a study area in central Europe, with an attention-based ResNeXt to better exploit the spectral information. Reasonable mapping accuracy has been achieved, compared to the state-of-the-art products. Based on the results and comparison with the existing products, we discuss two interesting questions: how can human settlement mapping be made consistent with or complementary to the existing human settlement maps and how can further improvement in human settlement mapping be achieved by exploring deep learning-based approaches?