SEN12MS -- A Curated Dataset of Georeferenced Multi-Spectral Sentinel-1/2 Imagery for Deep Learning and Data Fusion
This dataset addresses a data bottleneck for researchers in remote sensing and geoinformatics, enabling more robust deep learning models for tasks like scene classification and land cover mapping, though it is incremental as it builds on existing satellite data.
The authors tackled the lack of large-scale, diverse training data for deep learning in remote sensing by creating SEN12MS, a curated dataset of 180,662 georeferenced multi-spectral image triplets from Sentinel-1/2 and MODIS, covering all inhabited continents and seasons.
The availability of curated large-scale training data is a crucial factor for the development of well-generalizing deep learning methods for the extraction of geoinformation from multi-sensor remote sensing imagery. While quite some datasets have already been published by the community, most of them suffer from rather strong limitations, e.g. regarding spatial coverage, diversity or simply number of available samples. Exploiting the freely available data acquired by the Sentinel satellites of the Copernicus program implemented by the European Space Agency, as well as the cloud computing facilities of Google Earth Engine, we provide a dataset consisting of 180,662 triplets of dual-pol synthetic aperture radar (SAR) image patches, multi-spectral Sentinel-2 image patches, and MODIS land cover maps. With all patches being fully georeferenced at a 10 m ground sampling distance and covering all inhabited continents during all meteorological seasons, we expect the dataset to support the community in developing sophisticated deep learning-based approaches for common tasks such as scene classification or semantic segmentation for land cover mapping.