AndalUnmixingRGB: A dataset of Sentinel-2 Digital RGB imagery acquired in Andalusia region of Spain, enriched with environmental ancillary data and annotated for blind Spectral Unmixing using Deep Learning (License CC BY 4.0)

AndalUnmixingRGB is a Sentinel-2 satellite digital RGB imagery enriched with environmental ancillary data and designed for blind spectral unmixing using deep learning. Generally, spectral unmixing involves two main tasks: spectral signature identification of different available land use/cover types in the analyzed hyperspectral or multispectral imagery (endmember identification task) and their respective proportions measurement (abundance estimation task). However, hyperspectral or multispectral images are more expensive, harder to obtain and require more processing effort than their RGB counterpart. To overcome this need, we introduce this dataset, which constitutes to our knowledge the first deep-learning-ready dataset allowing to elaborate spectral unmixing objectives using affordable RGB imagery enriched with its environmental ancillary data without the need to extract hyperspectral or multispectral data. The v1.0 of this dataset contains 21,489 images in JPEG format corresponding to unique 2240x2240m2 tiles covering all the region of Andalusia in Spain. In fact, Each image has 224 x 224 pixels at 10m spatial resolution and was produced by assigning the 25th percentile of all available observations in the Sentinel-2 collection between June 2015 and October 2020 with the aim to diminish atmospheric effects (i.e., clouds, aerosols, shadows, snow, etc.). Each image in this dataset contains land use/cover types abundance values within its corresponding tile at two different annotation levels (N1 and N2), in addition to topographic and climatic ancillary data gathered inside that same area.