AndalUnmixingRGB: A dataset of Sentinel-2 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.

AndalUnmixingRGB 数据集为一款经环境辅助数据增强的 Sentinel-2 卫星数字 RGB 图像集，旨在利用深度学习技术实现盲光谱解混。通常，光谱解混包括两个主要任务：在分析的高光谱或多光谱图像中识别不同可用的土地利用/覆盖类型的光谱特征（端元识别任务）以及测量其相应比例（丰度估计任务）。然而，高光谱或多光谱图像相较于其 RGB 对应物，成本更高、获取难度更大，且需要更多的处理工作量。为解决这一需求，我们推出了该数据集，据我们所知，这是首个深度学习准备就绪的数据集，允许用户利用经济实惠的 RGB 图像及其环境辅助数据来制定光谱解混目标，无需提取高光谱或多光谱数据。本数据集的 v1.0 版本包含 21,489 张 JPEG 格式的图像，对应于覆盖西班牙安达卢西亚地区所有区域的 2240x2240m2 独立瓦片。实际上，每张图像具有 224 x 224 像素，空间分辨率为 10m，通过分配 Sentinel-2 数据集中 2015 年 6 月至 2020 年 10 月所有可用观测值的第 25 百分位数来生成，旨在减少大气影响（即云层、气溶胶、阴影、积雪等）。本数据集中的每张图像在其相应瓦片内包含土地利用/覆盖类型的丰度值，在两个不同的标注级别（N1 和 N2）上，此外还包含了该区域内收集的地形和气候辅助数据。