SSL4EO-S12: A Large-scale Multimodal Multitemporal Dataset for Self-supervised Learning in Earth Observation

The SSL4EO-S12 dataset is a large-scale dataset for unsupervised/self-supervised pre-training in Earth observation. The dataset consists of unlabeled patch triplets (Sentinel-1 dual-pol SAR, Sentinel-2 top-of-atmosphere multispectral, Sentinel-2 surface reflectance multispectral) from 251079 locations across the globe, each patch covering 2640mx2640m and including four seasonal time stamps. The raw dataset is provided in GeoTiff format, with each band being one single file.

SSL4EO-S12 数据集是一款面向地球观测领域的大规模无监督/自监督预训练数据集。该数据集包含来自全球251079个采样点位的未标注图像块三元组，具体涵盖哨兵一号（Sentinel-1）双极化合成孔径雷达（SAR）图像块、哨兵二号（Sentinel-2）大气顶层多光谱图像块以及哨兵二号（Sentinel-2）地表反射率多光谱图像块。每个图像块的覆盖范围为2640米×2640米，且包含四个季节对应的时间戳数据。原始数据集采用GeoTIFF格式存储，每个波段对应一个独立文件。