Geospatial models must adapt to the diversity of Earth observation data in terms of resolutions, scales, and modalities. However, existing approaches expect fixed input configurations, which limits their practical applicability. We propose AnySat, a multimodal model based on joint embedding predictive architecture (JEPA) and resolution-adaptive spatial encoders, allowing us to train a single model on highly heterogeneous data in a self-supervised manner. To demonstrate the advantages of this unified approach, we compile GeoPlex, a collection of $5$ multimodal datasets with varying characteristics and $11$ distinct sensors. We then train a single powerful model on these diverse datasets simultaneously. Once fine-tuned, we achieve better or near state-of-the-art results on the datasets of GeoPlex and $4$ additional ones for $5$ environment monitoring tasks: land cover mapping, tree species identification, crop type classification, change detection, and flood segmentation. The code and models are available at https://github.com/gastruc/AnySat.

翻译：地球空间模型必须适应地球观测数据在分辨率、尺度与模态方面的多样性。然而，现有方法通常要求固定的输入配置，这限制了其实际适用性。我们提出了AnySat，这是一种基于联合嵌入预测架构（JEPA）与分辨率自适应空间编码器的多模态模型，使我们能够以自监督方式在高度异质的数据上训练单一模型。为展示这种统一方法的优势，我们构建了GeoPlex——一个包含5个具有不同特性的多模态数据集和11种独立传感器的数据集集合。随后，我们在这些多样化数据集上同时训练了一个强大的单一模型。经过微调后，我们在GeoPlex的5个数据集及另外4个数据集上，针对5项环境监测任务——土地覆盖制图、树种识别、作物类型分类、变化检测与洪水分割——取得了优于或接近最先进水平的结果。代码与模型可在 https://github.com/gastruc/AnySat 获取。