地理空间基础模型已成为下游地球观测任务的最先进方法。然而，现有的预训练方法通过单一概念视角处理图像，未能捕捉复杂卫星场景的高度组合特性。我们提出了一种组合感知预训练框架，显式编码分数土地覆盖混合比例。每个卫星图像单元被映射为表示其分数土地覆盖分布的直方图，我们称之为“组合目标”。这些目标作为主要预测对象，并通过 Earth Mover's Distance 蒸馏至主干网络中。实验评估表明，组合感知预训练在需要语义相似性判断的区域级理解任务（包括零样本图像检索和场景分类）上取得了显著增益，同时在需要细粒度空间精度的任务（如分割和目标检测）上保持竞争力。凭借一个拥有 36.8M 参数的主干网络，我们的框架在大多数检索和场景分类设置中优于包含 303M 和 600M 参数的 SatMAE 和 Prithvi-EO-2.0。在用于严格测试组合判别能力的细粒度 ForestNet-12 数据集上，该方法将基线 mAP@10 从 0.279 提升至 0.434，相对提升 55.6%，为显式组合建模的有效性提供了直接证据。代码实现可在 https://github.com/05kashyap/GFM_Composition_Pretraining 获取。

Geospatial foundation models have emerged as state-of-the-art methods for downstream Earth observation tasks. However, existing pretraining methodologies process imagery through a single-concept lens, failing to capture the highly compositional nature of complex satellite scenes. We propose a composition-aware pretraining framework that explicitly encodes fractional land-cover mixtures. Each satellite image cell is mapped to a histogram representing its fractional land-cover distribution, which we term the "composition target". These targets serve as the primary prediction objective and are distilled into the backbone using Earth Mover's Distance. Experimental evaluation shows that composition-aware pretraining yields substantial gains on region-level understanding tasks requiring semantic similarity judgment, including zero-shot image retrieval and scene classification, while remaining competitive on tasks requiring fine-grained spatial precision, such as segmentation and object detection. With a 36.8M-parameter backbone, our framework outperforms SatMAE and Prithvi-EO-2.0, which contain 303M and 600M parameters, respectively, in most retrieval and scene classification settings. On the fine-grained ForestNet-12 dataset, a rigorous testbed for compositional discrimination, our method boosts baseline mAP@10 from 0.279 to 0.434, a 55.6% relative improvement, providing direct evidence for the effectiveness of explicit composition modeling. The code implementation can be found at https://github.com/05kashyap/GFM_Composition_Pretraining