Self-supervised geospatial foundation models (GeoFMs) learn transferable representations from remote sensing data, but their downstream behavior is difficult to characterize. We study six representative GeoFMs spanning joint-embedding, reconstruction, and multimodal pretraining families, and evaluate transfer across classification, regression, and segmentation benchmarks under different label availability and downstream pipelines. We find that model rankings change across tasks and adaptation settings. Layerwise probing shows that, in most cases, task-relevant information is more accessible in intermediate transformer blocks compared to final-layer embeddings, and that GeoFMs exhibit distinct depthwise profiles. In segmentation case studies on PASTIS and Sen1Floods11, downstream adaptation settings such as decoder design and fine-tuning can be as impactful as the choice of GeoFM, and standard dense-prediction heads may be poorly aligned with how GeoFMs organize information over depth. Finally, CKA analysis on case studies shows that fine-tuning does not rewrite GeoFMs uniformly across depth, and the strongest changes are localized to the first linear layer of the MLP in ViT blocks. These results help explain why GeoFM rankings shift across benchmarks and motivate more representation-aware evaluation and adaptation strategies.

翻译：自监督地理空间基础模型从遥感数据中学习可迁移的表征，但其下游行为难以刻画。本研究选取六种代表性地理空间基础模型，涵盖联合嵌入、重建及多模态预训练范式，并在不同标签可用性与下游流程条件下，评估其在分类、回归及分割基准上的迁移能力。研究发现，模型排名随任务与适应设置动态变化。逐层探测表明，在多数情况下，任务相关信息更易从中间Transformer块中获取，而非最终层嵌入，且地理空间基础模型表现出独特的深度方向分布特征。在PASTIS与Sen1Floods11数据集的分割案例研究中，解码器设计与微调等下游适应设置的影响可能不亚于地理空间基础模型的选择，且标准密集预测头可能难以与地理空间基础模型沿深度组织信息的方式对齐。最后，案例研究的CKA分析表明，微调不会在深度方向上均匀改写地理空间基础模型，最强变化集中于ViT块中MLP的首个线性层。这些结果有助于解释地理空间基础模型排名随基准变化的现象，并推动更具表征意识的评估与适应策略发展。