地理空间基础模型提供预先计算的嵌入向量，作为大规模卫星遥感数据的紧凑特征表示。尽管这些嵌入可缓解数据传输瓶颈和计算成本问题，地球观测（EO）应用仍可能面临用户定义的兴趣区域与固定预计算嵌入网格之间的几何不匹配问题。在此场景下，标准的潜在空间插值不可靠，因为嵌入流形具有高度非凸性，导致生成的表示无法对应于真实输入。我们通过Prithvi-EO-2.0验证了这一现象，以理解应用于图像块嵌入时插值方法的局限性。为此，我们提出一种学习等变性预测架构（LEPA）。LEPA不采用向量平均，而是将预测器条件设置为几何增强，直接预测变换后的嵌入。我们在NASA/USGS统一陆地卫星-哨兵（HLS）影像和ImageNet-1k数据集上评估LEPA。实验结果表明，标准插值的平均倒数排名（MRR）低于0.2，而LEPA将MRR提升至0.8以上，实现了无需重新编码即可准确进行几何调整。

Geospatial foundation models provide precomputed embeddings that serve as compact feature vectors for large-scale satellite remote sensing data. While these embeddings can reduce data-transfer bottlenecks and computational costs, Earth observation (EO) applications can still face geometric mismatches between user-defined areas of interest and the fixed precomputed embedding grid. Standard latent-space interpolation is unreliable in this setting because the embedding manifold is highly non-convex, yielding representations that do not correspond to realistic inputs. We verify this using Prithvi-EO-2.0 to understand the shortcomings of interpolation applied to patch embeddings. As a substitute, we propose a Learned Equivariance-Predicting Architecture (LEPA). Instead of averaging vectors, LEPA conditions a predictor on geometric augmentations to directly predict the transformed embedding. We evaluate LEPA on NASA/USGS Harmonized Landsat-Sentinel (HLS) imagery and ImageNet-1k. Experiments show that standard interpolation achieves a mean reciprocal rank (MRR) below 0.2, whereas LEPA increases MRR to over 0.8, enabling accurate geometric adjustment without re-encoding.