可靠的次国家级人口估计对诸多应用至关重要，但在人口普查数据稀疏、过时或空间分辨率粗糙的地区仍难以实现。现有制图工作流依赖人工构建的地理空间协变量（如聚居区范围、夜间灯光和环境条件），这些变量需跨尺度与跨区域进行组装与标准化。地理空间基础模型则提供了一种替代方案，其通过从更丰富、异构的数据源中学习可复用的地点表征来实现建模。本文在巴西、尼日利亚和美国开展基准测试，将人口动力学基础模型（PDFM）嵌入与标准化地理空间协变量用于次国家级人口估计。在地理结构化验证下，PDFM使预测拟合度中未解释方差的中位数降低20.1%（四分位距：10.0–33.2%，涵盖各国-模型对比），Kullback-Leibler散度降低23.2%（9.2–26.2%）。然而，这些改进呈现不均衡性：PDFM在地理空间协变量对聚居背景刻画较弱的区域（如面积较大且欠发达的次国家级区域）优势最为显著；此外，PDFM性能与空间尺度耦合紧密，其嵌入在不同空间聚合层级间的迁移灵活性低于传统地理空间协变量。结果表明，地理空间基础模型对地点的表征可在数据匮乏场景下提升人口估计精度，但当存在空间尺度错配时，其效益将出现可预测的衰减，揭示了当前地理空间人工智能的一项根本性局限。

Reliable subnational population estimates are essential for applications, yet remain difficult where censuses are sparse, outdated or spatially coarse. Existing population-mapping workflows rely on hand-built geospatial covariates, such as settlement extent, night-time lights, and environmental conditions, which must be assembled and harmonised across scales and geographies. Geospatial foundation models offer an alternative by learning reusable representations of place from more multifaceted and heterogeneous data sources. Here, we benchmark Population Dynamics Foundation Model (PDFM) embeddings against the harmonised geospatial covariates for subnational population estimation in Brazil, Nigeria and the United States. Under geographically structured validation, PDFM increased predictive fit by a median of 20.1% (IQR: 10.0-33.2%, across country-model comparisons) reduction in unexplained variance, and reduced Kullback-Leibler divergence by 23.2% (9.2-26.2%). However, these gains were uneven. PDFM was most advantageous where the geospatial covariates weakly characterised settlement context, such as larger and less-developed subnational areas. Moreover, PDFM performance was scale-coupled with embeddings providing less flexible transfer across spatial aggregations than geospatial covariates. These findings showed that geospatial foundation-model representations of place can improve population estimation in data poor settings, but their benefits break down predictably under spatial scale mismatch, revealing a fundamental limitation of current geospatial AI.