arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.01650cs.LG
收藏

地理基础模型嵌入物在空间和尺度上不均等地提高人口估计

Geospatial foundation-model embeddings improve population estimation unevenly across space and scale

WorldPop, School of Geography and Environmental Sciences, University of Southampton, United Kingdom(世界人口研究机构,地理与环境科学学院,南安普顿大学,英国);Geographic Data Science Lab, Department of Geography and Planning, School of Environmental Sciences, University of Liverpool, United Kingdom(地理数据科学实验室,地理与规划系,环境科学学院,利物浦大学,英国)

Wenbin Zhang, Eimear Cleary, Francisco Rowe, Somnath Chaudhuri, Maksym Bondarenko, Shengjie Lai, Andrew J. Tatem

AI总结:

本文评估了地理基础模型嵌入物在巴西、尼日利亚和美国的子国家人口估计中的表现,发现其在数据贫乏区域提升预测效果,但空间尺度不匹配时性能下降,揭示了当前地理AI的局限性。

摘要:

可靠的次国家人口估计对于应用至关重要,但在人口普查稀疏、过时或空间粗略的地区仍难以实现。现有的人口制图工作流程依赖于手工构建的地理空间协变量,如居民区范围、夜间灯光和环境条件,这些必须在不同尺度和地理区域中组装和协调。地理基础模型提供了一种替代方法,通过学习来自更多多面和异质数据源的可重用位置表示。在此,我们通过巴西、尼日利亚和美国的次国家人口估计,将人口动态基础模型(PDFM)嵌入物与协调的地理空间协变量进行基准测试。在地理结构验证下,PDFM将预测拟合度提高了中位数20.1%(IQR:10.0-33.2%,跨国家-模型比较),并减少了未解释方差23.2%(9.2-26.2%)。然而,这些收益是不均等的。PDFM在地理空间协变量弱化描述居民区情境的地方最为有利,如较大的、发展较慢的次国家区域。此外,PDFM的性能与尺度耦合,嵌入物在空间聚合转移时比地理空间协变量更不灵活。这些发现表明,地理基础模型对位置的表示可以改善数据贫乏地区的人口估计,但其在空间尺度不匹配时性能下降,揭示了当前地理AI的根本限制。

英文摘要:

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subnational population estimates are essential for applications, yet remain difficult where censuses are sparse, outdated or spatially coarse.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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑