借助 Google Earth AI 的人口动态基础模型（PDFM），我们可以解决现有流行病学工作流程中的数据缺口和时间报告滞后问题。在最新工作中，我们展示了五个由合作伙伴驱动的案例研究，说明该模型如何体现面向全球公共卫生的行星地理空间基础模型范式。PDFM 嵌入向量无需研究人员自行收集和预处理原始数据流，即可轻松接入现有的机器学习工作流，提供即用型地理空间上下文信息。

With Google Earth AI’s Population Dynamics Foundation Model (PDFM), we can address the data gaps and temporal reporting lags of existing epidemiological workflows. In our latest work, we present five partner-driven case studies demonstrating how this model exemplifies the planetary geospatial foundation model paradigm for global public health. Rather than requiring researchers to collect and process these raw data streams themselves, PDFM embeddings can be easily plugged into existing ML workflows to provide ready-to-use geospatial context.

借助 Google Earth AI 的人口动态基础模型（Population Dynamics Foundation Model, PDFM），我们可以解决现有流行病学工作流程中的数据缺口和时间报告滞后问题。在我们最新的研究中，我们展示了五个由合作伙伴驱动的案例研究，证明该模型如何体现面向全球公共卫生的行星尺度地理空间基础模型范式。PDFM 嵌入向量无需研究人员自行收集和预处理原始数据流，即可轻松接入现有的机器学习工作流，提供即插即用的地理空间上下文信息。先前的研究表明，这些嵌入向量具有任务无关性。由于这些日常信号捕捉了健康背后的社会、行为和环境决定因素，相同的嵌入向量在填补 CDC 各类健康指标数据的空白方面表现出强劲的性能。然而，确立全球健康的新范式需要更高的证据标准。为了达到这一标准，我们致力于在更广泛的健康挑战以及全球不同环境中展示 PDFM 嵌入向量的价值。 通过捕捉跨境流动性和信息溢出效应，解释方差相对提升 +36%（从 0.159 提升至 0.216，具有统计显著性）。在即时预测（nowcasting）方面，其准确性与基于人口普查的模型相当（每县平均绝对误差为 18.7 vs 19.1 例死亡；均方根误差 RMSE 为 46.00 vs 57.69；差异无统计显著性），这使得 PDFM 成为人口普查数据过时或不可用时的及时替代方案。通过集成 TimesFM，实现了具有统计显著性的一个月期预测增益（加权区间评分变化 Δ Weighted Interval Score = -0.0051，数值越低越好），且增益集中在活跃传播热点地区。在多达 72% 的活跃传播市镇中，预测准确性得到提升。风险预测具备可迁移增益（在已见州中，AUC 在 0.62 基线上提升 +0.0020；在未见州中提升 +0.0038）。编码区域贫困程度（R² = 0.45）。当收入保险记录缺失时，可恢复约 15% 的相关预测信号。 我们的评估显示，尽管流行病学模型受限于主权边界，但其追踪的结果并不受此限制。例如，在位于加拿大边境 150 公里范围内的 146 个美国县中，仅依赖国内数据的模型往往难以预测当地的疫苗接种率。心血管疾病（CVD）每年在美国夺去超过 916,000 人的生命。然而，来自国家生命统计系统（NVSS）的未经抑制的县级死亡率数据通常滞后 1–2 年，而美国社区调查（ACS）协变量反映的是过去 2–3 年的状况。PDFM 在更多地区可用且滞后时间大大缩短，从而提升了我们对疾病建模的能力。纽约大学格罗斯曼医学院（NYU Grossman School of Medicine）的合作伙伴测试了 PDFM 能否在估算约 3,100 个美国县的当年 CVD 死亡人数时替代这些基于人口普查的输入数据。他们发现，在即时预测方面，PDFM 与传统人口普查数据之间没有统计显著差异，且 PDFM 的数据更新更快、覆盖范围更广：这些结果表明，PDFM 可以帮助卫生部门利用当前状况指导预防资源分配，而无需等待多年一次的调查周期。 该模型在提前一个月进行预测时性能增益最大，使多达 72% 的登革热活跃传播市镇的预测准确性得到提升，总误差减少量是误差增加量的 3.4 倍。这种性能提升恰好发生在及时的媒介控制和临床人员配置决策最为关键的领域，尤其考虑到短期预测已被证实具有实用价值。对产后抑郁症（PPD）等孕产妇心理健康状况的筛查通常依赖于临床接诊信息，而这些信息很少能捕捉到影响母亲风险和护理获取途径的更广泛的社区条件。为了测试地理空间基础模型能否帮助弥补这一差距，华盛顿大学的研究人员在 CDC PRAMS 全国调查中针对 332,970 名参与者评估了 PDFM 嵌入向量。除了 PDFM 能够捕捉社区层面的社会经济条件（R²=0.45）外，添加嵌入向量还为预测哪些母亲处于风险之中提供了持续且具有统计显著性的提升（在已见州中 AUC +0.0020；在未见州中 +0.0038）。关键在于，这种信号在模型训练期间从未见过的州依然有效——它作为一种互补的本地上下文，在缺乏母亲自身收入和保险记录细节时，可恢复约 15% 的预测信号。 对于霍乱等水源性流行病的早期预警，对于预先部署口服霍乱疫苗和清洁水供应至关重要。幸运的是，疫情爆发较为罕见：在任何给定的一周内，该国不到百分之一的地区会出现病例。不幸的是，这也使得预测变得困难。我们的研究发现，虽然近期病例计数本身具有预测力，但结合 PDFM 提供的背景环境特征后，模型在识别即将发生爆发的区域方面表现更佳。特别是在那些历史数据稀疏的地区，PDFM 嵌入向量通过捕捉潜在的环境和社会脆弱性，显著提高了预警系统的灵敏度和特异性，为公共卫生干预争取了宝贵的时间窗口。

With Google Earth AI’s Population Dynamics Foundation Model (PDFM), we can address the data gaps and temporal reporting lags of existing epidemiological workflows. In our latest work, we present five partner-driven case studies demonstrating how this model exemplifies the planetary geospatial foundation model paradigm for global public health. Rather than requiring researchers to collect and process these raw data streams themselves, PDFM embeddings can be easily plugged into existing ML workflows to provide ready-to-use geospatial context. Prior work showed that these embeddings are task-agnostic. Because these everyday signals capture the underlying social, behavioral, and environmental determinants of health, the same embeddings showed strong performance on filling gaps in a wide variety of CDC health metrics. However, establishing a new paradigm for global health carries a higher burden of proof. To meet this standard, we set out to demonstrate the value of PDFM embeddings across a wider variety of health challenges, and in different environments across the globe. +36% relative gain in explained variance (0.159 0.216, statistically significant) by capturing cross-border mobility and information spillovers. Comparable accuracy to census-based models for nowcasting (mean absolute error 18.7 vs 19.1 deaths per county; RMSE 46.00 vs 57.69; differences not statistically significant), making PDFM a timely stand-in when census data are outdated or unavailable. Statistically significant 1-month forecast gain ( Δ Weighted Interval Score = -0.0051, lower is better) via TimesFM integration, concentrated in active transmission hotspots. Accuracy improved in up to 72% of active transmission municipalities. Transferable gain in risk prediction (AUC +0.0020 on a 0.62 baseline in seen states; +0.0038 in unseen states). Encoded area poverty (R² = 0.45). Recovers about 15% of the predictive signal of income and insurance records. Our evaluations show that while epidemiological models are constrained by sovereign borders, the outcomes they track are not. For example, in the 146 U.S. counties situated within 150 km of the Canadian border, domestic-only models often struggle to predict local vaccine uptake. Cardiovascular disease (CVD) claims over 916,000 lives annually in the U.S. However, unsuppressed official county-level mortality data from the National Vital Statistics System (NVSS) typically lags by 1–2 years, and American Community Survey (ACS) covariates reflect conditions up to 2–3 years in the past. PDFM is available in more places and has much less of a lag, allowing for the ability to improve our capacity to model disease. Our partners at NYU Grossman School of Medicine tested whether PDFM could stand in for these census-based inputs when estimating current-year CVD deaths across roughly 3,100 U.S. counties. They found no statistically significant differences between PDFM and traditional census data on nowcasting, with PDFM being much fresher and available in far more places: These results suggest that PDFM can enable health departments to guide prevention resources using current conditions rather than waiting on multi-year survey cycles. The model’s greatest performance gains occurred when predicting one month ahead, improving forecast accuracy in up to 72% of active dengue transmission municipalities, yielding total error reductions 3.4X larger than degradations. This performance occurred precisely where timely vector control and clinical staffing decisions matter most, especially considering the demonstrated utility of short term forecasts. Screening for maternal mental health conditions like postpartum depression (PPD) typically relies on clinical intake information, which rarely captures the broader community conditions that shape a mother’s risk and access to care. To test whether geospatial foundation models can help bridge this gap, researchers at the University of Washington evaluated PDFM embeddings across 332,970 participants in the CDC PRAMS national survey. In addition to PDFM capturing community-level socioeconomic conditions (R2=0.45), adding the embeddings provided a consistent, statistically significant boost to predicting which mothers were at risk (AUC +0.0020 in seen states; +0.0038 in unseen states). Crucially, this signal held up in states the model had never seen during training—acting as complementary local context that recovers about 15% of the predictive signal of a mother’s own income and insurance records when those details are unavailable. Early warning for waterborne epidemics like cholera is critical for prepositioning oral cholera vaccines and clean water supplies. Fortunately, outbreaks are rare: in any given week, fewer than 1 in 100 of the country's 403 health zones sees one begin. Unfortunately, this very same rarity makes them hard to anticipate. The benefit depended on how far ahead we looked. One or two weeks out, recent case counts told most of the story and PDFM did not significantly enhance the accuracy. Four to eight weeks out, when there is still time to move supplies, it helped produce: These findings demonstrate that while short-term tracking can rely on recent clinical data, foundation model embeddings capture underlying environmental, connectivity, and population determinants that supplement historical data, allowing for proactive planning one to two months in advance. Geospatial foundation models enable moving from reactive, localized modeling to proactive and time-sensitive health intelligence at planetary scale. Current limitations, such as static snapshots, are driving active research into temporally dynamic embeddings and geographic transfer learning for under-connected regions. By integrating planetary contextual data into existing public health workflows, we can help take steps to improve how healthcare resources, interventions, and outbreak alerts reach the communities that need them most. Read the paper for more details. PDFM embeddings are commercially available in Preview as Population Dynamics Insights, a geospatial embeddings dataset from Google Maps Platform. Academics and public health researchers can also request no-cost access for select, non-operational research use cases.