内容来源：https://blog.google/innovation-and-ai/technology/health/google-earth-ai-global-public-health/

内容总结：

谷歌地球AI赋能全球公共卫生：从预测疾病到精准干预

谷歌地球AI正以其强大的“行星智能”推动全球公共卫生进入预测与预防的新阶段。该技术通过整合地理空间数据、环境因素与人口动态模型，帮助公共卫生机构提前应对传染病爆发、优化医疗资源分配并探索慢性病管理新路径。

精准定位医疗需求
在马拉维，合作机构利用谷歌地球AI的人口动态模型与卫星数据，成功预测了地方诊所的服务使用率，帮助决策者更高效地分配有限资源。在美国，研究人员通过同一技术生成高分辨率疫苗接种覆盖率地图，精准识别接种不足区域，为麻疹防控提供关键依据。

预测天气相关疾病
谷歌与世卫组织非洲区域办公室合作开发的霍乱预测模型，结合时间序列分析与天气数据，将病例预测准确率提升超过35%。在巴西，牛津大学团队利用同类技术显著提高了登革热疫情的长期预测精度，为提前部署防控措施赢得时间。

探索慢性病管理新路径
在澳大利亚农村地区，谷歌与多家健康机构合作推出“人口健康AI”概念验证项目。通过分析空气质量、花粉分布等环境数据与人口动态，该系统致力于揭示社区慢性病需求，助力疾病预防工作。

谷歌地球AI通过将数十年积累的地理环境建模成果转化为公共卫生洞察，正推动全球健康系统从被动应对转向主动干预。随着技术不断验证与推广，数据驱动的公共卫生决策有望成为守护全球社区健康的新常态。

中文翻译：

谷歌地球AI的"行星智能"如何赋能全球公共卫生

公共卫生工作的核心支柱在于整合健康数据、地理空间洞察与预测模型，从而预见并化解健康风险。谷歌地球AI的问世及其提供的"行星智能"，正为这一领域开辟全新可能。

研究人员已开始运用地球AI技术预测登革热和霍乱等疾病，评估马拉维的诊所利用率，并识别澳大利亚的慢性病防治需求。这项技术快速改善全球健康结果的潜力正日益凸显。

基于数十年物理世界建模研究成果，地球AI通过"人口动态基础模型"和"移动智能"技术，帮助人们深入理解天气、空气质量、洪水等环境因素，以及人口与这些因素互动的复杂模式。通过将独特洞察与特定区域或场景的健康信息相结合，我们能够帮助公共卫生官员、研究人员及相关机构突破被动应对危机的局限，转向主动预测与防范——让数十年的研究成果转化为惠及全球社区的有效主动关怀。

我们的合作伙伴已开始验证这种方法的实际成效。以下案例展示了这些整合洞察的具体应用场景。

提升公共卫生干预精准度

在马拉维，谷歌公益资助的Cooper/Smith机构将地球AI的人口动态基础模型、AlphaEarth卫星嵌入数据与本地信息结合，成功预测了地方诊所的医疗服务使用情况。这有助于决策者发现疾病暴发的早期预警信号，更高效地配置有限资源。

为应对麻疹疫情抬头趋势，西奈山医学院与波士顿儿童医院/哈佛大学的研究团队运用地球AI人口动态基础模型填补数据空白，生成疫苗接种覆盖率的"超分辨率"估算。基于隐私保护的聚合数据，研究人员可绘制邮编级别的疫苗接种率地图，在保护敏感个人信息的同时，精准定位与近期疫情暴发区域重合的低接种率聚集区。

构建气候地理敏感型疾病预警系统

天气变化影响众多疾病的传播节奏，特定气象模式可能预示健康危机。例如夏季降雨可能导致登革热病例激增，洪水则会显著加剧霍乱暴发风险。将人口动态数据与气象预测模型结合，有助于提前数周乃至数月预测突发公共卫生事件。

我们与世卫组织非洲区域办事处合作，利用世卫组织集中式综合疾病监测数据，对霍乱病例的次国家级预测模型进行评估。研究发现，将谷歌TimesFM时间序列模型与人口动态基础模型及气象数据结合后，霍乱病例预测准确率较传统模型提升超35%。更精准的预测能使公共卫生官员变被动应对为主动规划——例如将救命的补液物资预先调拨至需求区域。

此外，牛津大学研究团队已成功运用地球AI模型与数据集提升巴西登革热预测水平。引入人口动态基础模型嵌入数据后，六个月期预测准确率显著提高，为地方当局实施预防措施争取了更充裕的时间。

解析慢性病防治需求

地球AI在非传染性疾病领域同样释放出关键洞察。在澳大利亚近期开展的试点项目中，我们与维克多·张心脏研究所、西农健康集团及拉筹伯健康服务组织合作部署"人口健康AI"。该平台将地球AI人口动态基础模型嵌入数据与空气质量、花粉分布、场所洞察等关键数据集结合，旨在揭示澳大利亚乡村社区的医疗需求，目前作为概念验证方案向特定合作伙伴开放，以支持慢性病防治工作。

迈向主动预防的健康未来

当技术转化为实际行动时，其力量最为强大。通过融合谷歌地球AI的行星智能与合作伙伴的深厚医学专长，我们正朝着这样的未来目标迈进：让全球各地的医疗系统都能获得数据驱动的深度洞察，从而更有效地守护并改善公众健康。

英文来源：

How Google Earth AI’s planetary intelligence is supporting global public health
A central pillar of effective public health is the combination of health-related data with geospatial insights and predictive modeling to anticipate and mitigate health risks. The introduction of Google Earth AI and its ability to provide planetary intelligence presents new opportunities for the field.
Earth AI is already in use by researchers to forecast diseases such as dengue fever and cholera, predict clinic utilization in Malawi and identify chronic disease needs in Australia, with its potential to improve health outcomes worldwide quickly coming into focus.
Leveraging decades of research that models the physical world, Earth AI provides a deeper understanding of environmental factors — such as weather, air quality and flooding — and the complex ways populations interact with them through our Population Dynamics Foundation Model (PDFM) and Mobility AI. By combining unique insights with region or context-specific health information, we can support public health officials, researchers and organizations in moving beyond reacting to crises. Instead, this creates the potential for forecasting and anticipating them — turning decades of research into effective, proactive care for communities everywhere.
Our partners are already beginning to validate the real-world impact of this approach. The following initiatives illustrate some examples of how these integrated insights are already being utilized.
Improving the precision of public health interventions
In Malawi, Google.org grantee Cooper/Smith combined Earth AI’s PDFM and AlphaEarth satellite embeddings with local data to predict health service utilization at local clinics. This can help decision-makers spot early warning signs of disease outbreaks and allocate limited resources more efficiently.
To combat the rise of measles, researchers at Mount Sinai and Boston Children’s Hospital/Harvard, used Earth AI’s PDFM to fill gaps and produce "superresolution" estimates of vaccination coverage. Based on privacy-preserving, aggregated data, researchers can map vaccination rates down to the ZIP-code level without revealing sensitive personal information, and identify localized clusters of undervaccination that align with recent outbreaks.
Forecasting for diseases where weather and geography matter
Weather influences the pace of many diseases, and specific weather patterns can signal health crises. For example, summer rains can cause dengue fever to spike, while flooding can significantly increase cholera outbreaks. Combining population dynamics with predictive weather models helps improve forecasting of health emergencies weeks or months in advance.
In collaboration with the WHO Regional Office for Africa, we evaluated a sub-national forecasting model for cholera cases utilizing the WHO centralized Integrated Disease Surveillance Data. We found that by combining Google's TimesFM time-series model with PDFM and weather data, we were able to improve the forecasting accuracy of cholera cases by over 35% compared to standard models. Better forecasting could enable public health officials to plan proactively, rather than react after a crisis — for example by moving life-saving rehydration supplies to where they will be needed.
Furthermore, researchers at the University of Oxford have successfully used Earth AI models and datasets to improve forecasting of dengue fever in Brazil. Including PDFM embeddings significantly raised the predictive accuracy of six-month forecasts, giving local authorities more time to implement preventative measures.
Understanding chronic disease needs
Earth AI is also unlocking critical insights into non-communicable diseases. In a recent initiative in Australia, we partnered with the Victor Chang Cardiac Research Institute, Wesfarmers Health and Latrobe Health Services to deploy Population Health AI (PHAI). Currently available as a proof-of-concept to select partners, PHAI uses Earth AI’s PDFM embeddings alongside other key datasets like air quality, pollen and places insights to uncover the health needs of communities in rural Australia, aiming to support their chronic disease needs and prevention efforts.
A proactive, healthier future
Technology is most powerful when it leads to real-world action. By fusing Google Earth AI’s planetary intelligence along with the deep health expertise of our partners, we are moving toward a future goal where health systems everywhere possess the data-driven insights needed to protect and improve public health.