Google Earth AI Advances Public Health with Predictive Modeling

Google Earth AI is increasingly being utilized to enhance global public health initiatives by combining health data with advanced geospatial models. This integration allows for more accurate predictions of outbreaks, identification of local vulnerabilities, and proactive delivery of care, moving the field from reactive responses to data-driven prevention.

Predicting and Mitigating Disease Outbreaks

Researchers are leveraging Google Earth AI to forecast diseases like dengue fever and cholera, predict clinic utilization, and identify needs related to chronic illnesses. These efforts are supported by Google’s Population Dynamics Foundation Model (PDFM) and Mobility AI, which provide deeper understanding of environmental factors and population interactions.

Malawi: Early Warning System for Health Service Utilization

In Malawi, a Google.org grantee, Cooper/Smith, combined Earth AI’s PDFM with AlphaEarth satellite embeddings to predict health service utilization at local clinics. ¹ This allows decision-makers to identify early warning signs of disease outbreaks and allocate limited resources more efficiently.

Improving Vaccination Coverage Estimates

To address the rise of measles, researchers at Mount Sinai and Boston Children’s Hospital/Harvard used Earth AI’s PDFM to generate “super-resolution” estimates of vaccination coverage down to the ZIP-code level. ³ This approach preserves privacy while identifying localized clusters of undervaccination that correlate with recent outbreaks.

Weather-Sensitive Disease Forecasting

Weather patterns significantly influence the spread of many diseases. Recognizing this, Google Earth AI is being used to improve forecasting accuracy for weather-sensitive illnesses.

Cholera Forecasting in Africa

Collaboration with the WHO Regional Office for Africa revealed that combining Google’s TimesFM time-series model with PDFM and weather data improved cholera case forecasting accuracy by over 35% compared to standard models. ² This enhanced forecasting enables public health officials to proactively deploy life-saving rehydration supplies.

Dengue Fever Forecasting in Brazil

Researchers at the University of Oxford have successfully used Earth AI models and datasets to improve forecasting of dengue fever in Brazil. ¹ Incorporating PDFM embeddings significantly raised the predictive accuracy of six-month forecasts, providing local authorities with more time to implement preventative measures.

Understanding Chronic Disease Needs

Google Earth AI is as well being applied to understand and address chronic disease needs.

Australia: Population Health AI (PHAI) Initiative

In Australia, Google partnered with the Victor Chang Cardiac Research Institute, Wesfarmers Health, and Latrobe Health Services to deploy Population Health AI (PHAI). ¹ Currently available as a proof-of-concept, PHAI uses Earth AI’s PDFM embeddings alongside data on air quality, pollen levels, and local amenities to uncover the health needs of communities in rural Australia, supporting chronic disease prevention efforts.

A Proactive Future for Public Health

By integrating Google Earth AI’s planetary intelligence with the expertise of its partners, Google aims to empower health systems worldwide with the data-driven insights needed to protect and improve public health. ¹