Tuesday, October 6, 2026 Newsletter Advertise
Breaking
AI

Google Research Details Earth AI Models for Public Health

Google Research outlined five case studies using its Population Dynamics Foundation Model to improve global public health workflows.

Google Research Details Earth AI Models for Public Health. Source: Google Research

Google Research published details on October 6, 2026, outlining how its Population Dynamics Foundation Model can integrate into global public health and epidemiological workflows.

Understanding PDFM

According to Google Research, the Population Dynamics Foundation Model (PDFM) is part of Google Earth AI, a suite of geospatial models that connects satellite imagery, weather, search trends, and human mobility. The model uses self-supervised learning to synthesize these signals into monthly updated location embeddings.

Google Research stated that these off-the-shelf location embeddings can be plugged directly into existing statistical and machine learning models used by epidemiologists without requiring task-specific fine-tuning.

Partner-Driven Evaluations

Google Research detailed five independent evaluations conducted by partner institutions across various health challenges. These included improving cross-border MMR vaccination tracking with the Mount Sinai Health System and Boston Children's Hospital, and cardiovascular disease mortality nowcasting with the NYU Grossman School of Medicine.

Other evaluations featured short-horizon dengue forecasting in Mexico with the University of Oxford and Tecnológico de Monterrey, postpartum depression risk prediction with the University of Washington, and cholera outbreak prediction in the Democratic Republic of the Congo with WHO AFRO.

Availability

Google Research announced that PDFM embeddings are commercially available in Preview as Population Dynamics Insights through the Google Maps Platform.

Additionally, academic and public health researchers can request no-cost access for select, non-operational research use cases.

Key facts and where they come from
  • Google Research presented five partner-driven case studies showing how PDFM applies to global public health.
    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.
  • PDFM compresses various signals into location embeddings.
    PDFM compresses privacy-preserving search trends, human mobility, built-environment density, and environmental determinants into location embeddings.
  • PDFM embeddings are commercially available in Preview under the name Population Dynamics Insights.
    PDFM embeddings are commercially available in Preview as Population Dynamics Insights, a geospatial embeddings dataset from Google Maps Platform.

Read the original from Google Research →

The TechUpscale Brief

The day's cyber, AI and tech news in one short email, every weekday morning. Free. Unsubscribe anytime.

I'm most interested in

More AI