# Google Research — Unlocking Earth AI’s planetary geospatial foundation models for global public health

- Company: Google Research (research.google)
- Announced: 2026-10-06T15:05:11+00:00
- Category: research-paper
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://research.google/blog/earth-ais-planetary-geospatial-foundation-models-for-global-public-health/
- Record: https://forck.live/items/16221-unlocking-earth-ai-s-planetary-geospatial-foundation-models-for-global-public
- Subject: Research
- Models affected: Population Dynamics Foundation Model (PDFM)

Google Research presents five partner-driven case studies using the Population Dynamics Foundation Model (PDFM) as a proof-of-concept for planetary geospatial foundation models in public health. PDFM embeddings, which compress privacy-preserving search trends, mobility, built-environment density, and environmental determinants, matched or improved on conventional inputs across tasks including MMR vaccination extrapolation, cardiovascular mortality nowcasting, dengue forecasting, postpartum depression risk prediction, and cholera outbreak prediction. The model requires no task-specific fine-tuning and is refreshed at a monthly cadence.

## Evidence

Verbatim from https://research.google/blog/earth-ais-planetary-geospatial-foundation-models-for-global-public-health/:

> Without requiring task-specific fine-tuning, these off-the-shelf location embeddings matched or improved on conventional inputs across a wide variety of disease domains, geographic settings, and epidemiological tasks.

---

Record: https://forck.live/items/16221-unlocking-earth-ai-s-planetary-geospatial-foundation-models-for-global-public
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md