Google Earth AI's PDFM Geospatial Embeddings Applied to Global Public Health Research
Understand the story
On October 6, 2026, Google Research announced that the Population Dynamics Foundation Model (PDFM) location embeddings of Earth AI will be made available to the public as plug-and-play inputs for global public health research. In collaboration with five institutions, the model's location embeddings have been independently validated on five categories of public health challenges, covering MMR vaccination, cardiovascular disease, dengue, postpartum depression, and cholera. This release shows that PDFM embeddings can serve as general-purpose geospatial representations that different institutions and application scenarios can directly plug into, providing foundation model support for modeling research in public health. The public information currently available is based on the above first-party release.
AI overview of reporting · Updated 11 days ago
Reporting timeline
Explore different aspects of the story through its reporting.
- Google ResearchUnlocking Earth AI’s planetary geospatial foundation models for global public health
Google Research opened up location embeddings from Earth AI's Population Dynamics Foundation Model (PDFM) as plug-and-play inputs, completing independent validation with five institutions across five types of public health challenges, covering MMR vaccination, cardiovascular disease, dengue, postpartum depression, and cholera.