software · Global

Population Dynamics Foundation Model (PDFM) embeddings

PDFM Embeddings: location-based vectors for geo-spatial analysis.

Claim this listing

Represent Population Dynamics Foundation Model (PDFM) embeddings? Send a claim for review so we can discuss listing updates. Claims do not automatically grant ownership or verification.

Explore paid sponsorship →

What's in it

Data offered docs-verified: PD-Foundations location embeddings (condensed vector representations per location) · Context features aggregated from search trends, busyness, maps data, and weather and air quality
Coverage docs-verified: 17+ countries (individual countries not named in docs)
Resolution docs-verified: Varies by country; aggregated at spatial levels such as postal code or county
Access docs-verified: Free for approved research use (subject to approval); commercial and public sector use planned via a paid Early Access Program; delivered via BigQuery Listing; subject to Google Terms of Service. Demo code under Apache 2.0.

Useful for

Use cases llm-inferred: Downscale or fill gaps in area-level socioeconomic or health indicators (county to postcode) as covariates for a consultancy baseline · Nowcast missing county-level indicators for a regional study area using partial current data · Add location-context embeddings as features in a GBDT or MLP model for spatial prediction tasks
Audience llm-inferred: GIS analysts · geospatial data scientists · planners · socioeconomic and public health analysts

Limitations

Constraints llm-inferred: Research access requires approval via an application form · Commercial and public sector use is only planned via a paid Early Access Program waitlist · Access is governed by Google Terms of Service and delivered through BigQuery · No UK coverage is listed in the docs, so UK suitability is unconfirmed · Requires ground truth data prepared at postal code or county level · Aggregated, privacy-preserving features; not suitable for individual-level analysis

Licence: Apache-2.0
Authentication: Unknown — review source docs
GitHub stars: 431
Last commit: 13/11/2025
Last successful page check: 14/10/2026
Page health: healthy
Package: Not recorded
Verification: Not independently verified

Auto-extracted, unverified fields: tools, auth. Check upstream documentation.

Provenance & evidence

Verified via GitHub API (2026-10-15). Tools/install/auth auto-extracted from README.

Metadata observed 14/10/2026 · research sweep: manual-2026-10-15 (Chris sources (Google Research geospatial))