NetGoodIndexSubmit a correction

Benefit Ledger · provisional · Climate & Environment

AlphaEarth Foundations releases annual 10-meter satellite embeddings

On 30 July 2025 DeepMind introduced AlphaEarth Foundations, a model that embeds petabytes of Earth observation into a compact annual 10-meter representation released in Google Earth Engine and tested with more than 50 partner organizations.

30 Jul 2025Tier 2 NotableMethodology 0.1

Current score

+0.16

3 base · Notable (tier 2 of 5, 3 pts)
× 0.7500 attribution · Critical contribution
× 0.2500 evidence · Technical disclosure or preprint
× 0.6500 realization · Independently validated or deployed
× 0.5000 durability
Event-level product before credit split: 0.18

Notable operational geospatial embedding (tier 2). Substantial attribution. Developer announcement evidence. Realization is a public Earth Engine dataset. Provisional pending independent accuracy audits.

What happened

Partners including mapping groups reported faster classification of ecosystems and land-use change. The release is a data product plus model, not a completed global conservation outcome. Evidence is still largely developer-reported case studies.

Model attribution

+0.16

AlphaEarth

Produced satellite embeddings released in Earth Engine.

The embedding model is the product; partners applied it to mapping tasks.

Attribution 0.7500 · Credit share 90% · Google DeepMind

Claims

  • AlphaEarth annual embeddings were released in Google Earth Engine for global land and coastal mapping.

    outcome · supported

Sources

primary sources

Secondary domains: Computer Science

Revision history

  • 13 Sep 2026 · 0.00 → 0.16

    Initial adjudicated seed score under methodology 0.1.