data api · Global

TESSERA

TESSERA (Temporal Embeddings of Surface Spectra for Earth Representation and Analysis) is a foundation model for Earth observation developed at the University of Cambridge. It compresses a full year of Sentinel-1 and Sentinel-2 satellite observations into dense, 128-dimensional per-pixel embeddings at 10m spatial resolution.

Visit source ↗

Claim this listing

Represent TESSERA? 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: 128-dimensional per-pixel embeddings · annual Sentinel-1 and Sentinel-2 observation summaries
Coverage llm-inferred: Global
Resolution docs-verified: 10 m spatial
Formats llm-inferred: npy · zarr
Access docs-verified: Public; licence unknown, see product README

Useful for

Use cases llm-inferred: Land-cover and habitat-type inputs for BNG habitat baseline mapping · Surface change screening across a catchment for FRA or drainage context · Pre-screening of site surface conditions for civils route options
Audience llm-inferred: GIS analysts · ecologists · hydrologists · planners

Limitations

Constraints llm-inferred: Provides derived embeddings, not raw satellite imagery; downstream use needs embedding-aware workflows · Licence not stated in DOCS; check the product README before commercial use · Country-level coverage shown in DOCS is download analytics, not a coverage statement; area is from ENTRY metadata only · Recently created dataset (June 2026); maintenance history is short · Accuracy for specific consultancy tasks is not documented

Licence: see product README
Authentication: Public; anonymous HTTPS/S3 access via data.source.coop
GitHub stars: Unknown
Last commit: Unknown
Last successful page check: 14/10/2026
Page health: page reachable
Package: Not recorded
Verification: Not independently verified

Provenance & evidence

Verified via Source Cooperative API /api/v1/products/tessera (public product, updated 2026-09-27).

Metadata observed 14/10/2026 · research sweep: manual-2026-10-15 (source.coop)