TESSERA Case Study
Overview
Satellite remote sensing enables a wide range of downstream applications, including habitat mapping, carbon accounting, and strategies for conservation and sustainable land use. However, satellite time series are voluminous and often cloud-corrupted, making them challenging to use. The scientific community's ability to extract actionable insights is often constrained by the scarcity of labelled training datasets and the computational burden of processing temporal data.
The Innovation
The key insight behind TESSERA is that forcing auto-encoder embeddings derived from two cloud-free random samples of satellite time series to align using Barlow Twins results in an embedding that represents the entire time series, including the missing observations.
What TESSERA Provides
TESSERA is an open foundation model that preserves per-pixel spectral-temporal signals in 128-dimensional latent representations at 10-metre resolution globally. It uses self-supervised learning to summarise petabytes of Earth observation data.
By preserving temporal phenological signals that are typically lost in conventional approaches, TESSERA enables new insights into ecosystem dynamics, agricultural food systems, and environmental change detection.
Its open-source implementation supports reproducibility and extensibility, while its privacy-preserving design allows researchers to maintain data sovereignty.
Key Impacts
Since the release of the TESSERA embeddings in August 2025, the model has:
- Been used by more than 100 projects worldwide.
- Achieved state-of-the-art performance across a wide range of ecological tasks.
- Become the foundation for an intensive effort, led by Professor David Coomes, to create habitat maps for the UK and globally.
"To our knowledge,TESSERA is unprecedented in its ease of use, scale, and accuracy: no other foundation model provides analysis-ready outputs, is open, and provides global, annual coverage at 10m resolution using only spectral-temporal features at pixel level."