TESSERA: An open-source satellite remote-sensing foundation model for researchers
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 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.
Our work introduces TESSERA (Temporal Embeddings of Surface Spectra for Earth Representation and Analysis), an open foundation model that preserves spectral-temporal signals in 128-dimensional latent representations at 10-meter 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. Moreover, our open-source implementation supports reproducibility and extensibility, while the privacy-preserving design allows researchers to maintain data sovereignty.
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.
TESSERA has been developed by a team led by Prof. Srinivasan Keshav, Prof. Anil Madhavapeddy, and Dr. Sadiq Jaffer at Department of Computer Science and Technology, and Prof. David Coomes at the Department of Plant Science. All of them are also affiliated with the Conservation Research Institute, University of Cambridge.
The original form of this article was published on 11 November 2025, as part of the Climate and Nature Impact Map:
Image credit: Getty Images
For more information see: