--- title: README emoji: ๐ŸŒ colorFrom: green colorTo: blue sdk: static pinned: false ---

TESSERA โ€” pixel-wise Earth observation foundation model

TESSERA

A pixel-wise Earth observation foundation model
from the University of Cambridge ยท ucam-eo

--- **TESSERA** turns raw satellite time series into ready-to-use **embeddings**. For every **10 m** pixel on Earth it reads a full year of **Sentinel-1 (SAR)** and **Sentinel-2 (optical)** observations and compresses them into a compact, task-agnostic vector โ€” a learned summary of the land's spectral and temporal behaviour. Trained self-supervised on billions of pixels, with **no labels required**, these embeddings work as drop-in features for land cover and crop mapping, biomass and carbon estimation, change detection, and more, and are far cheaper to store and serve than raw imagery. | | | |---|---| | ๐Ÿ›ฐ๏ธ **Inputs** | Sentinel-1 + Sentinel-2, one full year per pixel | | ๐Ÿ“ **Resolution** | 10 m, global, annual embeddings for **2017โ€“2025** | | ๐Ÿงฉ **Output** | dense per-pixel embeddings โ€” v2 adds nested **Matryoshka** vectors (use 16 / 32 / 64 / 128 dims) | | ๐Ÿง  **Training** | self-supervised (Barlow Twins), no labels | ## Models | Release | Description | Weights | |---|---|---| | **TESSERA v2** *(latest)* | Four compact pixel students โ€” **Nano 1.07M ยท Small 7.11M ยท Medium 21.03M ยท Large 43.83M** โ€” distilled from a **2B teacher**, with 128-d Matryoshka output. | [N](https://huggingface.co/geotessera/TESSERA-V-2.0-2B-N) ยท [S](https://huggingface.co/geotessera/TESSERA-V-2.0-2B-S) ยท [M](https://huggingface.co/geotessera/TESSERA-V-2.0-2B-M) ยท [L](https://huggingface.co/geotessera/TESSERA-V-2.0-2B-L) ยท [Teacher](https://huggingface.co/geotessera/TESSERA-V-2.0-2B-Teacher) | | **TESSERA v1.1** | Wider QAT encoder, all-observation inference; MPC & AWS checkpoints (int8). | [TESSERA-V-1.1](https://huggingface.co/geotessera/TESSERA-V-1.1) | | **TESSERA v1.0** | The original release (QAT / int8 and early fp32). | [TESSERA-V-1.0](https://huggingface.co/geotessera/TESSERA-V-1.0) | ๐Ÿ‘‰ Everything in one place: the [**TESSERA collection**](https://huggingface.co/collections/geotessera/tessera-6a108c1a6618e155f551c065). ## Get started **Just want embeddings?** Skip the model entirely โ€” download ready-made global embeddings with the [`geotessera`](https://github.com/ucam-eo/geotessera) Python library: ```bash pip install geotessera ``` ...or [request coverage](https://github.com/ucam-eo/geotessera#request-missing-embeddings) for your region. New v2 embeddings can be [pre-requested here](https://github.com/ucam-eo/geotessera/issues/new?template=v2-embedding-prerequest.yml&labels=v2-embedding-prerequest). **Want to run the model yourself?** Generate embeddings from your own Sentinel-1/2 tiles with the code and instructions in [`ucam-eo/tessera`](https://github.com/ucam-eo/tessera). ## Learn more - ๐ŸŒ Website โ€” https://geotessera.org - ๐Ÿ“ฆ Model & inference code โ€” https://github.com/ucam-eo/tessera - ๐Ÿ Embeddings library โ€” https://github.com/ucam-eo/geotessera - ๐Ÿ“„ Papers โ€” [TESSERA v2: Scaling Pixel-wise Earth Foundation Models](https://arxiv.org/abs/2607.03949) ยท [TESSERA (v1)](https://arxiv.org/abs/2506.20380) Model weights are released under CC0-1.0; the `geotessera` library under MIT. Use is additionally governed by the TESSERA Acceptable Use Policy.