# TESSERA v2: Scaling Pixel-wise Earth Foundation Models *2026-07-01 — paper* Authors: Zhengpeng Feng, Sadiq Jaffer, Ira Shokar, Jovana Knezevic, Mark Elvers, Clement Atzberger, Robin Young, Aneesh Naik, Niall Robinson, Andrew Blake, David Coomes, Anil Madhavapeddy, Srinivasan Keshav Pixel-wise Earth-observation (EO) foundation models are now achieving state-of-the-art performance via generated spatial embeddings. However, how these models scale and how best to spend a pretraining budget remain poorly understood. We present the largest controlled scaling study for EO to date: 395 training runs on 1,024 GH200 superchips within a fixed pixel-wise Barlow Twins family, each evaluated on 15 downstream tasks. We find that pretraining loss barely predicts downstream performance (\|Pearson r\| \< 0.2), so selecting models by loss wastes a large share of the compute. We also find that, as the training budget grows, the encoder and the data should grow together while the projector stays fixed, which gives a simple rule for allocating compute. Using this rule, we train a family of pixel-wise models (0.5B and 1B, with a 2B model in training) and distill them into compact students for embeddings-as-data deployment. The 21-million-parameter distilled TESSERA v2-1B-M in aggregate outperforms all open and proprietary models tested, some of which are orders of magnitude larger. These students produce Matryoshka representations that are inexpensive to serve: a 16-dimensional prefix keeps 92% of the full 128-dimensional performance at 1/8 of the storage. Upon completion of training we plan to release v2 global embeddings covering 2017-2025. Together, these results give a concrete, empirically grounded recipe for scaling pixel-wise EO foundation models: train large encoders, select by downstream performance, and distil into flexible student models. All code will be released at https://github.com/ucam-eo/tessera. DOI: 10.48550/arXiv.2607.03949 Classification: preprint Venue: arXiv URL: http://arxiv.org/abs/2607.03949 ## Related - [Celebrating a year of Tessera embeddings and releasing GeoTessera 0.10](https://anil.recoil.org/notes/geotessera-a-year-on) (note, 2026-08-27) - [.plan-26-34: Am I human or am I antibotty](https://anil.recoil.org/notes/2026w34) (note, 2026-08-23) - [.plan-26-33: Zarro rides out and evidence papers pour in](https://anil.recoil.org/notes/2026w33) (note, 2026-08-16) - [Improving local weather forecasts using Tessera embeddings](https://anil.recoil.org/notes/weather-downscaling-tessera) (note, 2026-08-13) - [.plan-26-31: Sorting out Tessera and Evidence TAP infrastructure](https://anil.recoil.org/notes/2026w31) (note, 2026-08-02) - [Generative detection of ghost roads with Tessera embeddings](https://anil.recoil.org/ideas/tessera-ghost-roads) (idea, 2026-08-01) - [Global habitat maps from Tessera embeddings](https://anil.recoil.org/ideas/tessera-habitat-maps) (idea, 2026-08-01) - [Generating potential natural vegetation maps under contemporary climate with Tessera](https://anil.recoil.org/ideas/tessera-pnv) (idea, 2026-08-01) - [.plan-26-30: Bananas ripen, models open, and OxCaml releases](https://anil.recoil.org/notes/2026w30) (note, 2026-07-26) - [.plan-26-29: Perfect weather, imperfectly measured, precisely predicted](https://anil.recoil.org/notes/2026w29) (note, 2026-07-19) - [.plan-26-28: What fun papers piled up while I was out at sea](https://anil.recoil.org/notes/2026w28) (note, 2026-07-12) - [TESSERA, a pixelwise geospatial foundation model](https://anil.recoil.org/projects/tessera) (project, 2025-01-01) --- Canonical: https://anil.recoil.org/papers/2026-tessera-v2 Type: paper License: CC BY 4.0 Tags: preprint