TESSERA: A Foundation Model for Label-Efficient and Multi-Modal EO at Scale ( Zhengpeng Feng)

“TESSERA: A Foundation Model for Label-Efficient and Multi-Modal Earth Observation at Scale” by Zhengpeng (Frank) Feng The Open-Earth Monitor Global Workshop 2026 "Next-Generation EO & GeoAI Built on Openness and Distributed Data" 7-9 October 2026, Barcelona, Spain https://earthmonitor.org/global-workshop-2026/ Satellite Earth Observation (EO) time series are fundamental to monitoring our planet's changing environment. However, inconsistent revisit times and frequent cloud obstruction in optical data (Sentinel-2) often force practitioners to rely on lossy data compositing, which discards critical phenological information. In this keynote, we introduce TESSERA (Temporal Embeddings of Surface Spectra for Earth Representation and Analysis), a pixel-wise foundation model designed to overcome these challenges. TESSERA leverages multi-modal fusion of Sentinel-1 (radar) and Sentinel-2 (optical) data, employing a self-supervised learning framework based on Barlow Twins and random temporal sampling. This approach ensures high robustness to irregular sampling and missing data without requiring expensive ground-truth labels. A key highlight of TESSERA is its scale and commitment to Open Science: trained on a global dataset spanning 2017–2025, the model provides high-dimensional temporal embeddings that capture the "spectral fingerprint" of the Earth's surface. In alignment with the FAIR principles, we are committed to making TESSERA an open-access resource for the community. We will demonstrate how TESSERA achieves state-of-the-art performance in downstream tasks such as crop type mapping and land cover classification with minimal labeled data, paving the way for the next generation of open-source, distributed GeoAI monitoring systems.