Abstract

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 talk, Zhengpeng (Frank) Feng introduces 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 2017–2024, the model provides high-dimensional temporal embeddings that capture the "spectral fingerprint" of the Earth's surface. In alignment with the FAIR principles, the team are committed to making TESSERA an open-access resource for the community. Zhengpeng will demonstrate how TESSERA achieves state-of-the-art performance in downstream tasks such as crop type mapping and land cover classification with minimal labelled data, paving the way for the next generation of open-source, distributed GeoAI monitoring systems.

About Zhengpeng (Frank) Feng

Zhengpeng (Frank) Feng is a second-year Ph.D. candidate in the Energy and Environment Group, Department of Computer Science and Technology, at the University of Cambridge. His research interests lie at the intersection of machine learning and earth sciences, with a particular focus on developing self-supervised learning methods in remote sensing.

About the PIXEL Seminar Series

Satellite imagery offers unprecedented opportunities to better understand human activity and its impact upon the environment. People, Insights, and eXploration in Earth observation and Learning (PIXEL) is a forum for researchers to showcase their work that explores satellite imagery and related approaches.

Hosted by Imago, the PIXEL Seminar Series fosters a global Community of Practice through monthly technical and applied seminars that demystify satellite data for research and policy. These seminars aim to make satellite imagery more useful, usable, and used across social research, public health, and policy by demystifying methods, tools, and use cases.