skip to content

Department of Computer Science and Technology

Date: 
Friday, 7 February, 2025 - 13:00 to 13:55
Speaker: 
Frank Feng, University of Cambridge
Venue: 
GS15, William Gates Building. Zoom link: https://cl-cam-ac-uk.zoom.us/j/4361570789?pwd=Nkl2T3ZLaTZwRm05bzRTOUUxY3Q4QT09&from=addon

*Abstract*

Satellite imagery provides a critical lens for monitoring Earth’s dynamic systems, yet integrating multi-source, multi-temporal data into globally consistent, high-resolution representations remains a challenge. Traditional remote sensing vision models, which process patches or images as inputs, often struggle to capture fine-grained spatiotemporal-spectral relationships critical for downstream tasks like land classification, climate modeling, and change detection. We present a self-supervised framework leveraging Barlow Twins to train an Earth Foundation Model that outputs pixel-level representations from diverse satellite data sources. Unlike conventional ML approaches, our model treats pixels as primary units of learning, explicitly optimizing for temporal-spectral coherence across billions of global 10m-resolution pixels. Preliminary results demonstrate that the resulting representation map encodes high-quality spatiotemporal patterns, outperforming traditional ML methods in land classification. By bridging multi-modal satellite data into a harmonized latent space, our approach unlocks new opportunities for monitoring planetary-scale processes with higher precision.

*Bio*

Frank Feng is a first-year PhD student in the 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 the application of self-supervised learning in remote sensing.

Seminar series: 
Energy and Environment Group

Upcoming seminars