Home  | Publications | WXL+25

Towards a Unified Copernicus Foundation Model for Earth Vision

MCML Authors

Link to Profile Xiaoxiang Zhu PI Matchmaking

Xiaoxiang Zhu

Prof. Dr.

Principal Investigator

Data Science in Earth Observation

Abstract

Advances in Earth observation (EO) foundation models have unlocked the potential of big satellite data to learn generic representations from space, benefiting a wide range of downstream applications crucial to our planet. However, most existing efforts remain limited to fixed spectral sensors, focus solely on the Earth's surface, and overlook valuable metadata beyond imagery. In this work, we take a step towards next-generation EO foundation models with three key components: 1) Copernicus-Pretrain, a massive-scale pretraining dataset that integrates 18.7M aligned images from all major Copernicus Sentinel missions, spanning from the Earth's surface to its atmosphere; 2) Copernicus-FM, a unified foundation model capable of processing any spectral or non-spectral sensor modality using extended dynamic hypernetworks and flexible metadata encoding; and 3) Copernicus-Bench, a systematic evaluation benchmark with 15 hierarchical downstream tasks ranging from preprocessing to specialized applications for each Sentinel mission. Our dataset, model, and benchmark greatly improve the scalability, versatility, and multimodal adaptability of EO foundation models, while also creating new opportunities to connect EO, weather, and climate research.

inproceedings

ICCV 2025

IEEE/CVF International Conference on Computer Vision. Honolulu, Hawai'i, Oct 19-23, 2025. To be published. Preprint available.
Conference logo
A* Conference

Authors

Y. Wang • Z. Xiong • C. Liu • A. J. Stewart • T. Dujardin • N. I. Bountos • A. Zavras • F. Gerken • I. Papoutsis • L. Leal-Taixé • X. Zhu

Links

GitHub

Research Areas

 B1 | Computer Vision

 C3 | Physics and Geo Sciences

BibTeXKey: WXL+25

Back to Top