Toward a Global SAR Foundation Model for SAR-to-Spectral-Indices Mapping

Ziyi Song, Noel Ivan Ulloa, Juntao Yang, Sang-Ho Yun

Submission Type: I want my submission to be considered for poster only

Keywords: multitemporal synthetic aperture radar, remote sensing, Earth observation, foundation models, Vision Transformers, self-supervised learning, transfer learning, spectral indices

TL;DR: We develop a global SAR foundation model using masked autoencoding on Sentinel-1 data and demonstrate its transferability for cross-modal SAR-to-optical spectral indices mapping.

Confirmation Of Submission Requirements: I submit an abstract. It uses the template provided on the submission page and is no longer than 2 pages.

Submission Number: 50