SOURCE-LINKED INTELLIGENCE

A Composition-Aware Pretraining Framework for Geospatial Foundation Models

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Geospatial foundation models have emerged as state-of-the-art methods for downstream Earth observation tasks. However, existing pretraining methodologies process imagery through a single-concept lens, failing to capture the highly compositional nature of complex satellite scenes. We propose a composition-aware pretraining framework that explicitly encodes fractional land-cover mixtures. Each satellite image cell is mapped to a histogram representing its fractional land-cover distribution, which we term the "composition target". These targets serve as the primary prediction objective and are di

Read original source ↗ Open in workspace

recordType

paper

region

Global