{"ID":2842306,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.10370","arxiv_id":"2511.10370","title":"SHRUG-FM: Reliability-Aware Foundation Models for Earth Observation","abstract":"Geospatial foundation models (GFMs) for Earth observation often fail to perform reliably in environments underrepresented during pretraining. We introduce SHRUG-FM, a framework for reliability-aware prediction that enables GFMs to identify and abstain from likely failures. Our approach integrates three complementary signals: geophysical out-of-distribution (OOD) detection in the input space, OOD detection in the embedding space, and task-specific predictive uncertainty. We evaluate SHRUG-FM across three high-stakes rapid-mapping tasks: burn scar segmentation, flood mapping, and landslide detection. Our results show that SHRUG-FM consistently reduces prediction risk on retained samples, outperforming established single-signal baselines like predictive entropy. Crucially, by utilizing a shallow \"glass-box\" decision tree for signal fusion, SHRUG-FM provides interpretable abstention thresholds. It builds a pathway toward safer and more interpretable deployment of GFMs in climate-sensitive applications, bridging the gap between benchmark performance and real-world reliability.","short_abstract":"Geospatial foundation models (GFMs) for Earth observation often fail to perform reliably in environments underrepresented during pretraining. We introduce SHRUG-FM, a framework for reliability-aware prediction that enables GFMs to identify and abstain from likely failures. Our approach integrates three complementary si...","url_abs":"https://arxiv.org/abs/2511.10370","url_pdf":"https://arxiv.org/pdf/2511.10370v2","authors":"[\"Maria Gonzalez-Calabuig\",\"Kai-Hendrik Cohrs\",\"Vishal Nedungadi\",\"Zuzanna Osika\",\"Ruben Cartuyvels\",\"Steffen Knoblauch\",\"Joppe Massant\",\"Shruti Nath\",\"Patrick Ebel\",\"Vasileios Sitokonstantinou\"]","published":"2025-11-13T14:48:55Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\",\"cs.LG\"]","methods":"[]","has_code":false}