让遥感大模型学会识别不确定预测，避免在不靠谱时乱下结论。
SHRUG-FM: Reliability-Aware Foundation Models for Earth Observation
- 融合输入、特征和任务三类异常信号，判断模型是否该放弃预测。
- 在火灾、洪水、滑坡三类任务中，保留样本的预测风险显著降低。
- 用透明决策树给出可解释的弃权阈值，适合气候敏感场景使用。
面向地球观测的地理空间基础模型（GFMs）在预训练数据未覆盖的环境中常表现不可靠。本文提出SHRUG-FM，一种可靠性感知预测框架，使GFMs能识别并拒绝可能出错的预测。该方法整合三类互补信号：输入空间中的地物物理分布外（OOD）检测、嵌入空间中的OOD检测，以及任务特定的预测不确定性。我们在三个高风险快速制图任务——烧伤区域分割、洪涝制图与滑坡检测上评估了SHRUG-FM。结果表明，该框架在保留样本上持续降低预测风险，优于仅使用预测熵等单一信号的基线方法。关键在于，通过一个浅层“白盒”决策树融合信号，实现可解释的弃权阈值设定，为气候敏感应用中更安全、更透明的GFMs部署提供可行路径，弥合基准性能与真实可靠性之间的差距。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。