提出新评估框架，让野火预测模型的不确定性更贴近实际救灾需求。
Boundary-Aware Uncertainty Quantification for Wildfire Spread Prediction
- 设计空间约束评估框架，聚焦野火关键区域的不确定性
- 单次推理学生模型在边界区域与集成模型效果相当
- 适合应急规划、灾害管理等实战场景使用
可靠的野火蔓延预测对风险导向的应急规划至关重要，但大多数深度学习模型缺乏合理的不确定性量化（UQ）。对于野火蔓延这类边界敏感的问题，仅用全局指标评估模型往往不够。为此，本文引入火点中心评估区域（FCER）框架，作为一种空间条件化的评估协议，用于刻画关键火区内的不确定性。基于该框架，在WildfireSpreadTS数据集上对比了集成模型与蒸馏后的单次推理学生模型。结果表明，学生模型在边界相关场景下具备相近的校准能力，并呈现互补的不确定性排序。代码已公开于 https://github.com/jonasvilhofunk/WildfireUQ-FCER。
原文摘要 · Abstract (English)
Reliable wildfire spread prediction is vital for risk-aware emergency planning, yet most deep learning models lack principled uncertainty quantification (UQ). Further, for boundary-sensitive cases like wildfire spread, evaluating models with global metrics alone is often insufficient. To shift the focus of UQ evaluation toward a more operationally relevant approach, the Fire-Centered Evaluation Region (FCER) framework is introduced as a spatially conditioned protocol to characterize UQ within critical fire zones. Using FCER, an Ensemble is compared against an distilled single-pass student model on the WildfireSpreadTS dataset. The student model demonstrates comparable calibration and complementary uncertainty ranking in boundary-relevant regimes. Code is available at https://github.com/jonasvilhofunk/WildfireUQ-FCER
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。