用时序SAR数据自动监测喜马拉雅冰湖，提升冰湖溃决预警能力
Targeted Semantic Segmentation of Himalayan Glacial Lakes Using Time-Series SAR: Towards Automated GLOF Early Warning
- 采用时间优先训练策略，结合高效网络结构进行精准分割
- 在4个重点冰湖上实现0.913的交并比，验证方法有效性
- 构建可部署的自动化系统，适合灾害预警与长期监测场景
冰川湖溃决洪水（GLOFs）是气候变化引发的最严重灾害之一。现有遥感监测方法通常侧重于扩大空间覆盖以训练通用模型，或依赖受持续云层遮蔽影响的光学影像。本文提出一种端到端的自动化深度学习流程，利用时序哨兵-1 SAR数据对高风险喜马拉雅冰湖进行靶向监测。引入“时间优先”训练策略，采用基于EfficientNet-B3主干的U-Net模型，在包含4个湖泊（特肖罗拉湖、查姆朗湖、蒂利乔湖和戈科湖）的精选数据集上进行训练。模型在验证中取得0.9130的交并比，证明“时间优先”策略的有效性，为早期预警系统转化奠定基础。此外，我们设计了一套工程化架构：基于Docker的流水线，通过ASF搜索API自动获取数据，并通过RESTful接口提供推理结果。该系统推动监测范式从静态制图转向动态自动化预警，为早期预警系统的未来发展提供可扩展的架构基础。
原文摘要 · Abstract (English)
Glacial Lake Outburst Floods (GLOFs) are one of the most devastating climate change induced hazards. Existing remote monitoring approaches often prioritise maximising spatial coverage to train generalistic models or rely on optical imagery hampered by persistent cloud coverage. This paper presents an end-to-end, automated deep learning pipeline for the targeted monitoring of high-risk Himalayan glacial lakes using time-series Sentinel-1 SAR. We introduce a "temporal-first" training strategy, utilising a U-Net with an EfficientNet-B3 backbone trained on a curated dataset of a cohort of 4 lakes (Tsho Rolpa, Chamlang Tsho, Tilicho and Gokyo Lake). The model achieves an IoU of 0.9130 validating the success and efficacy of the "temporal-first" strategy required for transitioning to Early Warning Systems. Beyond the model, we propose an operational engineering architecture: a Dockerised pipeline that automates data ingestion via the ASF Search API and exposes inference results via a RESTful endpoint. This system shifts the paradigm from static mapping to dynamic and automated early warning, providing a scalable architectural foundation for future development in Early Warning Systems.
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。