Targeted Semantic Segmentation of Himalayan Glacial Lakes Using Time-Series SAR: Towards Automated GLOF Early Warning
This work addresses the need for automated early warning systems for Glacial Lake Outburst Floods, a critical climate change hazard, though it is incremental as it builds on existing remote sensing and deep learning methods.
The paper tackles the problem of monitoring high-risk Himalayan glacial lakes for early warning of floods by developing an automated deep learning pipeline using time-series SAR data, achieving an IoU of 0.9130 on a dataset of four lakes.
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.