Feng et al. (2025) A Remote Sensing-Driven Dynamic Risk Assessment Model for Cyclical Glacial Lake Outbursts: A Case Study of Merzbacher Lake

⚠️ Warning: This summary was generated from the abstract only, as the full text was not available.

Identification

• Journal: Remote Sensing
• Year: 2025
• Date: 2025-12-24
• Authors: Tianshi Feng, Wenlong Song, Xingdong Li, Yizhu Lu, Kaizheng Xiang, Shaobo Linghu, Hongjie Liu, Long Chen
• DOI: 10.3390/rs18010047

Research Groups

Not explicitly mentioned in the provided text.

Short Summary

This study develops and validates a dynamic, remote sensing-driven framework for Glacial Lake Outburst Flood (GLOF) risk assessment at Lake Merzbacher, utilizing an innovative Ice-Water Composite Index and a Random Forest model to accurately predict lake volume and identify Positive Accumulated Temperature as the dominant hydrological driver.

Objective

• To develop and validate a dynamic, remote sensing-driven risk assessment framework for Glacial Lake Outburst Floods (GLOFs) in data-scarce alpine regions, specifically focusing on Lake Merzbacher, to enable site-specific early warning.

Study Configuration

• Spatial Scale: Lake Merzbacher basin in the Tien Shan mountains; Digital Elevation Model (DEM) at 5 meter resolution.
• Temporal Scale: Daily volume retrieval; focuses on near-annual cyclical outbursts and lake-filling cycles; model validated for 2023–2024.

Methodology and Data

• Models used: Random Forest (RF) machine learning model.
• Data sources: GF-7 Dual-Line Camera (DLC) imagery (for DEM generation), MODIS products, and other remote sensing products (for nine hydro-thermal drivers).

Main Results

• The Random Forest model demonstrated robust predictive performance on an independent validation set (2023–2024) with an R² of 0.80 and a Root Mean Square Error (RMSE) of 5.15 × 10⁶ m³.
• The model accurately captures the complete lake-filling cycle from initiation to near-peak stage.
• Feature importance analysis quantitatively confirmed that Positive Accumulated Temperature (PAT) is the dominant physical mechanism governing the lake’s storage dynamics.

Contributions

• Introduces an innovative, end-to-end framework for dynamic GLOF risk assessment driven entirely by remote sensing data, transferable to other data-scarce alpine regions.
• Develops the Ice-Water Composite Index (IWCI) to resolve the challenge of lake area extraction under mixed ice-water conditions.
• Enables a critical shift from static, regional GLOF hazard assessments to dynamic, site-specific early warning systems in data-scarce alpine environments.

Funding

Not explicitly mentioned in the provided text.

Citation

@article{Feng2025Remote,
  author = {Feng, Tianshi and Song, Wenlong and Li, Xingdong and Lu, Yizhu and Xiang, Kaizheng and Linghu, Shaobo and Liu, Hongjie and Chen, Long},
  title = {A Remote Sensing-Driven Dynamic Risk Assessment Model for Cyclical Glacial Lake Outbursts: A Case Study of Merzbacher Lake},
  journal = {Remote Sensing},
  year = {2025},
  doi = {10.3390/rs18010047},
  url = {https://doi.org/10.3390/rs18010047}
}