Multisensor Fusion and Deep Learning Approaches for Semantic Segmentation of Glacial Lakes: A Comparative Study for Coastal Hydrology Applications

Multisensor Fusion and Deep Learning Approaches for Semantic Segmentation of Glacial Lakes: A Comparative Study for Coastal Hydrology Applications

Monitoring glacial lakes is critical for assessing climate change impacts and mitigating glacial lake outburst flood risks. This study evaluates three deep learning architectures, U-Net, simple convolutional neural network (CNN), and atrous spatial pyramid pooling SegNet (ASPP SegNet), for binary se...

Full description

Saved in:
Bibliographic Details
Main Authors: Lingling Xue, Asad Khan, Muhammad Haseeb, Mourad Aqnouy, Dawood Ahmad, Refka Ghodhbani, Dmitry E. Kucher, Olga D. Kucher
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Atrous spatial pyramid pooling SegNet (ASPP SegNet)
coastal monitoring
deep learning
glacial lake
remote sensing
semantic segmentation
Online Access:https://ieeexplore.ieee.org/document/11021621/
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Monitoring glacial lakes is critical for assessing climate change impacts and mitigating glacial lake outburst flood risks. This study evaluates three deep learning architectures, U-Net, simple convolutional neural network (CNN), and atrous spatial pyramid pooling SegNet (ASPP SegNet), for binary semantic segmentation of glacial lakes using multisensor optical satellite imagery (Sentinel-2). Incorporating data augmentation and custom evaluation metrics (IoU, F1-score, validation loss), the results show that Simple CNN achieves the highest IoU (0.9155) and F1-score (0.9557). At the same time, ASPP SegNet demonstrates superior generalization with the lowest validation loss (0.03337). U-Net also delivers a reliable performance, albeit slightly lower. Visual and quantitative assessments highlight the advantage of multiscale, context-aware architectures in delineating fragmented lake boundaries. This comparative study provides practical guidance for deep learning model selection in remote sensing-based glacial and coastal hydrology monitoring. Future work will explore temporal modeling, multiclass segmentation, and the integration of optical, radar, and elevation data for improved resilience.
ISSN:1939-1404
2151-1535

Similar Items