Boundary Aware U-Net for Glacier Segmentation

TL;DR

This paper introduces a boundary-aware U-Net model with a novel loss function and feature analysis for improved glacier segmentation in Landsat 7 images, aiding climate change studies.

Contribution

It presents a modified U-Net architecture, a self-learning boundary-aware loss, and a feature saliency method for glacier segmentation in remote sensing images.

Findings

Boundary-aware U-Net outperforms standard models.

Red, shortwave infrared, and near-infrared bands are most important.

Self-learning boundary loss improves debris-covered glacier segmentation.

Abstract

Large-scale study of glaciers improves our understanding of global glacier change and is imperative for monitoring the ecological environment, preventing disasters, and studying the effects of global climate change. Glaciers in the Hindu Kush Himalaya (HKH) are particularly interesting as the HKH is one of the world's most sensitive regions for climate change. In this work, we: (1) propose a modified version of the U-Net for large-scale, spatially non-overlapping, clean glacial ice, and debris-covered glacial ice segmentation; (2) introduce a novel self-learning boundary-aware loss to improve debris-covered glacial ice segmentation performance; and (3) propose a feature-wise saliency score to understand the contribution of each feature in the multispectral Landsat 7 imagery for glacier mapping. Our results show that the debris-covered glacial ice segmentation model trained using self-learning boundary-aware loss outperformed the model trained using dice loss. Furthermore, we conclude that red, shortwave infrared, and near-infrared bands have the highest contribution toward debris-covered glacial ice segmentation from Landsat 7 images.