Estimating Snow Line Altitude by Optical and SAR Data Fusion: Inverse-mapping Explainable Neural Network-Based Approach — Case Study of the Great Aletsch Glacier

Inhalt:
Accurate glacier surface classification is crucial for understanding glacier dynamics. In this study, we combine Sentinel-2 and Sentinel-1 data, using an explainable neural network to determine the Snow Line Altitude (SLA). This study focuses on the Great Aletsch Glacier, which, apart from facing mass loss, is also affected by the presence of Sahara dust. The proposed approach determines the SLA and the presence of Sahara dust on the glacier. We study the glacier for 2015, 2021 and 2023 and observe the retreat of the SLA to higher elevations by 36 to 133 m (depending on the region) between 2015 and 2023.