Automated Determination of Glacier Ablation Zones

Abstract

In recent decades, global temperature rises have significantly influenced glacier dynamics [1][2], underscoring the vital need for accurately delineating glacier boundaries to comprehend these shifts and document regional patterns. Despite this urgency, conventional methods struggle to map debris-covered glaciers (DCGs) due to their intricate nature. Climate change exacerbates glacier mass loss and intensifies glacier-related risks, necessitating ongoing monitoring and thorough analysis of climate-glacier interactions. Our research assesses the effectiveness of a convolutional neural network (CNN) in glacier mapping, utilizing Landsat satellite images, digital elevation models (DEMs), and DEM-derived land-surface parameters. Specifically, we seek to enhance the GlacierNet methodology by employing a CNN segmentation model to precisely identify regional DCG ablation zones. By training the models with satellite data from USGS and snow labeling from QGIS, and testing them on glaciers in the Karakoram region, we achieve improved estimations of the ablation zone, yielding high intersection over union scores. This study advances glacier mapping techniques, offering critical insights into climate change impacts on glacier dynamics in the Karakoram region. Furthermore, it marks a significant stride towards automating comprehensive glacier mapping, with potential applications in accurate glacier modeling and mass-balance analysis.