Title: Understanding Regional Ice Sheet Mass Balance: Remote Sensing, Regional Climate Models, and Deep Learning
Abstract: The Antarctic and Greenland ice sheets are experiencing significant mass change with heterogeneous spatial and temporal characteristics and global consequences such as sea level rise affecting millions of people in low-lying coastal areas. Advances in large-scale satellite remote-sensing, modeling, and machine learning have ushered a new era of improved monitoring and understanding of these changes. In this dissertation, we analyze the mass balance of glaciers across the ice sheets using satellite gravimetric data from the Gravity Recovery and Climate Experiment (GRACE) mission and Mass Budget Method (MBM) estimates from grounding line discharge measurements and surface mass balance from regional climate models, and discuss any differences and the underlying processes. We develop a novel approach to process GRACE spherical harmonics based on a regionally-optimized spherical cap mascon approach to assess the mass balance of glaciers at basin or sub-basin scales. We focus on several Antarctic regions with large sea level rise potential, relatively high uncertainty, and previous discrepancies between various gravimetric and MBM estimates. In addition to evaluating the mass balance of these regions at a regional level, we evaluate various regional climate models and outline the discrepancies, focusing on recent developments in models that may require further analysis. In addition, we focus on the calving behavior of glaciers with the application of deep learning on satellite imagery products. Understanding the processes affecting the mass balance of glaciers requires continuous and wide-scale monitoring of their dynamics. To that end, we implement a deep Convolutional Neural Network (CNN) architecture to automatically delineate glacier calving fronts from Landsat imagery on the Greenland Ice Sheet and achieve performance comparable to manual delineation by human investigators, demonstrating the potential for CNNs to enable large-scale monitoring of glacier calving fronts across the ice sheets. Ultimately, a better understanding of the ice sheets is crucial for a better assessment of the effects of a changing cryosphere and sea level rise around the globe.