DeepTopoNet: A Framework for Subglacial Topography Estimation on the Greenland Ice Sheets

TL;DR

DeepTopoNet is a deep learning framework that combines radar ice thickness data and BedMachine Greenland to accurately estimate subglacial topography, addressing data sparsity and improving projection models of ice sheet mass loss.

Contribution

It introduces a novel dynamic loss-balancing mechanism within a CNN architecture to integrate diverse data sources for subglacial topography estimation.

Findings

Outperforms baseline methods in the Upernavik region

Robustly handles areas with limited radar coverage

Enhances subglacial terrain reconstruction accuracy

Abstract

Understanding Greenland's subglacial topography is critical for projecting the future mass loss of the ice sheet and its contribution to global sea-level rise. However, the complex and sparse nature of observational data, particularly information about the bed topography under the ice sheet, significantly increases the uncertainty in model projections. Bed topography is traditionally measured by airborne ice-penetrating radar that measures the ice thickness directly underneath the aircraft, leaving data gap of tens of kilometers in between flight lines. This study introduces a deep learning framework, which we call as DeepTopoNet, that integrates radar-derived ice thickness observations and BedMachine Greenland data through a novel dynamic loss-balancing mechanism. Among all efforts to reconstruct bed topography, BedMachine has emerged as one of the most widely used datasets, combining mass conservation principles and ice thickness measurements to generate high-resolution bed elevation estimates. The proposed loss function adaptively adjusts the weighting between radar and BedMachine data, ensuring robustness in areas with limited radar coverage while leveraging the high spatial resolution of BedMachine predictions i.e. bed estimates. Our approach incorporates gradient-based and trend surface features to enhance model performance and utilizes a CNN architecture designed for subgrid-scale predictions. By systematically testing on the Upernavik Isstr{\o}m) region, the model achieves high accuracy, outperforming baseline methods in reconstructing subglacial terrain. This work demonstrates the potential of deep learning in bridging observational gaps, providing a scalable and efficient solution to inferring subglacial topography.