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

2025-05-29

AI Summary

Sparse and highly uncertain observations hinder accurate subglacial topography estimation for the Greenland Ice Sheet, limiting sea-level rise projections. To address this, we propose a deep learning framework that fuses airborne radar ice-thickness measurements with the BedMachine v4 prior product. Our method introduces a dynamically weighted loss function to adaptively balance contributions from heterogeneous data sources; incorporates gradient and trend-surface features to enhance large-scale topographic modeling; and designs a dedicated CNN architecture tailored for sub-grid-resolution reconstruction, embedded with physical constraints derived from glaciological mass conservation. Evaluated over the Upernavik Isstrøm region, our approach significantly outperforms baseline models, robustly interpolating radar gaps spanning tens of kilometers while achieving high accuracy and generalizability in bed topography reconstruction. The resulting high-fidelity bed elevation maps provide reliable boundary conditions for ice-sheet dynamical simulations and improved sea-level rise assessments.

Technology Category

• Machine Learning: Learning with Manifolds
• Intelligent Robots: State Estimation
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• Estimating Greenland's subglacial topography for ice loss projections
• Addressing data gaps in radar-derived ice thickness measurements
• Integrating sparse observations with high-resolution BedMachine data

Innovation

• Deep learning integrates radar and BedMachine data
• Dynamic loss-balancing enhances robustness and resolution
• CNN architecture improves subgrid-scale prediction accuracy