Improving Greenland Bed Topography Mapping with Uncertainty-Aware Graph Learning on Sparse Radar Data
This work addresses the need for accurate bed topography maps for sea-level projections, benefiting climate forecasting agencies, though it is incremental as it builds on existing graph-based methods with novel uncertainty handling.
The paper tackled the problem of mapping Greenland's subglacial bed from sparse radar data by introducing GraphTopoNet, a graph-learning framework that models uncertainty and fuses heterogeneous supervision, resulting in up to 60% error reduction compared to baselines while preserving fine-scale features.
Accurate maps of Greenland's subglacial bed are essential for sea-level projections, but radar observations are sparse and uneven. We introduce GraphTopoNet, a graph-learning framework that fuses heterogeneous supervision and explicitly models uncertainty via Monte Carlo dropout. Spatial graphs built from surface observables (elevation, velocity, mass balance) are augmented with gradient features and polynomial trends to capture both local variability and broad structure. To handle data gaps, we employ a hybrid loss that combines confidence-weighted radar supervision with dynamically balanced regularization. Applied to three Greenland subregions, GraphTopoNet outperforms interpolation, convolutional, and graph-based baselines, reducing error by up to 60 percent while preserving fine-scale glacial features. The resulting bed maps improve reliability for operational modeling, supporting agencies engaged in climate forecasting and policy. More broadly, GraphTopoNet shows how graph machine learning can convert sparse, uncertain geophysical observations into actionable knowledge at continental scale.