# Learning Subglacial Bed Topography from Sparse Radar with Physics-Guided Residuals

arXiv: https://arxiv.org/abs/2511.14473 · HTML: https://mlsanity.com/paper/2511.14473/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 39 references that are in the map.
- First posted on arXiv 18 Nov 2025.

## Builds on (most cited first, 14 of 14)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [Panoptic Feature Pyramid Networks](https://mlsanity.com/paper/1901.02446/) (2019)
- [Dilated Residual Networks](https://mlsanity.com/paper/1705.09914/) (2017)
- [Kriging Convolutional Networks](https://mlsanity.com/paper/2306.09463/) (2023)
- [Critical Features Tracking on Triangulated Irregular Networks by a Scale-Space Method](https://mlsanity.com/paper/2409.06638/) (2024)
- [DeepTopoNet: A Framework for Subglacial Topography Estimation on the Greenland Ice Sheets](https://mlsanity.com/paper/2505.23980/) (2025)
- [Improving Greenland Bed Topography Mapping with Uncertainty-Aware Graph Learning on Sparse Radar Data](https://mlsanity.com/paper/2509.08571/) (2025)

## Abstract (arXiv)

Accurate subglacial bed topography is essential for ice sheet modeling, yet radar observations are sparse and uneven. We propose a physics-guided residual learning framework that predicts bed thickness residuals over a BedMachine prior and reconstructs bed from the observed surface. A DeepLabV3+ decoder over a standard encoder (e.g.,ResNet-50) is trained with lightweight physics and data terms: multi-scale mass conservation, flow-aligned total variation, Laplacian damping, non-negativity of thickness, a ramped prior-consistency term, and a masked Huber fit to radar picks modulated by a confidence map. To measure real-world generalization, we adopt leakage-safe blockwise hold-outs (vertical/horizontal) with safety buffers and report metrics only on held-out cores. Across two Greenland sub-regions, our approach achieves strong test-core accuracy and high structural fidelity, outperforming U-Net, Attention U-Net, FPN, and a plain CNN. The residual-over-prior design, combined with physics, yields spatially coherent, physically plausible beds suitable for operational mapping under domain shift.