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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Tama, Bayu Adhi, Wang, Jianwu, Janeja, Vandana, Cham, Mostafa
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908662434365440
author Tama, Bayu Adhi
Wang, Jianwu
Janeja, Vandana
Cham, Mostafa
author_facet Tama, Bayu Adhi
Wang, Jianwu
Janeja, Vandana
Cham, Mostafa
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_14473
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Subglacial Bed Topography from Sparse Radar with Physics-Guided Residuals
Tama, Bayu Adhi
Wang, Jianwu
Janeja, Vandana
Cham, Mostafa
Computer Vision and Pattern Recognition
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.
title Learning Subglacial Bed Topography from Sparse Radar with Physics-Guided Residuals
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.14473