Navigation-Risk-Aware Ordinal Segmentation for SAR Sea-Ice Stage-of-Development Mapping
Authors:
- Wannian LiWLWannian Li
- Yudi WangYWYudi Wang
- Huanhao LiaoHLHuanhao Liao
- Yifang LuoYLYifang Luo
- Hang DiaoHDHang Diao
- Jiale ChenJCJiale Chen
- Zixiong MaZMZixiong Ma
- Ziyi ZhuZZZiyi Zhu
- Yihe WangYWYihe Wang
- Fan ZhangFZFan Zhang
Preprint
- 25 July 2026
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
Sea-ice stage-of-development (SOD) mapping from synthetic aperture radar (SAR) is a key input for polar navigation safety. Existing deep-learning methods treat SOD as ordinary multi-class segmentation and optimize accuracy alone. However, SOD classes are intrinsically ordinal, from open water to multi-year ice, and their errors are asymmetric for navigation: underestimating ice severity is far more dangerous than overestimating it. We propose a navigation-risk-aware ordinal segmentation framework that makes this asymmetry an explicit learning target. An asymmetric navigation cost matrix encodes ordinal distance and underestimation risk; complementary safety metrics expose the operational risk that accuracy cannot capture; and the cost matrix is injected into both the loss and the inference decision, comparing matrix-expected-risk, asymmetric-soft-label, ordinal Brier and CORAL losses against Bayes-minimum-risk and CVaR decoding on a shared SAR backbone. On a Sentinel-1 dataset, a lightweight cost-aware auxiliary loss, CE+0.2 MERL, Pareto-dominates both a standard cross-entropy baseline and a strong cost-aware Bayes-risk decoder, improving F1 by 1.19 points and mIoU by 1.51 points while reducing expected navigation cost by ~28.2% and the underestimation rate by ~40.4%. Encoding safety asymmetry into training rather than only into the decision rule yields models that are both more accurate and safer for operational ice charting.Keywords
This publication has 16 references indexed in Scilit:
- Sea Ice Segmentation from SAR Data by Convolutional Transformer Networks2023
- Deep neural networks for rank-consistent ordinal regression based on conditional probabilitiesPattern Analysis and Applications, 2023
- Rank consistent ordinal regression for neural networks with application to age estimationPattern Recognition Letters, 2020
- Efficient Thermal Noise Removal for Sentinel-1 TOPSAR Cross-Polarization ChannelIEEE Transactions on Geoscience and Remote Sensing, 2017
- Cost-Sensitive Learning of Deep Feature Representations From Imbalanced DataIEEE Transactions on Neural Networks and Learning Systems, 2017
- Sea Ice Concentration Estimation During Melt From Dual-Pol SAR Scenes Using Deep Convolutional Neural Networks: A Case StudyIEEE Transactions on Geoscience and Remote Sensing, 2016
- Classification of Sea Ice Types in ENVISAT Synthetic Aperture Radar ImagesIEEE Transactions on Geoscience and Remote Sensing, 2012
- GMES Sentinel-1 missionRemote Sensing of Environment, 2012
- MetaCost1999
- Textural Features for Image ClassificationIEEE Transactions on Systems, Man, and Cybernetics, 1973