发表机构
University of Colorado Denver; National Snow and Ice Data Center (NSIDC), CIRES, University of Colorado Boulder（科罗拉多大学丹佛分校; 国家冰雪数据中心（NSIDC），科罗拉多大学博尔德分校环境科学合作研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出基于多实例学习和多标签比例学习的弱监督框架，直接利用多边形级冰图标签预测海冰类型，避免标签近似，显著提升精度。
AI 中文摘要
海冰类型预测对于气候监测、海上航行和极地地区的决策至关重要。该任务标签数据的主要来源是冰图，由冰分析师人工制作，他们解读卫星图像，将冰区划分为多边形。尽管冰图很有价值，但其制作劳动密集且成本高昂，这促使近期利用深度学习实现自动化的工作。然而，深度学习模型需要补丁级（或像素级）标签数据进行训练，而冰图仅提供多边形级标注。作为一种变通方法，监督方法通常通过将每个样本分配为其父多边形的优势冰类型，从多边形级冰图标签创建近似的补丁级标签。这种方法实现了监督训练，但产生了一个不适定的学习问题，其解本质上是近似的。在本文中，我们将海冰类型预测重新定义为一个弱监督的多标签比例学习问题，以便直接使用多边形级冰图标签，避免不必要的标签近似，从而提高预测精度。为解决此问题，我们提出了一个两模块框架，首先使用多实例学习（MIL）进行水-冰分类，然后引入多标签比例学习（MLPL）进行冰类型组成预测。我们进一步通过多模态模型扩展该框架，该模型通过模态引导的辅助正则化整合SAR图像与AMSR2亮度温度和ERA5再分析数据。在AI4Arctic数据集上的评估中，仅SAR模型将MAE降低了14.5%，并将平均冰类F1分数比最佳监督基线提高了一倍以上。多模态模型进一步将MAE降低了21.5%，平均F1比仅SAR模型提高了41.2%，比监督多模态基线提高了52.7%。
英文摘要
Sea-ice type prediction is important for climate monitoring, maritime navigation, and decision-making in polar regions. The main source of label data for this task is the ice chart, produced manually by ice analysts who interpret satellite imagery to delineate ice zones into polygons. Although ice charts are valuable, their production is labor-intensive and expensive, motivating recent efforts to automate the process using deep learning. However, deep learning models require patch-level (or pixel-level) label data for training, while ice charts provide only polygon-level annotations. As a workaround, supervised approaches often create approximate patch-level labels from polygon-level ice chart labels by assigning each sample the dominant ice type of its parent polygon. This approach enables supervised training but creates an ill-posed learning problem with intrinsically approximate solution. In this paper, we redefine sea-ice type prediction as a weakly supervised multi-label proportion learning problem to be able to directly use the polygon-level ice chart labels and avoid unnecessary label approximation for improved prediction accuracy. To address this problem, we propose a two-module framework where first Multiple Instance Learning (MIL) is used for water--ice classification, and then a multi-label proportion learning (MLPL) is introduced for ice-type composition prediction. We further extend this framework with a multimodal model that integrates SAR imagery with AMSR2 brightness temperatures and ERA5 reanalysis data through modality-guided auxiliary regularization. Evaluated on the AI4Arctic dataset, the SAR-only model reduces MAE by 14.5\% and more than doubles mean ice-class F1 over the best supervised baseline. The multimodal model further reduces MAE by 21.5\% and raises mean F1 by 41.2\% over the SAR-only model, and by 52.7\% over the supervised multimodal baseline.
