Synthetic Aperture Radar (SAR) imagery is the primary data type used for sea ice mapping due to its spatiotemporal coverage and the ability to detect sea ice independent of cloud and lighting conditions. Automatic sea ice detection using SAR imagery remains problematic due to the presence of ambiguous signal and noise within the image. Conversely, ice and water are easily distinguishable using multispectral imagery (MSI), but in the polar regions the ocean's surface is often occluded by cloud or the sun may not appear above the horizon for many months. To address some of these limitations, this paper proposes a new tool trained using concurrent multispectral Visible and SAR imagery for sea Ice Detection (ViSual_IceD). ViSual_IceD is a convolution neural network (CNN) that builds on the classic U-Net architecture by containing two parallel encoder stages, enabling the fusion and concatenation of MSI and SAR imagery containing different spatial resolutions. The performance of ViSual_IceD is compared with U-Net models trained using concatenated MSI and SAR imagery as well as models trained exclusively on MSI or SAR imagery. ViSual_IceD outperforms the other networks, with a F1 score 1.30% points higher than the next best network, and results indicate that ViSual_IceD is selective in the image type it uses during image segmentation. Outputs from ViSual_IceD are compared to sea ice concentration products derived from the AMSR2 Passive Microwave (PMW) sensor. Results highlight how ViSual_IceD is a useful tool to use in conjunction with PMW data, particularly in coastal regions. As the spatial-temporal coverage of MSI and SAR imagery continues to increase, ViSual_IceD provides a new opportunity for robust, accurate sea ice coverage detection in polar regions.

中文翻译：

---

使用并发多光谱和合成孔径雷达图像进行海冰探测

合成孔径雷达 (SAR) 图像是用于海冰测绘的主要数据类型，因为它具有时空覆盖范围，并且能够独立于云和照明条件检测海冰。由于图像中存在模糊信号和噪声，使用 SAR 图像进行自动海冰检测仍然存在问题。相反，使用多光谱图像 (MSI) 可以轻松区分冰和水，但在极地地区，海洋表面经常被云遮挡，或者太阳可能好几个月都不会出现在地平线上方。为了解决其中的一些限制，本文提出了一种使用并发多光谱可见光和 SAR 图像进行海冰检测训练的新工具 (ViSual_IceD)。 ViSual_IceD 是一种基于经典 U-Net 架构的卷积神经网络 (CNN)，包含两个并行编码器级，能够融合和串联包含不同空间分辨率的 MSI 和 SAR 图像。将 ViSual_IceD 的性能与使用串联 MSI 和 SAR 图像训练的 U-Net 模型以及仅在 MSI 或 SAR 图像上训练的模型进行比较。 ViSual_IceD 优于其他网络，F1 分数比次优网络高 1.30%，结果表明 ViSual_IceD 在图像分割过程中使用的图像类型具有选择性。将 ViSual_IceD 的输出与 AMSR2 无源微波 (PMW) 传感器得出的海冰浓度产品进行比较。结果凸显了 ViSual_IceD 如何成为与 PMW 数据结合使用的有用工具，特别是在沿海地区。随着 MSI 和 SAR 图像的时空覆盖范围不断增加，ViSual_IceD 为极地地区稳健、准确的海冰覆盖范围检测提供了新的机会。