Ice Thickness From Deep Learning and Conditional Random Fields: Application to Ice-Penetrating Radar Data With Radiometric Validation
Ice Thickness From Deep Learning and Conditional Random Fields: Application to Ice-Penetrating Radar Data With Radiometric Validation
复制标题
DOI：
10.1109/tgrs.2022.3214147
复制
发表时间：
2022
影响因子：
8.2
通讯作者：
Miguel Liu-Schiaffini;G. Ng;C. Grima;D. Young
中科院分区：
文献类型：
--
作者：
Miguel Liu-Schiaffini;G. Ng;C. Grima;D. Young
确定冰川和冰盖的冰-基岩界面的位置对于广泛的地球物理应用至关重要，例如在基底区域寻找液态水和计算冰厚度以量化冰盖和冰川质量平衡。简单的，逐个记录的方法来检测冰回波的底部可能会受到虚假的偏离最低点的噪音，需要大量的手动交互来纠正。在本文中，我们提出了一种基于卷积神经网络（CNN）和连续条件随机场（CCRF）的深度学习模型，以自动识别冰层并更好地捕获细粒度的基础细节。我们将这种方法部署在高性能雷达测深仪（HiCARS）雷达图上，这是深度学习方法首次应用于该数据集。直观地说，我们的CNN捕捉到了冰床的全局几何形状，而CCRF则调整了CNN的初始输出，以更好地将精细尺度的空间信息融入到最终的预测中。我们还开发了一个连贯的地球物理框架，使用三个回波字符（沿跟踪连续性，相对延迟，和信号相干性）比较我们的模型的输出与手动有针对性的方法。我们的分析表明，我们的CNN + CCRF模型与辐射测量应用的手动方法一样适合，并且在识别第一个连续返回（通常是近底反射）方面优于手动技术。因此，我们的方法比当前的手动标记方法在可以使用的地球物理应用范围内更通用，并且它提供了关于检测到的基础返回的来源的更好的置信度。
Identifying the location of the ice–bedrock interface of glaciers and ice sheets is crucial for a wide range of geophysical applications, such as searching for liquid water in basal regions and computing ice thickness to quantify ice sheet and glacier mass balance. Simple, record-by-record, approaches to detecting the bottom of the ice echo may be affected by spurious off-nadir noise that requires significant manual interaction to correct. In this article, we propose a deep learning model based on convolutional neural networks (CNNs) and continuous conditional random fields (CCRFs) to automate ice bed identification and better capture fine-grained basal detail. We deploy this approach on high-capability radar sounder (HiCARS) radargrams, and this is the first time deep learning methods have been applied to this dataset. Intuitively, our CNN captures the global geometry of the ice bed, while the CCRF adjusts the initial CNN outputs to better incorporate fine-scale spatial information into the final prediction. We also develop a coherent geophysical framework using three echo characters (along-track continuity, relative delay, and signal coherency) to compare our model’s outputs with those of a manually targeted approach. Our analysis suggests that our CNN + CCRF model is as suitable as the manual approach for radiometric applications, and it outperforms the manual technique in identifying the first continuous return, which is most often the near-nadir reflection. Thus, our approach is more universal than the current manual labeling methodology in the range of geophysical applications where it can be used, and it provides better confidence regarding the source of the basal return detected.