The twin Sentinel‐1 (S1) satellites have been extensively acquiring synthetic aperture radar (SAR) data in the Arctic, providing the unique opportunity to obtain ocean dynamic parameters with both high spatial resolution and wide swath coverage in the Arctic Ocean. In this study, we proposed a method for retrieving the ocean significant wave height (SWH) from S1 SAR data in horizontal‐horizontal (HH) polarization based on a backpropagation neural network (BPNN). A total of 4,273 scenes from S1 extra‐wide swath mode data acquired in the Arctic were collocated with data from four radar altimeters (RA), yielding 126,128 collocated data pairs. These data were separated into training and testing data sets to develop the BPNN model for retrieving SWH. Comparing the S1 retrieved SWH using the testing data set with the RA SWH yielded a bias of 0.17 m, a root‐mean‐square error of 0.71 m and a scatter index (SI) of 23.05% for SWH less than 10 m. The S1 retrieved SWH was further compared with the CFOSAT/SWIM data acquired in the Arctic between August 2019 and May 2020, which suggests that the SWIM has different performances on wave measurements at different beams.

中文翻译：

---

基于神经网络的北冰洋星载SAR海浪高度反演

双Sentinel-1（S1）卫星已在北极广泛地获取合成孔径雷达（SAR）数据，为获得北冰洋具有高空间分辨率和宽幅覆盖范围的海洋动力学参数提供了独特的机会。在这项研究中，我们提出了一种基于反向传播神经网络（BPNN）的水平-水平（HH）极化中的S1 SAR数据来检索海洋有效波高（SWH）的方法。来自北极地区的S1超宽幅模式数据中的总共4,273个场景与来自四个雷达高度计（RA）的数据并置，产生了126,128个并置数据对。这些数据被分为训练和测试数据集，以开发用于检索SWH的BPNN模型。使用测试数据集将S1检索到的SWH与RA SWH进行比较，得出的偏差为0.17 m，小于10 m的SWH的均方根误差为0.71 m，散射指数（SI）为23.05％。将S1检索到的SWH与2019年8月至2020年5月在北极获得的CFOSAT / SWIM数据进行了进一步比较，这表明SWIM在不同波束的波测量方面具有不同的性能。