Abstract This paper introduces a novel approach to estimate the wind direction over the sea from Synthetic Aperture Radar (SAR) images without any external information. The method employs deep residual network (ResNet), a variant of Convolutional Neural Network, to obtain high resolution (2 km by 2 km) aliased wind direction fields. Forty-seven SAR images of the European Space Agency satellites Sentinel-1 have been processed with ResNet, previously trained with other fifteen images. The areas of interest are the Mediterranean Sea and the Persian Gulf, two regional seas where the SAR images often present complex patterns associated to the wind field spatial structure reporting traces of the interaction with coastal orography, hence valuable test sites to evaluate the performance of the methodology here proposed. Statistical analysis was carried out comparing the SAR-derived wind directions with those from ECMWF atmospheric model, ASCAT scatterometer and in-situ gauges. It reports biases β of -1.1°, 2.4° and -4.6° respectively, and centered root mean square difference cRMSd

中文翻译：

---

使用 ResNet 从 Sentinel-1 SAR 图像中检索风向

摘要 本文介绍了一种在没有任何外部信息的情况下从合成孔径雷达 (SAR) 图像估计海上风向的新方法。该方法采用深度残差网络 (ResNet)，这是卷积神经网络的一种变体，以获得高分辨率（2 公里 x 2 公里）混叠风向场。欧洲航天局卫星 Sentinel-1 的 47 幅 SAR 图像已经用 ResNet 处理过，之前用其他 15 幅图像进行过训练。感兴趣的区域是地中海和波斯湾，这两个区域海域的 SAR 图像通常呈现与风场空间结构相关的复杂模式，报告与海岸地形相互作用的痕迹，因此是评估该系统性能的宝贵测试场地。这里提出的方法。进行了统计分析，将 SAR 导出的风向与 ECMWF 大气模型、ASCAT 散射计和现场测量仪的风向进行了比较。它分别报告了 -1.1°、2.4° 和 -4.6° 的偏差 β，以及中心均方根差值 crMSd