Sentinel-1 maritime mesocyclone dataset

This dataset consists of 2004 geocoded Sentinel-1 image samples, divided into two classes: one class with mesocyclones being present in the images (class "pos"), and one class with mesocyclones being absent (class "neg"). The dataset is divided in training and test set. The training set contains 1,547 images (254 of class "pos", 1,293 of class "neg"). The test set contains 435 images (64 of class "pos", 371 of class "neg"). The dataset was used for the first time in the paper "Recognition of polar lows in Sentinel-1 SAR images with deep learning", where a detailed description of the dataset formation is presented. In the paper, the dataset is used to study the possibility of detecting polar lows in C-band SAR images. Specifically, a deep learning model was trained to classify the labelled images. Evaluated on an independent test set, the model yields an F-1 score of 0.95, indicating that polar lows can be consistently detected from SAR images. Interpretability techniques applied to the deep learning model reveal that atmospheric fronts and cyclonic eyes are key features in the classification. Moreover, experimental results show that the model is accurate even if: (i) such features are significantly cropped due to the limited swath width of the SAR, (ii) the features are partly covered by sea ice and (iii) land is covering significant parts of the images. By evaluating the model performance on multiple input image resolutions (pixel sizes of 500m, 1km and 2km), it is found that higher resolutions yield the best performance. This emphasises the potential of using high-resolution sensors like SAR for detecting polar lows, as compared to conventionally used sensors such as scatterometers.

本数据集汇聚了2004年地理编码的Sentinel-1影像样本，分为两类：一类包含图像中存在的中气旋（标记为“pos”类别），另一类则不含中气旋（标记为“neg”类别）。数据集被划分为训练集和测试集，其中训练集包含1,547幅图像（254幅为“pos”类别，1,293幅为“neg”类别），测试集包含435幅图像（64幅为“pos”类别，371幅为“neg”类别）。该数据集首次被应用于论文《利用深度学习在Sentinel-1 SAR图像中识别极地低压》中，论文中对数据集的构建进行了详细的描述。在该研究中，数据集被用于探讨检测C波段SAR图像中极地低压的可能性。具体而言，训练了一个深度学习模型以对标记图像进行分类。该模型在独立的测试集上评估，F-1分数达到0.95，表明极地低压可以从SAR图像中持续检测到。对深度学习模型应用的可解释性技术揭示了大气锋面和气旋眼是分类中的关键特征。此外，实验结果表明，即使（i）这些特征因SAR的有限波束宽度而被显著裁剪，（ii）特征部分被海冰覆盖，以及（iii）图像中有大片区域被陆地覆盖，该模型仍然保持准确性。通过对多个输入图像分辨率（像素大小为500米、1公里和2公里）的模型性能进行评估，发现更高分辨率产生了最佳性能。这强调了与常规使用的散射计等传感器相比，利用高分辨率传感器如SAR进行极地低压检测的潜力。