Synthetically generated clouds on ground-based solar observations

A dataset consisting of Ca II &amp; H-alpha images taken at the Paris Meudon Observatory. Synthetically generated cloud coverage has been applied to clean images, thereby creating an (cloudy, clean) pair--facilitating the training of cloud-removal algorithms. <strong>Data description</strong> The Ca-II and H-α synthetic dataset comprise respectively 319 and 367 pairs of shadow/shadow-free images, split into 223/96 and 256/111 training/testing pairs. Listed here are two zip archives: filament-bounding-boxes.zip -- bounding boxes of filaments that were used to compute the patched metrics. synthetic-clouds.zip -- the cloudy input/clean output images that are used to train machine learning algorithms. A PyTorch dataset has been created that handles the download, importing, and usage of this dataset. You can find this code at the github repository: https://github.com/jaypmorgan/cloud-removal <strong>Pre-processing routines</strong> To generate this set of data, we have applied a series of pre-processing routines. These are: Correct determination of the solar limb (source code can be found at: https://gitlab.lis-lab.fr/presage/solar-limb-detection). Scaling the solar disk to 420 pixels, and centring it at 511.5 pixels in the x and y dimensions. Setting background values outside the solar disk to 0. Normalising the disk intensity values into the range of 0-1.本数据集包含取自巴黎默东天文台（Paris Meudon Observatory）的Ca II与H-α波段天文图像。我们对清晰图像施加了人工合成云覆盖效果，由此生成（多云图像、清晰图像）配对样本，以辅助云去除算法的训练。<strong>数据集说明</strong>：该Ca II与H-α合成数据集分别包含319对和367对带阴影/无阴影图像，训练集与测试集的划分数量为223/96和256/111个图像对。本次提供两个压缩归档文件：filament-bounding-boxes.zip——用于计算分块评估指标的丝状体边界框文件；synthetic-clouds.zip——用于训练机器学习算法的多云输入/清晰输出图像数据集。我们已构建PyTorch数据集工具以实现该数据集的下载、导入与使用，相关代码可在GitHub仓库获取：https://github.com/jaypmorgan/cloud-removal。<strong>预处理流程</strong>：为生成本数据集，我们执行了一系列预处理操作，具体如下：1. 精准测定太阳边缘（相关源代码可通过https://gitlab.lis-lab.fr/presage/solar-limb-detection 获取）；2. 将太阳盘面缩放至420像素，并使其在x、y轴方向均居中于511.5像素位置；3. 将太阳盘面外的背景像素值置为0；4. 将盘面的强度值归一化至0-1区间。