Detection of bow echoes in French kilometer-scale models (AROME-EPS & AROME models of Météo-France)

To detect bow echoes (BE) directly in simulated reflectivity fields from French kilometer-scale models, three datasets are available. These datasets allowed for fitting and testing a univariate U-Net (convolutional neural network) using simulated reflectivity fields. Grid area : 717x1121 grid points, Western Europe (12°W-16°E and 37.5°N-55.4°N, resolution 0.025°) In each tar.gz file, files named 'input_BE' are reflectivity fields from operational models (in mm per hour), 'groundTruth' files correspond to manually labeled contours of BE (field with 1 for each grid point in BE and 0 for outside). The file format is HDF5. HDF5 files contain an array of N fields (array shape : (N,1,717,1121)) - dataset_train.tar.gz (N=6206): input and target fields to train the U-Net (<strong>only</strong> from the AROME-EPS model) - dataset_validation.tar.gz (N=2620): input and target fields to validate the U-Net (<strong>only</strong> from the AROME-EPS model). Training and validation databases contain independent weather case studies. - dataset_det_AROME.tar.gz (N=348): input and target fields to apply U-Net to the French deterministic AROME model (same grid than one of AROME-EPS). Weather case studies are the same than those in the validation database. - optimal_UNet_architecture.json : architecture of the optimal U-Net configuration - optimal_UNet_weights.h5 : weights of the trained optimal U-Net configuration为直接从法国千米尺度数值模式的模拟反射率场中检测弓状回波（bow echoes, BE），现有三类可用数据集。本系列数据集可基于模拟反射率场，完成单变量U-Net（卷积神经网络）的训练与测试。 网格范围为717×1121个格点，覆盖西欧区域（西经12°至东经16°、北纬37.5°至55.4°，空间分辨率0.025°）。 在每个tar.gz压缩包中，名为"input_BE"的文件为业务数值模式输出的反射率场（单位：毫米每小时）；名为"groundTruth"的文件对应弓状回波（bow echoes, BE）的人工标注轮廓：处于弓状回波区域内的格点取值为1，域外格点取值为0。 文件格式为HDF5，此类文件包含N个反射率场的数组，数组形状为(N, 1, 717, 1121)。各数据集详情如下： 1. dataset_train.tar.gz（样本量N=6206）：用于U-Net训练的输入与目标场，仅源自AROME-EPS模式。 2. dataset_validation.tar.gz（样本量N=2620）：用于U-Net验证的输入与目标场，仅源自AROME-EPS模式。训练与验证数据集包含相互独立的天气个例。 3. dataset_det_AROME.tar.gz（样本量N=348）：用于将训练好的U-Net应用于法国确定性AROME模式的输入与目标场，其网格与AROME-EPS模式完全一致。该数据集所用天气个例与验证数据集完全相同。 此外还包含两个配套文件： - optimal_UNet_architecture.json：最优U-Net配置的架构文件 - optimal_UNet_weights.h5：经训练的最优U-Net配置的权重文件