Fast Calorimeter Simulation Challenge 2022 - Dataset 2

This is dataset 2 of the “Fast Calorimeter Simulation Challenge 2022”. It consists of two files with 100k GEANT4-simulated showers each of electrons with energies sampled from a log-uniform distribution ranging from 1 GeV to 1 TeV. The detector has a concentric cylinder geometry with 45 layers, where each layer consists of active (silicon) and passive (tungesten) material. Each layer has 144 readout cells, 9 in radial and 16 in angular direction, yielding a total of 9x16x45 = 6480 voxels. dataset_2_1.hdf5 should be used for training, dataset_2_2.hdf5 can be used as reference in the evaluation. More details, in particular helper scripts to parse the data and calculate and visualize basic high-level physics features, are available at https://calochallenge.github.io/homepage/本数据集为2022年快量热计模拟挑战赛（Fast Calorimeter Simulation Challenge 2022）的数据集2。该数据集包含两个文件，每个文件均存有10万次由GEANT4模拟的电子簇射，电子能量取自1 GeV至1 TeV的对数均匀分布。该探测器采用同心圆柱几何结构，共包含45层探测层；每层均由有源（硅）与无源（钨）材料构成，设有144个读出单元，其中沿径向分布9个、沿角向分布16个，总体素（voxel）数为9×16×45=6480。其中dataset_2_1.hdf5可用于模型训练，dataset_2_2.hdf5可作为评估阶段的参考数据集。更多细节（尤其是用于解析数据、计算并可视化基础高级物理特征的辅助脚本）可访问https://calochallenge.github.io/homepage/ 获取。