Fast Calorimeter Simulation Challenge 2022 - Dataset 1

This is dataset 1 of the “Fast Calorimeter Simulation Challenge 2022”. It is based on the ATLAS GEANT4 open datasets that were published here. There are three files, two for photons and one for charged pions. Each dataset contains the voxelised shower information obtained from single particles produced at the calorimeter surface in the η range (0.2-0.25) and simulated in the ATLAS detector. Each file contains "incident_energies" of shape (num_showers, 1) and "showers" of shape (num_showers, num_voxels). There are 15 incident energies from 256 MeV up to 4 TeV produced in powers of two. 10k events are available in each sample with the exception of those at higher energies that have a lower statistics. These samples were used to train the corresponding two GANs presented in the AtlFast3 paper SIMU-2018-04 and in the FastCaloGAN note ATL-SOFT-PUB-2020-006. The number of radial and angular bins varies from layer to layer and is also different for photons and pions, resulting in 368 voxels for photons and 533 for pions.

dataset_1_photons_1.hdf5 should be used for training, dataset_1_photons_2.hdf5 for evaluation. An evaluation dataset for the pions might be added in the future.

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/