CaloClouds: Fast Geometry-Independent Highly-Granular Calorimeter Simulation
This addresses a major computing bottleneck in particle physics by enabling fast and accurate generative simulations to augment traditional methods.
The paper tackles the challenge of simulating particle showers in highly-granular detectors by directly generating point clouds of up to 6,000 space points in 3D without a fixed grid, achieving good modeling of physical distributions for photon showers in the ILD calorimeter.
Simulating showers of particles in highly-granular detectors is a key frontier in the application of machine learning to particle physics. Achieving high accuracy and speed with generative machine learning models would enable them to augment traditional simulations and alleviate a major computing constraint. This work achieves a major breakthrough in this task by, for the first time, directly generating a point cloud of a few thousand space points with energy depositions in the detector in 3D space without relying on a fixed-grid structure. This is made possible by two key innovations: i) Using recent improvements in generative modeling we apply a diffusion model to generate photon showers as high-cardinality point clouds. ii) These point clouds of up to $6,000$ space points are largely geometry-independent as they are down-sampled from initial even higher-resolution point clouds of up to $40,000$ so-called Geant4 steps. We showcase the performance of this approach using the specific example of simulating photon showers in the planned electromagnetic calorimeter of the International Large Detector (ILD) and achieve overall good modeling of physically relevant distributions.