CaloClouds3: Ultra-Fast Geometry-Independent Highly-Granular Calorimeter Simulation

TL;DR

CaloClouds3 is a rapid, geometry-independent photon shower simulation model utilizing pointcloud techniques with angular conditioning, achieving significant speed improvements over traditional methods and adaptable for full detector simulation.

Contribution

This work introduces a novel pointcloud-based photon shower model with angular conditioning, enabling fast, geometry-independent simulations suitable for integration into full detector chains.

Findings

Achieves 100x faster inference than Geant4.

Employs angular conditioning for all incident angles.

Demonstrates applicability in full simulation and reconstruction chains.

Abstract

We present CaloClouds3, a model for the fast simulation of photon showers in the barrel of a high granularity detector. This iteration demonstrates for the first time how a pointcloud model can employ angular conditioning to replicate photons at all incident angles. Showers produced by this model can be used across the whole detector barrel, due to specially produced position agnostic training data. With this flexibility, the model is usable in a full simulation and reconstruction chain, which offers a further handle for evaluating physics performance of the model. As inference time is a crucial consideration for a generative model, the pre-processing and hyperparameters are aggressively optimised, achieving a speed up factor of two orders of magnitude over Geant4 at inference.