Speaker
Description
Fast Simulation of the ALICE Zero Degree Calorimeter using Generative Models
Davide Fuligno
On behalf of the ALICE Collaboration
Università di Pisa and INFN, Trieste Italy
The ALICE experiment at the LHC faces unprecedented computing challenges in Run 3 and 4, necessitating innovative solutions to cope with the increased data-taking luminosity and the continuous readout. A critical bottleneck in the current simulation pipeline for Pb-Pb collisions is the Zero Degree Calorimeter (ZDC), which characterizes collision geometry by detecting spectator nucleons. The full Geant4 transport simulation of hadronic showers in the ZDC is currently so computationally expensive that it is omitted from standard Monte Carlo productions, resulting in the absence of a realistic modeling of forward energy, centrality, and spectator-nucleon multiplicity.
In this contribution, we present a novel deep-learning-based fast simulation framework designed to overcome this limitation. We employ a modular architecture based on two fast Multi-Layer Perceptrons (MLPs) trained on simulated spectator nucleons in Pb-Pb collisions. The first MLP performs deterministic particle transport to the Zero Degree Calorimeter (ZDC), while the second uses Conditional Flow Matching (CFM) to generatively model the detector response. This decoupled approach minimizes the computing time required for training data production, providing an immediately deployable model while ensuring the modularity needed to easily accommodate different LHC beam configurations.
Designed for seamless integration into the ALICE O2 software framework via the ONNX standard, the inference engine achieves a computational speed-up of approximately six orders of magnitude over full simulations. These results demonstrate the potential to enable high-statistics ZDC simulation in future ALICE production campaigns.