Machine Learning methods for simulating particle response in the Zero Degree Calorimeter at the ALICE experiment, CERN

TL;DR

This paper introduces machine learning techniques, specifically neural network classifiers and generative models, to significantly accelerate the simulation of particle responses in the ALICE experiment's Zero Degree Calorimeter at CERN, reducing computational costs.

Contribution

It presents a novel ML-based approach using variational autoencoders and GANs to efficiently simulate calorimeter responses, outperforming traditional Monte Carlo methods.

Findings

Simulation speed increased by 100x

Maintained high fidelity of calorimeter response

Effective use of GAN architecture with regularisation and postprocessing

Abstract

Currently, over half of the computing power at CERN GRID is used to run High Energy Physics simulations. The recent updates at the Large Hadron Collider (LHC) create the need for developing more efficient simulation methods. In particular, there exists a demand for a fast simulation of the neutron Zero Degree Calorimeter, where existing Monte Carlo-based methods impose a significant computational burden. We propose an alternative approach to the problem that leverages machine learning. Our solution utilises neural network classifiers and generative models to directly simulate the response of the calorimeter. In particular, we examine the performance of variational autoencoders and generative adversarial networks, expanding the GAN architecture by an additional regularisation network and a simple, yet effective postprocessing step. Our approach increases the simulation speed by 2 orders of magnitude while maintaining the high fidelity of the simulation.