ML-based Fast Simulation of FARICH Responses

Unknown Date

AI Summary

This work addresses the high computational cost of traditional Monte Carlo simulations in high-energy physics, which hinder efficient modeling of detector responses—specifically for the FARICH detector. The authors propose, for the first time, a lightweight convolutional conditional generative adversarial network (cGAN) that takes particle trajectories and momenta as input conditions to rapidly generate realistic photon hit distributions. The method achieves high fidelity while significantly outperforming a linear statistical baseline and offers substantial acceleration compared to full Monte Carlo simulation. This approach thus presents an efficient and viable alternative for simulating detector responses in high-energy physics experiments.

Abstract

A fast simulation of the detector response is a vital task in high-energy physics (HEP). Traditional Monte-Carlo methods form the backbone of modern particle physics simulation software but are computationally expensive. We present a machine-learning-based approach to fast simulation of the Focusing Aerogel Ring Imaging Cherenkov (FARICH) detector response. Given a particle track and momentum, the goal is to generate realistic samples of photon hits on the detector matrix. We propose a conditional Generative Adversarial Network (cGAN) with a lightweight convolutional architecture that reproduces the projected detector response conditioned on particle parameters. We compare the cGAN against a linear statistical baseline using metrics applied to probability maps and to the reconstructed velocity distributions. The cGAN produces realistic samples and provides a significant speed-up over Monte-Carlo simulation.

Problem

• fast simulation
• FARICH
• detector response
• high-energy physics
• photon hits

Innovation

• conditional Generative Adversarial Network
• fast simulation
• FARICH detector
• machine learning
• high-energy physics