Simulating the Time Projection Chamber responses at the MPD detector using Generative Adversarial Networks

TL;DR

This paper introduces a deep learning-based generative model to significantly accelerate the simulation of the Time Projection Chamber in the MPD detector, maintaining high accuracy while reducing computational costs.

Contribution

The work presents a novel application of Generative Adversarial Networks for fast, accurate simulation of detector responses in high energy physics experiments.

Findings

Achieved at least tenfold speed-up in detector response simulation.

Generated events closely match those from detailed traditional simulations.

Successfully integrated the model into the MPD software stack.

Abstract

High energy physics experiments rely heavily on the detailed detector simulation models in many tasks. Running these detailed models typically requires a notable amount of the computing time available to the experiments. In this work, we demonstrate a new approach to speed up the simulation of the Time Projection Chamber tracker of the MPD experiment at the NICA accelerator complex. Our method is based on a Generative Adversarial Network - a deep learning technique allowing for implicit estimation of the population distribution for a given set of objects. This approach lets us learn and then sample from the distribution of raw detector responses, conditioned on the parameters of the charged particle tracks. To evaluate the quality of the proposed model, we integrate a prototype into the MPD software stack and demonstrate that it produces high-quality events similar to the detailed simulator, with a speed-up of at least an order of magnitude. The prototype is trained on the responses from the inner part of the detector and, once expanded to the full detector, should be ready for use in physics tasks.