Deep Learning for the Classification of Quenched Jets

TL;DR

This paper explores deep learning methods to distinguish between jets modified by Quark-Gluon Plasma and those unaffected, demonstrating the potential of neural networks in identifying jet quenching effects in heavy-ion collisions.

Contribution

It introduces deep learning models specifically designed for classifying quenched jets, a novel application in high-energy nuclear physics.

Findings

Deep neural networks can effectively discriminate medium- from vacuum-like jets.

Convolutional, Dense, and Recurrent Neural Networks show promising performance.

Results indicate deep learning's potential for studying jet quenching phenomena.

Abstract

An important aspect of the study of Quark-Gluon Plasma (QGP) in ultra-relativistic collisions of heavy ions is the ability to identify, in experimental data, a subset of the jets that were strongly modified by the interaction with the QGP. In this work, we propose studying deep learning techniques for this purpose. Samples of $Z+$jet events were simulated in vacuum and medium and used to train deep neural networks with the objective of discriminating between medium- and vacuum-like jets. Dedicated Convolutional Neural Networks, Dense Neural Networks and Recurrent Neural Networks were developed and trained, and their performance was studied. Our results show the potential of these techniques for the identification of jet quenching effects induced by the presence of the QGP.