Jet momentum reconstruction in the QGP background with machine learning

TL;DR

This paper demonstrates that machine learning models trained on medium-modified jet data outperform traditional background subtraction methods in reconstructing jet momentum within a quark-gluon plasma, leading to more accurate nuclear modification factor evaluations.

Contribution

The study introduces a DNN-based approach trained on quenched jet data to improve background subtraction in heavy-ion collisions, surpassing conventional methods.

Findings

ML models trained on quenched jets reduce bias in background subtraction.

ML-based reconstruction yields more accurate jet momentum and nuclear modification factors.

Training on medium-modified jets improves performance even after unfolding procedures.

Abstract

We apply a Dense Neural Network (DNN) approach to reconstruct jet momentum within a quark-gluon plasma (QGP) background, using simulated data from PYTHIA and Linear Boltzmann Transport (LBT) Models for comparative analysis. We find that medium response particles from the LBT simulation, scattered out of the QGP background but belonging to medium-modified jets, lead to oversubtraction of the background if the DNN model is trained on vacuum jets from PYTHIA simulation. By training the DNN model on quenched jets generated using LBT or the combination of jet samples from PYTHIA and LBT, we significantly reduce this prediction bias and achieve more accurate background subtraction compared to conventional Area-based and Constituent Subtraction methods widely adopted in experimental measurements. We further study the performance of these machine learning models on evaluating the nuclear modification factor of jets, and find that while the unfolding procedure is necessary for correcting residuals in reconstructed jet momenta, models trained on samples incorporating quenched jets still achieve superior accuracy than those trained on vacuum jets even after unfolding.