Jet tomography in hot QCD medium with deep learning

TL;DR

This paper introduces a deep learning method to analyze jet modifications in hot QCD media, enabling precise localization of jet creation points and advancing jet tomography of quark-gluon plasma.

Contribution

The study presents a novel deep learning approach that correlates jet properties with their creation points, improving the precision of jet tomography in quark-gluon plasma.

Findings

Deep learning accurately identifies jet modification levels on a jet-by-jet basis.

Jet properties like width and orientation enhance localization of jet creation points.

Method advances the use of jets as tomographic probes of quark-gluon plasma.

Abstract

With deep learning techniques, the degree of modification of energetic jets that traversed hot QCD medium can be identified on a jet-by-jet basis. Due to the strong correlations between the degree of jet modification and its traversed length in the medium, we demonstrate the power of our novel method to locate the creation point of a dijet pair in the nuclear overlap region. In particular, jet properties, such as jet width and orientation can serve as additional handles to locate the creation points to a higher level of precision, which constitutes a significant development towards the long-standing goal of using jets as tomographic probes of the quark-gluon plasma.