Deep learning in color: towards automated quark/gluon jet discrimination

TL;DR

This paper demonstrates that deep convolutional neural networks can effectively discriminate between quark and gluon jets in collider physics, outperforming traditional observables and showing robustness across different simulations.

Contribution

It introduces a novel image-based approach with color channels for jet discrimination and shows deep learning's superiority and robustness over traditional methods.

Findings

Deep networks match or outperform traditional jet variables.

Networks are surprisingly insensitive to simulation differences.

Deep learning provides robust physical insights from imperfect data.

Abstract

Artificial intelligence offers the potential to automate challenging data-processing tasks in collider physics. To establish its prospects, we explore to what extent deep learning with convolutional neural networks can discriminate quark and gluon jets better than observables designed by physicists. Our approach builds upon the paradigm that a jet can be treated as an image, with intensity given by the local calorimeter deposits. We supplement this construction by adding color to the images, with red, green and blue intensities given by the transverse momentum in charged particles, transverse momentum in neutral particles, and pixel-level charged particle counts. Overall, the deep networks match or outperform traditional jet variables. We also find that, while various simulations produce different quark and gluon jets, the neural networks are surprisingly insensitive to these differences, similar to traditional observables. This suggests that the networks can extract robust physical information from imperfect simulations.