Deep learning in color: towards automated quark/gluon jet discrimination
This work addresses the challenge of automating jet discrimination in particle physics, offering a novel approach that could improve data analysis efficiency, though it is incremental as it builds on existing image-based paradigms.
The researchers tackled the problem of discriminating between quark and gluon jets in collider physics by using deep learning with convolutional neural networks on color-enhanced jet images, achieving performance that matches or outperforms traditional physics-designed observables. They also found that the neural networks are robust to differences in simulations, similar to traditional methods.
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.