Probing highly collimated photon-jets with deep learning

TL;DR

This paper explores the use of deep learning techniques to identify highly collimated photon-jets resulting from potential new particles predicted by extensions of the standard model, aiming to improve detection at the LHC.

Contribution

It introduces a novel application of CNNs and BDTs to distinguish photon-jets from background, enhancing search strategies for sub-GeV particles from Higgs decays.

Findings

Deep learning improves photon-jet discrimination.

Enhanced sensitivity in LHC searches for new particles.

Effective background suppression achieved.

Abstract

Many extensions of the standard model (SM) predict the existence of axion-like particles and/or dark Higgs in the sub-GeV scale. Two new sub-GeV particles, a scalar and a pseudoscalar, produced through the Higgs boson exotic decays, are investigated. The decay signatures of these two new particles with highly collimated photons in the final states are discriminated from the ones of SM backgrounds using the Convolutional Neural Networks and Boosted Decision Trees techniques. The sensitivities of searching for such new physics signatures at the Large Hadron Collider are obtained.