Tagging the Higgs boson decay to bottom quarks with colour-sensitive observables and the Lund jet plane

TL;DR

This paper develops a new $Hbb$ tagging method combining theory-driven observables and Lund jet plane images, trained with machine learning, to improve discrimination of Higgs decay to bottom quarks from QCD background at the LHC.

Contribution

The paper introduces an original $Hbb$ tagger that combines high-level observables with Lund jet plane images using machine learning, enhancing Higgs to bottom quark identification.

Findings

High discrimination performance achieved with combined observables and Lund jet plane.

The tagger's dependence on invariant mass suggests potential for generic $Xbb$ tagging.

Machine learning effectively integrates multiple observables for jet classification.

Abstract

We study the problem of distinguishing $b$-jets stemming from the decay of a colour singlet, such as the Higgs boson, from those originating from the abundant QCD background. In particular, as a case study, we focus on associate production of a vector boson and a Higgs boson decaying into a pair of $b$-jets, which has been recently observed at the LHC. We consider the combination of several theory-driven observables proposed in the literature, together with Lund jet plane images, in order to design an original $Hbb$ tagger. The observables are combined by means of standard machine learning algorithms, which are trained on events obtained with fast detector simulation techniques. We find that the combination of high-level single-variable observables with the Lund jet plane provides an excellent discrimination performance. We also study the dependence of the tagger on the invariant mass of the decaying particles, in order to assess the extension to a generic $Xbb$ tagger.