A deep neural network for simultaneous estimation of b jet energy and resolution

TL;DR

This paper introduces a deep neural network-based method to accurately estimate the energy and resolution of b jets in proton-proton collisions at 13 TeV, enhancing analysis sensitivity in high-energy physics experiments.

Contribution

It presents a novel multivariate regression algorithm using deep learning to improve b jet energy and resolution estimation, validated on CMS data from 2017.

Findings

Improved b jet energy resolution and accuracy.

Enhanced sensitivity in Higgs boson decay analyses.

Validated on real CMS data with large simulated samples.

Abstract

We describe a method to obtain point and dispersion estimates for the energies of jets arising from b quarks produced in proton-proton collisions at an energy of $\sqrt{s} =$ 13 TeV at the CERN LHC. The algorithm is trained on a large simulated sample of b jets and validated on data recorded by the CMS detector in 2017 corresponding to an integrated luminosity of 41 fb$^{-1}$. A multivariate regression algorithm based on a deep feed-forward neural network employs jet composition and shape information, and the properties of reconstructed secondary vertices associated with the jet. The results of the algorithm are used to improve the sensitivity of analyses that make use of b jets in the final state, such as the observation of Higgs boson decay to $\mathrm{b\bar{b}}$.