ATLAS flavour-tagging algorithms for the LHC Run 2 $pp$ collision dataset

TL;DR

This paper presents new ATLAS flavour-tagging algorithms based on deep neural networks, significantly improving jet-flavour identification performance in LHC Run 2 proton-proton collision data analysis.

Contribution

Introduction of recurrent and deep neural network-based flavour-tagging algorithms with enhanced accuracy over previous methods.

Findings

Achieved 77% $b$-jet efficiency with a light-jet rejection factor of 170.

Obtained 30% $c$-jet efficiency with a light-jet rejection factor of 70.

Demonstrated substantial performance improvements in simulated Standard Model $t\bar{t}$ events.

Abstract

The flavour-tagging algorithms developed by the ATLAS Collaboration and used to analyse its dataset of $\sqrt s = 13$ TeV $pp$ collisions from Run 2 of the Large Hadron Collider are presented. These new tagging algorithms are based on recurrent and deep neural networks, and their performance is evaluated in simulated collision events. These developments yield considerable improvements over previous jet-flavour identification strategies. At the 77% $b$-jet identification efficiency operating point, light-jet (charm-jet) rejection factors of 170 (5) are achieved in a sample of simulated Standard Model $t\bar{t}$ events; similarly, at a $c$-jet identification efficiency of 30%, a light-jet ($b$-jet) rejection factor of 70 (9) is obtained.