Ring-based ML calibration with in situ pileup correction for real-time jet triggers

TL;DR

This paper introduces a real-time machine learning calibration method for jet energy in HL-LHC trigger systems, utilizing FPGA implementation and in situ pileup correction to enhance Higgs pair detection efficiency.

Contribution

It presents a novel FPGA-compatible ML approach for jet calibration that combines regression and classification to improve trigger performance in high pileup conditions.

Findings

Doubling signal efficiency for Higgs pair detection

Effective in situ pileup correction in dense collision environments

Real-time implementation on FPGA hardware

Abstract

We present a machine learning (ML) method to calibrate hadronic jet energy in real-time trigger systems of the High-Luminosity Large Hadron Collider (HL-LHC) using an efficient implementation on field programmable gate arrays (FPGA). Regression is done to estimate the transverse energy of jet candidates, using concentric rings of electromagnetic and hadronic contributions in 0.1 x 0.1 towers around fixed-radius cone jet seeds, that accounts for in situ pileup correction. Classification separates hard-scatter jets from those due to pileup using the same inputs; its output provides a correction for the regression estimate. The algorithm is tested on simulated samples using an ATLAS-inspired detector in the dense environment of 200 simultaneous proton-proton collisions per bunch crossing. Our method improves the signal efficiency of saving Higgs pair production in HH -> bbbb by a factor of two over the traditional cone jet algorithm in real-time trigger systems.