CERN Accelerating science

ATLAS Slides
Report number	ATL-PHYS-SLIDE-2024-579
Title	Jet Finding as a Real-Time Object Detection Task
Author(s)	Bozianu, Leon (Universite de Geneve (CH))
Corporate author(s)	The ATLAS collaboration
Collaboration	ATLAS Collaboration
Submitted to	ML4Jets2024, Paris, Fr, 4 - 8 Nov 2024
Submitted by	leon.bozianu@cern.ch on 13 Nov 2024
Subject category	Particle Physics - Experiment
Accelerator/Facility, Experiment	CERN LHC ; ATLAS
Free keywords	Machine Learning ; Calorimeter ; Jets ; Object Detection ; OTHER
Abstract	The High Luminosity upgrade to the LHC (HL-LHC) will deliver an unprecedented luminosity to the ATLAS experiment. Ahead of this increase in data the ATLAS trigger and data acquisition system will undergo a comprehensive upgrade. The key function of the trigger system is to maintain a high signal efficiency together with a high background rejection whilst adhering to the throughput constraints of the data acquisition system. CaloJetSSD is proposed as a fast calorimeter-only preselection step to speed up the trigger decision for hadronic signals containing jets. The design and implementation of an object detection architecture for jet finding in the ATLAS calorimeter is presented. While identifying and localising calorimeter jets the model simultaneously estimates their transverse momenta. The performance of the network, which targets deployment in the Phase-II Event Filter (EF), is evaluated using a set of simulated particle interactions in the ATLAS detector with up to 200 concurrent pile-up interactions.