Deep learning level-3 electron trigger for CLAS12

Tyson, R., Gavalian, G., Ireland, D.G. and McKinnon, B. (2023) Deep learning level-3 electron trigger for CLAS12. Computer Physics Communications, 290, 108783. (doi: 10.1016/j.cpc.2023.108783)

[img] Text
298277.pdf - Published Version
Available under License Creative Commons Attribution.

2MB

Abstract

Fast, efficient and accurate triggers are a critical requirement for modern high energy physics experiments given the increasingly large quantities of data that they produce. The CEBAF Large Acceptance Spectrometer (CLAS12) employs a highly efficient electron trigger to filter the amount of recorded data by requiring at least one electron in each event, at the cost of a low purity in electron identification. Machine learning algorithms are increasingly employed for classification tasks such as particle identification due to their high accuracy and fast processing times. In this article we show how a convolutional neural network could be deployed as a Level 3 electron trigger at CLAS12. We demonstrate that the Artificial Intelligence (AI) trigger would achieve a significant data reduction compared to the traditional trigger, whilst preserving a 99.5% electron identification efficiency. The AI trigger purity as a function of increased luminosity is improved relative to the traditional trigger. As a consequence, this AI trigger can achieve a data recording reduction improvement of about 65% at standard CLAS12 luminosities when compared to the traditional trigger. A reduction in data output also reduces storage costs and post-processing times, which in turn reduces time to publication of new physics measurements.

Item Type:Articles
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:McKinnon, Dr Bryan and Tyson, Mr Richard and Ireland, Professor David
Authors: Tyson, R., Gavalian, G., Ireland, D.G., and McKinnon, B.
College/School:College of Science and Engineering > School of Physics and Astronomy
Journal Name:Computer Physics Communications
Publisher:Elsevier
ISSN:0010-4655
ISSN (Online):1879-2944
Published Online:17 May 2023
Copyright Holders:Copyright © 2023 The Authors
First Published:First published in Computer Physics Communications 290: 108783
Publisher Policy:Reproduced under a Creative Commons License

University Staff: Request a correction | Enlighten Editors: Update this record

Project CodeAward NoProject NamePrincipal InvestigatorFunder's NameFunder RefLead Dept
301379Nuclear Physics Consolidated GrantDavid IrelandScience and Technology Facilities Council (STFC)ST/P004458/1P&S - Physics & Astronomy
309552Nuclear Physics Consolidated Grant 2David IrelandScience and Technology Facilities Council (STFC)ST/V00106X/1P&S - Physics & Astronomy