Cargando…

Autoencoders for Semivisible Jet Detection

The production of dark matter particles from confining dark sectors may lead to many novel experimental signatures. Depending on the details of the theory, dark quark production in proton-proton collisions could result in semivisible jets of particles: collimated sprays of dark hadrons of which only...

Descripción completa

Detalles Bibliográficos
Autores principales: Canelli, Florencia, de Cosa, Annapaola, Pottier, Luc Le, Niedziela, Jeremi, Pedro, Kevin, Pierini, Maurizio
Lenguaje:eng
Publicado: 2021
Materias:
Acceso en línea:https://dx.doi.org/10.1007/JHEP02(2022)074
http://cds.cern.ch/record/2792362
_version_ 1780972353366261760
author Canelli, Florencia
de Cosa, Annapaola
Pottier, Luc Le
Niedziela, Jeremi
Pedro, Kevin
Pierini, Maurizio
author_facet Canelli, Florencia
de Cosa, Annapaola
Pottier, Luc Le
Niedziela, Jeremi
Pedro, Kevin
Pierini, Maurizio
author_sort Canelli, Florencia
collection CERN
description The production of dark matter particles from confining dark sectors may lead to many novel experimental signatures. Depending on the details of the theory, dark quark production in proton-proton collisions could result in semivisible jets of particles: collimated sprays of dark hadrons of which only some are detectable by particle collider experiments. The experimental signature is characterised by the presence of reconstructed missing momentum collinear with the visible components of the jets. This complex topology is sensitive to detector inefficiencies and mis-reconstruction that generate artificial missing momentum. With this work, we propose a signal-agnostic strategy to reject ordinary jets and identify semivisible jets via anomaly detection techniques. A deep neural autoencoder network with jet substructure variables as input proves highly useful for analyzing anomalous jets. The study focuses on the semivisible jet signature; however, the technique can apply to any new physics model that predicts signatures with anomalous jets from non-SM particles.
id cern-2792362
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2021
record_format invenio
spelling cern-27923622023-01-31T10:55:52Zdoi:10.1007/JHEP02(2022)074http://cds.cern.ch/record/2792362engCanelli, Florenciade Cosa, AnnapaolaPottier, Luc LeNiedziela, JeremiPedro, KevinPierini, MaurizioAutoencoders for Semivisible Jet Detectionhep-exParticle Physics - Experimentcs.LGComputing and Computershep-phParticle Physics - PhenomenologyThe production of dark matter particles from confining dark sectors may lead to many novel experimental signatures. Depending on the details of the theory, dark quark production in proton-proton collisions could result in semivisible jets of particles: collimated sprays of dark hadrons of which only some are detectable by particle collider experiments. The experimental signature is characterised by the presence of reconstructed missing momentum collinear with the visible components of the jets. This complex topology is sensitive to detector inefficiencies and mis-reconstruction that generate artificial missing momentum. With this work, we propose a signal-agnostic strategy to reject ordinary jets and identify semivisible jets via anomaly detection techniques. A deep neural autoencoder network with jet substructure variables as input proves highly useful for analyzing anomalous jets. The study focuses on the semivisible jet signature; however, the technique can apply to any new physics model that predicts signatures with anomalous jets from non-SM particles.The production of dark matter particles from confining dark sectors may lead to many novel experimental signatures. Depending on the details of the theory, dark quark production in proton-proton collisions could result in semivisible jets of particles: collimated sprays of dark hadrons of which only some are detectable by particle collider experiments. The experimental signature is characterised by the presence of reconstructed missing momentum collinear with the visible components of the jets. This complex topology is sensitive to detector inefficiencies and mis-reconstruction that generate artificial missing momentum. With this work, we propose a signal-agnostic strategy to reject ordinary jets and identify semivisible jets via anomaly detection techniques. A deep neural autoencoder network with jet substructure variables as input proves highly useful for analyzing anomalous jets. The study focuses on the semivisible jet signature; however, the technique can apply to any new physics model that predicts signatures with anomalous jets from non-SM particles.arXiv:2112.02864oai:cds.cern.ch:27923622021-12-06
spellingShingle hep-ex
Particle Physics - Experiment
cs.LG
Computing and Computers
hep-ph
Particle Physics - Phenomenology
Canelli, Florencia
de Cosa, Annapaola
Pottier, Luc Le
Niedziela, Jeremi
Pedro, Kevin
Pierini, Maurizio
Autoencoders for Semivisible Jet Detection
title Autoencoders for Semivisible Jet Detection
title_full Autoencoders for Semivisible Jet Detection
title_fullStr Autoencoders for Semivisible Jet Detection
title_full_unstemmed Autoencoders for Semivisible Jet Detection
title_short Autoencoders for Semivisible Jet Detection
title_sort autoencoders for semivisible jet detection
topic hep-ex
Particle Physics - Experiment
cs.LG
Computing and Computers
hep-ph
Particle Physics - Phenomenology
url https://dx.doi.org/10.1007/JHEP02(2022)074
http://cds.cern.ch/record/2792362
work_keys_str_mv AT canelliflorencia autoencodersforsemivisiblejetdetection
AT decosaannapaola autoencodersforsemivisiblejetdetection
AT pottierlucle autoencodersforsemivisiblejetdetection
AT niedzielajeremi autoencodersforsemivisiblejetdetection
AT pedrokevin autoencodersforsemivisiblejetdetection
AT pierinimaurizio autoencodersforsemivisiblejetdetection