Deep learning techniques for energy clustering in the CMS ECAL

The reconstruction of electrons and photons in CMS depends on topological clustering of the energy deposited by an incident particle in different crystals of the electromagnetic calorimeter (ECAL). These clusters are formed by aggregating neighbouring crystals according to the expected topology of a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of physics. Conference series 2023-02, Vol.2438 (1), p.12077
1. Verfasser: Valsecchi, Davide
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue 1
container_start_page 12077
container_title Journal of physics. Conference series
container_volume 2438
creator Valsecchi, Davide
description The reconstruction of electrons and photons in CMS depends on topological clustering of the energy deposited by an incident particle in different crystals of the electromagnetic calorimeter (ECAL). These clusters are formed by aggregating neighbouring crystals according to the expected topology of an electromagnetic shower in the ECAL. The presence of upstream material (beampipe, tracker and support structures) causes electrons and photons to start showering before reaching the calorimeter. This effect, combined with the 3.8T CMS magnetic field, leads to energy being spread in several clusters around the primary one. It is essential to recover the energy contained in these satellite clusters in order to achieve the best possible energy resolution for physics analyses. Historically satellite clusters have been associated to the primary cluster using a purely topological algorithm which does not attempt to remove spurious energy deposits from additional pileup interactions (PU). The performance of this algorithm is expected to degrade during LHC Run 3 (2022+) because of the larger average PU levels and the increasing levels of noise due to the ageing of the ECAL detector. New methods are being investigated that exploit state-of-the-art deep learning architectures like Graph Neural Networks (GNN) and self-attention algorithms. These more sophisticated models improve the energy collection and are more resilient to PU and noise, helping to preserve the electron and photon energy resolution achieved during LHC Runs 1 and 2. This work will cover the challenges of training the models as well the opportunity that this new approach offers to unify the ECAL energy measurement with the particle identification steps used in the global CMS photon and electron reconstruction.
doi_str_mv 10.1088/1742-6596/2438/1/012077
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2777070903</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2777070903</sourcerecordid><originalsourceid>FETCH-LOGICAL-c414t-af1187be2d8597d3ef8fef74eae4892f0fb2e8bda7bd7f2950ee5a1ae381ce6c3</originalsourceid><addsrcrecordid>eNqFkEtPhDAQxxujiSv6GWziGWnLY8rFxOD6SNZ4UM9NgekuGwRs4bDf3hLMenQuM5OZ_zx-hFxzdsuZlBGHRIRZmmeRSGKfRowLBnBCVsfK6TGW8pxcOLdnLPYGK3L3gDjQFrXtmm5LR6x2XfM9oaOmtxQ7tNsDrdrJjWjnhqaj4w5p8fpO18X95pKcGd06vPr1Afl8XH8Uz-Hm7enF18Mq4ckYasO5hBJFLdMc6hiNNGggQY2JzIVhphQoy1pDWYMRecoQU801xpJXmFVxQG6WuYPt5-tGte8n2_mVSgAAA5b7jwICS1dle-csGjXY5kvbg-JMzbDUjEHNSNQMS3G1wPLKeFE2_fA3-j_VDxhha48</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2777070903</pqid></control><display><type>article</type><title>Deep learning techniques for energy clustering in the CMS ECAL</title><source>IOP Publishing Free Content</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><source>IOPscience extra</source><source>Alma/SFX Local Collection</source><source>Free Full-Text Journals in Chemistry</source><creator>Valsecchi, Davide</creator><creatorcontrib>Valsecchi, Davide</creatorcontrib><description>The reconstruction of electrons and photons in CMS depends on topological clustering of the energy deposited by an incident particle in different crystals of the electromagnetic calorimeter (ECAL). These clusters are formed by aggregating neighbouring crystals according to the expected topology of an electromagnetic shower in the ECAL. The presence of upstream material (beampipe, tracker and support structures) causes electrons and photons to start showering before reaching the calorimeter. This effect, combined with the 3.8T CMS magnetic field, leads to energy being spread in several clusters around the primary one. It is essential to recover the energy contained in these satellite clusters in order to achieve the best possible energy resolution for physics analyses. Historically satellite clusters have been associated to the primary cluster using a purely topological algorithm which does not attempt to remove spurious energy deposits from additional pileup interactions (PU). The performance of this algorithm is expected to degrade during LHC Run 3 (2022+) because of the larger average PU levels and the increasing levels of noise due to the ageing of the ECAL detector. New methods are being investigated that exploit state-of-the-art deep learning architectures like Graph Neural Networks (GNN) and self-attention algorithms. These more sophisticated models improve the energy collection and are more resilient to PU and noise, helping to preserve the electron and photon energy resolution achieved during LHC Runs 1 and 2. This work will cover the challenges of training the models as well the opportunity that this new approach offers to unify the ECAL energy measurement with the particle identification steps used in the global CMS photon and electron reconstruction.</description><identifier>ISSN: 1742-6588</identifier><identifier>EISSN: 1742-6596</identifier><identifier>DOI: 10.1088/1742-6596/2438/1/012077</identifier><language>eng</language><publisher>Bristol: IOP Publishing</publisher><subject>Algorithms ; Cluster analysis ; Clustering ; Deep learning ; Electrons ; Energy ; Energy measurement ; Energy resolution ; Graph neural networks ; Machine learning ; Photons ; Physics ; Reconstruction ; Satellite constellations ; Topology</subject><ispartof>Journal of physics. Conference series, 2023-02, Vol.2438 (1), p.12077</ispartof><rights>Published under licence by IOP Publishing Ltd</rights><rights>Published under licence by IOP Publishing Ltd. This work is published under http://creativecommons.org/licenses/by/3.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c414t-af1187be2d8597d3ef8fef74eae4892f0fb2e8bda7bd7f2950ee5a1ae381ce6c3</citedby><cites>FETCH-LOGICAL-c414t-af1187be2d8597d3ef8fef74eae4892f0fb2e8bda7bd7f2950ee5a1ae381ce6c3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://iopscience.iop.org/article/10.1088/1742-6596/2438/1/012077/pdf$$EPDF$$P50$$Giop$$Hfree_for_read</linktopdf><link.rule.ids>314,776,780,27901,27902,38845,38867,53815,53842</link.rule.ids></links><search><creatorcontrib>Valsecchi, Davide</creatorcontrib><title>Deep learning techniques for energy clustering in the CMS ECAL</title><title>Journal of physics. Conference series</title><addtitle>J. Phys.: Conf. Ser</addtitle><description>The reconstruction of electrons and photons in CMS depends on topological clustering of the energy deposited by an incident particle in different crystals of the electromagnetic calorimeter (ECAL). These clusters are formed by aggregating neighbouring crystals according to the expected topology of an electromagnetic shower in the ECAL. The presence of upstream material (beampipe, tracker and support structures) causes electrons and photons to start showering before reaching the calorimeter. This effect, combined with the 3.8T CMS magnetic field, leads to energy being spread in several clusters around the primary one. It is essential to recover the energy contained in these satellite clusters in order to achieve the best possible energy resolution for physics analyses. Historically satellite clusters have been associated to the primary cluster using a purely topological algorithm which does not attempt to remove spurious energy deposits from additional pileup interactions (PU). The performance of this algorithm is expected to degrade during LHC Run 3 (2022+) because of the larger average PU levels and the increasing levels of noise due to the ageing of the ECAL detector. New methods are being investigated that exploit state-of-the-art deep learning architectures like Graph Neural Networks (GNN) and self-attention algorithms. These more sophisticated models improve the energy collection and are more resilient to PU and noise, helping to preserve the electron and photon energy resolution achieved during LHC Runs 1 and 2. This work will cover the challenges of training the models as well the opportunity that this new approach offers to unify the ECAL energy measurement with the particle identification steps used in the global CMS photon and electron reconstruction.</description><subject>Algorithms</subject><subject>Cluster analysis</subject><subject>Clustering</subject><subject>Deep learning</subject><subject>Electrons</subject><subject>Energy</subject><subject>Energy measurement</subject><subject>Energy resolution</subject><subject>Graph neural networks</subject><subject>Machine learning</subject><subject>Photons</subject><subject>Physics</subject><subject>Reconstruction</subject><subject>Satellite constellations</subject><subject>Topology</subject><issn>1742-6588</issn><issn>1742-6596</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>O3W</sourceid><sourceid>BENPR</sourceid><recordid>eNqFkEtPhDAQxxujiSv6GWziGWnLY8rFxOD6SNZ4UM9NgekuGwRs4bDf3hLMenQuM5OZ_zx-hFxzdsuZlBGHRIRZmmeRSGKfRowLBnBCVsfK6TGW8pxcOLdnLPYGK3L3gDjQFrXtmm5LR6x2XfM9oaOmtxQ7tNsDrdrJjWjnhqaj4w5p8fpO18X95pKcGd06vPr1Afl8XH8Uz-Hm7enF18Mq4ckYasO5hBJFLdMc6hiNNGggQY2JzIVhphQoy1pDWYMRecoQU801xpJXmFVxQG6WuYPt5-tGte8n2_mVSgAAA5b7jwICS1dle-csGjXY5kvbg-JMzbDUjEHNSNQMS3G1wPLKeFE2_fA3-j_VDxhha48</recordid><startdate>20230201</startdate><enddate>20230201</enddate><creator>Valsecchi, Davide</creator><general>IOP Publishing</general><scope>O3W</scope><scope>TSCCA</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>8FD</scope><scope>8FE</scope><scope>8FG</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>H8D</scope><scope>HCIFZ</scope><scope>L7M</scope><scope>P5Z</scope><scope>P62</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope></search><sort><creationdate>20230201</creationdate><title>Deep learning techniques for energy clustering in the CMS ECAL</title><author>Valsecchi, Davide</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c414t-af1187be2d8597d3ef8fef74eae4892f0fb2e8bda7bd7f2950ee5a1ae381ce6c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Algorithms</topic><topic>Cluster analysis</topic><topic>Clustering</topic><topic>Deep learning</topic><topic>Electrons</topic><topic>Energy</topic><topic>Energy measurement</topic><topic>Energy resolution</topic><topic>Graph neural networks</topic><topic>Machine learning</topic><topic>Photons</topic><topic>Physics</topic><topic>Reconstruction</topic><topic>Satellite constellations</topic><topic>Topology</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Valsecchi, Davide</creatorcontrib><collection>IOP Publishing Free Content</collection><collection>IOPscience (Open Access)</collection><collection>CrossRef</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>Advanced Technologies &amp; Aerospace Collection</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>Aerospace Database</collection><collection>SciTech Premium Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Advanced Technologies &amp; Aerospace Database</collection><collection>ProQuest Advanced Technologies &amp; Aerospace Collection</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><jtitle>Journal of physics. Conference series</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Valsecchi, Davide</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Deep learning techniques for energy clustering in the CMS ECAL</atitle><jtitle>Journal of physics. Conference series</jtitle><addtitle>J. Phys.: Conf. Ser</addtitle><date>2023-02-01</date><risdate>2023</risdate><volume>2438</volume><issue>1</issue><spage>12077</spage><pages>12077-</pages><issn>1742-6588</issn><eissn>1742-6596</eissn><abstract>The reconstruction of electrons and photons in CMS depends on topological clustering of the energy deposited by an incident particle in different crystals of the electromagnetic calorimeter (ECAL). These clusters are formed by aggregating neighbouring crystals according to the expected topology of an electromagnetic shower in the ECAL. The presence of upstream material (beampipe, tracker and support structures) causes electrons and photons to start showering before reaching the calorimeter. This effect, combined with the 3.8T CMS magnetic field, leads to energy being spread in several clusters around the primary one. It is essential to recover the energy contained in these satellite clusters in order to achieve the best possible energy resolution for physics analyses. Historically satellite clusters have been associated to the primary cluster using a purely topological algorithm which does not attempt to remove spurious energy deposits from additional pileup interactions (PU). The performance of this algorithm is expected to degrade during LHC Run 3 (2022+) because of the larger average PU levels and the increasing levels of noise due to the ageing of the ECAL detector. New methods are being investigated that exploit state-of-the-art deep learning architectures like Graph Neural Networks (GNN) and self-attention algorithms. These more sophisticated models improve the energy collection and are more resilient to PU and noise, helping to preserve the electron and photon energy resolution achieved during LHC Runs 1 and 2. This work will cover the challenges of training the models as well the opportunity that this new approach offers to unify the ECAL energy measurement with the particle identification steps used in the global CMS photon and electron reconstruction.</abstract><cop>Bristol</cop><pub>IOP Publishing</pub><doi>10.1088/1742-6596/2438/1/012077</doi><tpages>6</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1742-6588
ispartof Journal of physics. Conference series, 2023-02, Vol.2438 (1), p.12077
issn 1742-6588
1742-6596
language eng
recordid cdi_proquest_journals_2777070903
source IOP Publishing Free Content; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals; IOPscience extra; Alma/SFX Local Collection; Free Full-Text Journals in Chemistry
subjects Algorithms
Cluster analysis
Clustering
Deep learning
Electrons
Energy
Energy measurement
Energy resolution
Graph neural networks
Machine learning
Photons
Physics
Reconstruction
Satellite constellations
Topology
title Deep learning techniques for energy clustering in the CMS ECAL
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-03T03%3A34%3A19IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Deep%20learning%20techniques%20for%20energy%20clustering%20in%20the%20CMS%20ECAL&rft.jtitle=Journal%20of%20physics.%20Conference%20series&rft.au=Valsecchi,%20Davide&rft.date=2023-02-01&rft.volume=2438&rft.issue=1&rft.spage=12077&rft.pages=12077-&rft.issn=1742-6588&rft.eissn=1742-6596&rft_id=info:doi/10.1088/1742-6596/2438/1/012077&rft_dat=%3Cproquest_cross%3E2777070903%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2777070903&rft_id=info:pmid/&rfr_iscdi=true