Autoencoder-Based Anomaly Detection System for Online Data Quality Monitoring of the CMS Electromagnetic Calorimeter-Reference-Cited by-同舟云学术

Autoencoder-Based Anomaly Detection System for Online Data Quality Monitoring of the CMS Electromagnetic Calorimeter

Published:2024-06-24 Issue:1 Volume:8 Page:
ISSN:2510-2036
Container-title:Computing and Software for Big Science
language:en
Short-container-title:Comput Softw Big Sci

Author:

,Abadjiev D.,Adams T.^ORCID,Adzic P.^ORCID,Ahmad M.^ORCID,Amendola C.^ORCID,Andrews M. B.^ORCID,Arcidiacono R.^ORCID,Argiro S.^ORCID,Askew A.^ORCID,Auffray E.^ORCID,Azzolini V.,Bailleux D.,Band R.^ORCID,Barney D.^ORCID,Barria P.^ORCID,Bartosik N.^ORCID,Basile C.,Bastos D.^ORCID,Bell K. W.^ORCID,Besancon M.^ORCID,Bianco R.,Biino C.^ORCID,Blinov V.,Borca C.,Bornheim A.^ORCID,Brown R. M.^ORCID,Campana M.^ORCID,Castells S.^ORCID,Cavallari F.^ORCID,Cetorelli F.^ORCID,Chatterjee R. M.,Chatterjee S.^ORCID,Chaudhary G.^ORCID,Chen J. A.,Chernyavskaya N.^ORCID,Chung H.,Cipriani M.^ORCID,Cokic L.,Cooke C.^ORCID,Cossio F.,Couderc F.^ORCID,Cristoforetti D.,Cucciati G.,Cunqueiro Mendez L.,Da Silva Di Calafiori D.,Dafinei I.,Cockerill D. J. A.^ORCID,Dejardin M.^ORCID,Re D. Del^ORCID,Ricca G. Della^ORCID,Depasse P.^ORCID,Dervan J.,Marco E. Di^ORCID,Diemoz M.^ORCID,Dimova T.^ORCID,Dissertori G.^ORCID,Dittmar M.,Dolgopolov A.,Donegà M.^ORCID,Dordevic M.^ORCID,Mamouni H. El,Errico F.^ORCID,Espinosa F.,Faure J. L.,Fay J.^ORCID,Menendez J. Fernandez^ORCID,Ferri F.^ORCID,Finco L.^ORCID,Fiori F.,Frahm E.,Funk W.^ORCID,Gadek T.,Gajownik J.,Galli M.^ORCID,Ganjour S.^ORCID,Gascon S.^ORCID,Ghezzi A.^ORCID,Ghose P.,Gninenko S.^ORCID,Goadhouse S.,Godinovic N.^ORCID,Golubev N.^ORCID,Govoni P.^ORCID,Gras P.^ORCID,Hakala J.^ORCID,de Monchenault G. Hamel^ORCID,Harilal A.^ORCID,Härringer N.,Hashmi R.,Heath H. F.^ORCID,Hirosky R.^ORCID,Ho K. W.,Hou X.,Ingram Q.^ORCID,Jain Sh.^ORCID,Javaid T.^ORCID,Jessop C.^ORCID,Jimènez R.,Joshi B. M.^ORCID,Jourd‘hui E.,Kaadze K.^ORCID,Kao Y.-W.,Kardapoltsev L.^ORCID,Khurana R.,King J.^ORCID,Kirilovas A.,Konstantinov D.^ORCID,Kovac M.^ORCID,Krishna A.^ORCID,Kuo C. M.,Lambrecht L.^ORCID,Lavizzari G.,Lecoq P.^ORCID,Ledovskoy A.^ORCID,Legger F.^ORCID,Lelas D.^ORCID,Li Y. y.^ORCID,Liang Z.,Lin W.,Longo E.^ORCID,Loukas N.^ORCID,Lu R. -S.^ORCID,Lustermann W.^ORCID,Lutton L.^ORCID,Lyon A. -M.^ORCID,Maeshima K.^ORCID,Malcles J.^ORCID,Mandrik P.^ORCID,Manzoni R. A.^ORCID,Marchese L.^ORCID,Marinelli N.,Marini A. C.^ORCID,Martin L.,Marzocchi B.^ORCID,Mascellani A.^ORCID,Massironi A.^ORCID,Matveev V.^ORCID,Mazza G.,Meridiani P.^ORCID,Mijic M.,Mijuskovic J.^ORCID,Milenovic P.^ORCID,Milosevic J.^ORCID,Monteno M.^ORCID,Monti F.^ORCID,Moortgat F.^ORCID,Mousa J.^ORCID,Mudholkar T.^ORCID,Nessi-Tedaldi F.^ORCID,Nicolaou C.,Nigamova A.^ORCID,Obertino M. M.^ORCID,Organtini G.^ORCID,Orimoto T.^ORCID,Orlandi F.,Ovtin I.^ORCID,Paganis E.^ORCID,Papagiannis D.^ORCID,Pandolfi F.^ORCID,Paramatti R.^ORCID,Park K.^ORCID,Pastrone N.^ORCID,Paulini M.^ORCID,Pauss F.^ORCID,Petkovic, A.,Petraityte E.,Pettinacci V.,Petyt D.^ORCID,Pigazzini S.^ORCID,Pinolini B. S.,Prova P. R.,Quaranta C.^ORCID,Ragazzi S.^ORCID,Rahatlou S.^ORCID,Rasteiro Da Silva J. C.,Razis P. A.^ORCID,Teles P. Rebello^ORCID,Reis T.^ORCID,Riti F.^ORCID,Rogan C.^ORCID,Romanteau T.,Rosowsky A.,Rovelli C.^ORCID,Rovere M.^ORCID,Rusack R.^ORCID,Salvi G.^ORCID,Sancar O.,Sanchez A.^ORCID,Sandever C.,Santanastasio F.^ORCID,Saradhy R.^ORCID,Sarkar U.^ORCID,Schneider M.,Schroeder N.^ORCID,Sculac A.,Sculac T.^ORCID,Shahzad M. A.,Shepherd-Themistocleous C. H.^ORCID,Simkina P.^ORCID,Singla A.^ORCID,Singovsky A.,Skovpen Y.^ORCID,Smith V. J.^ORCID,Soffi L.^ORCID,Stachon K.,Steen A.^ORCID,Steggemann J.^ORCID,Succar M.^ORCID,Tao J.^ORCID,Tishelman-Charny A.^ORCID,Tiwari P. C.^ORCID,Tornago M.^ORCID,Tramontano R.^ORCID,Tsai L. -S.,Usai E.^ORCID,Valsecchi D.^ORCID,Vagnerini A.^ORCID,Varela J.^ORCID,Venditti R.^ORCID,Verma P.^ORCID,Vlassov E.,Wachirapusitanand V.^ORCID,Wamorkar T.^ORCID,Wang C.,Wang J.^ORCID,Wadud M. A.^ORCID,Yu S. S.^ORCID,Zabi A.^ORCID,Zghiche A.^ORCID,Zhang L.,Zhu R. Y.^ORCID,Zygal L.^ORCID

Abstract

AbstractThe CMS detector is a general-purpose apparatus that detects high-energy collisions produced at the LHC. Online data quality monitoring of the CMS electromagnetic calorimeter is a vital operational tool that allows detector experts to quickly identify, localize, and diagnose a broad range of detector issues that could affect the quality of physics data. A real-time autoencoder-based anomaly detection system using semi-supervised machine learning is presented enabling the detection of anomalies in the CMS electromagnetic calorimeter data. A novel method is introduced which maximizes the anomaly detection performance by exploiting the time-dependent evolution of anomalies as well as spatial variations in the detector response. The autoencoder-based system is able to efficiently detect anomalies, while maintaining a very low false discovery rate. The performance of the system is validated with anomalies found in 2018 and 2022 LHC collision data. In addition, the first results from deploying the autoencoder-based system in the CMS online data quality monitoring workflow during the beginning of Run 3 of the LHC are presented, showing its ability to detect issues missed by the existing system.

Publisher

Springer Science and Business Media LLC

Link

https://link.springer.com/content/pdf/10.1007/s41781-024-00118-z.pdf

Reference24 articles.

1. Chatrchyan S et al (2008) The CMS experiment at the CERN LHC. JINST 3:S08004

2. Sirunyan AM et al (2021) Electron and photon reconstruction and identification with the CMS experiment at the CERN LHC. JINST 16(05):P05014

3. Aad G et al (2012) Observation of a new particle in the search for the Standard Model Higgs boson with the ATLAS detector at the LHC. Phys Lett B 716:1–29

4. Chatrchyan Serguei et al (2012) Observation of a New Boson at a Mass of 125 GeV with the CMS Experiment at the LHC. Phys Lett B 716:30–61

5. Sirunyan Albert M et al (2020) A measurement of the Higgs boson mass in the diphoton decay channel. Phys Lett B 805:135425

Cited by 2 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Deep generative models for detector signature simulation: A taxonomic review;Reviews in Physics;2024-12

2. Anomaly detection in collider physics via factorized observables;Physical Review D;2024-09-09