Spatio-Temporal Anomaly Detection with Graph Networks for Data Quality Monitoring of the Hadron Calorimeter
The Compact Muon Solenoid (CMS) experiment is a general-purpose detector for high-energy collision at the Large Hadron Collider (LHC) at CERN. It employs an online data quality monitoring (DQM) system to promptly spot and diagnose particle data acquisition problems to avoid data quality loss. In thi...
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/24/9679 |
| _version_ | 1797379459135832064 |
|---|---|
| author | Mulugeta Weldezgina Asres Christian Walter Omlin Long Wang David Yu Pavel Parygin Jay Dittmann Georgia Karapostoli Markus Seidel Rosamaria Venditti Luka Lambrecht Emanuele Usai Muhammad Ahmad Javier Fernandez Menendez Kaori Maeshima the CMS-HCAL Collaboration |
| author_facet | Mulugeta Weldezgina Asres Christian Walter Omlin Long Wang David Yu Pavel Parygin Jay Dittmann Georgia Karapostoli Markus Seidel Rosamaria Venditti Luka Lambrecht Emanuele Usai Muhammad Ahmad Javier Fernandez Menendez Kaori Maeshima the CMS-HCAL Collaboration |
| author_sort | Mulugeta Weldezgina Asres |
| collection | DOAJ |
| description | The Compact Muon Solenoid (CMS) experiment is a general-purpose detector for high-energy collision at the Large Hadron Collider (LHC) at CERN. It employs an online data quality monitoring (DQM) system to promptly spot and diagnose particle data acquisition problems to avoid data quality loss. In this study, we present a semi-supervised spatio-temporal anomaly detection (AD) monitoring system for the physics particle reading channels of the Hadron Calorimeter (HCAL) of the CMS using three-dimensional digi-occupancy map data of the DQM. We propose the GraphSTAD system, which employs convolutional and graph neural networks to learn local spatial characteristics induced by particles traversing the detector and the global behavior owing to shared backend circuit connections and housing boxes of the channels, respectively. Recurrent neural networks capture the temporal evolution of the extracted spatial features. We validate the accuracy of the proposed AD system in capturing diverse channel fault types using the LHC collision data sets. The GraphSTAD system achieves production-level accuracy and is being integrated into the CMS core production system for real-time monitoring of the HCAL. We provide a quantitative performance comparison with alternative benchmark models to demonstrate the promising leverage of the presented system. |
| first_indexed | 2024-03-08T20:23:33Z |
| format | Article |
| id | doaj.art-e76afd8526164a548b0af49997b91372 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-08T20:23:33Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-e76afd8526164a548b0af49997b913722023-12-22T14:40:12ZengMDPI AGSensors1424-82202023-12-012324967910.3390/s23249679Spatio-Temporal Anomaly Detection with Graph Networks for Data Quality Monitoring of the Hadron CalorimeterMulugeta Weldezgina Asres0Christian Walter Omlin1Long Wang2David Yu3Pavel Parygin4Jay Dittmann5Georgia Karapostoli6Markus Seidel7Rosamaria Venditti8Luka Lambrecht9Emanuele Usai10Muhammad Ahmad11Javier Fernandez Menendez12Kaori Maeshima13the CMS-HCAL CollaborationCentre for Artificial Intelligence Research, Department of Information and Communication Technology, University of Agder, 4879 Grimstad, NorwayCentre for Artificial Intelligence Research, Department of Information and Communication Technology, University of Agder, 4879 Grimstad, NorwayDepartment of Physics, University of Maryland, College Park, MD 20742, USADepartment of Physics, Brown University, Providence, RI 02912, USADepartment of Physics and Astronomy, University of Rochester, Rochester, NY 14627, USADepartment of Physics, Baylor University, Waco, TX 76706, USADepartment of Physics & Astronomy, University of California, Riverside, CA 92521, USAInstitute of Particle Physics and Accelerator Technologies, Riga Technical University, LV-1048 Rīga, LatviaDepartment of Physics, Bari University, 70121 Bari, ItalyDepartment of Physics and Astronomy, Ghent University, B-9000 Ghent, BelgiumDepartment of Physics and Astronomy, University of Alabama, Tuscaloosa, AL 35487, USADepartment of Physics and Astronomy, Texas A&M University, College Station, TX 77843, USAInstituto Universitario de Ciencias y Tecnologías Espaciales de Asturias, University of Oviedo, 33004 Oviedo, SpainFermi National Accelerator Laboratory, Batavia, IL 60510, USAThe Compact Muon Solenoid (CMS) experiment is a general-purpose detector for high-energy collision at the Large Hadron Collider (LHC) at CERN. It employs an online data quality monitoring (DQM) system to promptly spot and diagnose particle data acquisition problems to avoid data quality loss. In this study, we present a semi-supervised spatio-temporal anomaly detection (AD) monitoring system for the physics particle reading channels of the Hadron Calorimeter (HCAL) of the CMS using three-dimensional digi-occupancy map data of the DQM. We propose the GraphSTAD system, which employs convolutional and graph neural networks to learn local spatial characteristics induced by particles traversing the detector and the global behavior owing to shared backend circuit connections and housing boxes of the channels, respectively. Recurrent neural networks capture the temporal evolution of the extracted spatial features. We validate the accuracy of the proposed AD system in capturing diverse channel fault types using the LHC collision data sets. The GraphSTAD system achieves production-level accuracy and is being integrated into the CMS core production system for real-time monitoring of the HCAL. We provide a quantitative performance comparison with alternative benchmark models to demonstrate the promising leverage of the presented system.https://www.mdpi.com/1424-8220/23/24/9679anomaly detectionmonitoringspatio-temporaldeep learninggraph networksparticle sensors |
| spellingShingle | Mulugeta Weldezgina Asres Christian Walter Omlin Long Wang David Yu Pavel Parygin Jay Dittmann Georgia Karapostoli Markus Seidel Rosamaria Venditti Luka Lambrecht Emanuele Usai Muhammad Ahmad Javier Fernandez Menendez Kaori Maeshima the CMS-HCAL Collaboration Spatio-Temporal Anomaly Detection with Graph Networks for Data Quality Monitoring of the Hadron Calorimeter Sensors anomaly detection monitoring spatio-temporal deep learning graph networks particle sensors |
| title | Spatio-Temporal Anomaly Detection with Graph Networks for Data Quality Monitoring of the Hadron Calorimeter |
| title_full | Spatio-Temporal Anomaly Detection with Graph Networks for Data Quality Monitoring of the Hadron Calorimeter |
| title_fullStr | Spatio-Temporal Anomaly Detection with Graph Networks for Data Quality Monitoring of the Hadron Calorimeter |
| title_full_unstemmed | Spatio-Temporal Anomaly Detection with Graph Networks for Data Quality Monitoring of the Hadron Calorimeter |
| title_short | Spatio-Temporal Anomaly Detection with Graph Networks for Data Quality Monitoring of the Hadron Calorimeter |
| title_sort | spatio temporal anomaly detection with graph networks for data quality monitoring of the hadron calorimeter |
| topic | anomaly detection monitoring spatio-temporal deep learning graph networks particle sensors |
| url | https://www.mdpi.com/1424-8220/23/24/9679 |
| work_keys_str_mv | AT mulugetaweldezginaasres spatiotemporalanomalydetectionwithgraphnetworksfordataqualitymonitoringofthehadroncalorimeter AT christianwalteromlin spatiotemporalanomalydetectionwithgraphnetworksfordataqualitymonitoringofthehadroncalorimeter AT longwang spatiotemporalanomalydetectionwithgraphnetworksfordataqualitymonitoringofthehadroncalorimeter AT davidyu spatiotemporalanomalydetectionwithgraphnetworksfordataqualitymonitoringofthehadroncalorimeter AT pavelparygin spatiotemporalanomalydetectionwithgraphnetworksfordataqualitymonitoringofthehadroncalorimeter AT jaydittmann spatiotemporalanomalydetectionwithgraphnetworksfordataqualitymonitoringofthehadroncalorimeter AT georgiakarapostoli spatiotemporalanomalydetectionwithgraphnetworksfordataqualitymonitoringofthehadroncalorimeter AT markusseidel spatiotemporalanomalydetectionwithgraphnetworksfordataqualitymonitoringofthehadroncalorimeter AT rosamariavenditti spatiotemporalanomalydetectionwithgraphnetworksfordataqualitymonitoringofthehadroncalorimeter AT lukalambrecht spatiotemporalanomalydetectionwithgraphnetworksfordataqualitymonitoringofthehadroncalorimeter AT emanueleusai spatiotemporalanomalydetectionwithgraphnetworksfordataqualitymonitoringofthehadroncalorimeter AT muhammadahmad spatiotemporalanomalydetectionwithgraphnetworksfordataqualitymonitoringofthehadroncalorimeter AT javierfernandezmenendez spatiotemporalanomalydetectionwithgraphnetworksfordataqualitymonitoringofthehadroncalorimeter AT kaorimaeshima spatiotemporalanomalydetectionwithgraphnetworksfordataqualitymonitoringofthehadroncalorimeter AT thecmshcalcollaboration spatiotemporalanomalydetectionwithgraphnetworksfordataqualitymonitoringofthehadroncalorimeter |