Anomaly Detection for Automated Data Quality Monitoring in the CMS Detector

the CMS Muon Detector Collaboration; Andrew Brinkerhoff; Chosila Sutantawibul; Indara Suarez; Robert White; Caio Daumann; Jonathan Guiang; Chad Freer; Samuel May; Bennett Marsh; Darin Acosta; Alex Aubuchon; Emanuela Barberis; Aaron Bundock; Claudio Campagnari; Evan Collins; Preston Epps; Johannes Erdmann; Henning Flaecher; Junshen Huang; Vivan Nguyen; Ryan Nie; Sudarshan Paramesvaran; John Rotter; Kaitlin Salyer; Siddhesh Sawant; Tanvi Sheokand; Darien Wood

doi:10.1007/s41781-025-00147-2

Anomaly Detection for Automated Data Quality Monitoring in the CMS Detector

the CMS Muon Detector Collaboration, Andrew Brinkerhoff^*, Chosila Sutantawibul, Indara Suarez, Robert White, Caio Daumann, Jonathan Guiang, Chad Freer, Samuel May, Bennett Marsh, Darin Acosta, Alex Aubuchon, Emanuela Barberis, Aaron Bundock, Claudio Campagnari, Evan Collins, Preston Epps, Johannes Erdmann, Henning Flaecher, Junshen HuangVivan Nguyen, Ryan Nie, Sudarshan Paramesvaran, John Rotter, Kaitlin Salyer, Siddhesh Sawant, Tanvi Sheokand, Darien Wood

^*Corresponding author for this work

Research output: Contribution to journal › Article (Academic Journal) › peer-review

Abstract

Successful operation of large particle detectors like the Compact Muon Solenoid (CMS) at the CERN Large Hadron Collider requires rapid, in-depth assessment of data quality. We introduce the “AutoDQM” system for Automated Data Quality Monitoring using advanced statistical techniques and unsupervised machine learning. Anomaly detection algorithms based on the beta-binomial probability function and principal component analysis are tested on the full set of proton-proton collision data collected by CMS in 2022. AutoDQM identifies anomalous “bad” data affected by significant detector malfunction at a rate 4 – 6 times higher than “good” data, demonstrating its effectiveness as a general data quality monitoring tool.

Original language	English
Article number	4
Number of pages	21
Journal	EPJ Research Infrastructures
Volume	10
DOIs	https://doi.org/10.1007/s41781-025-00147-2
Publication status	Published - 9 Feb 2026

Bibliographical note

Keywords

Data Quality Monitoring
PCA
Anomoly Detection
Particle Physics

Access to Document

10.1007/s41781-025-00147-2Licence: CC BY

Handle.net

Persistent link

Cite this

the CMS Muon Detector Collaboration, Brinkerhoff, A., Sutantawibul, C., Suarez, I., White, R., Daumann, C., Guiang, J., Freer, C., May, S., Marsh, B., Acosta, D., Aubuchon, A., Barberis, E., Bundock, A., Campagnari, C., Collins, E., Epps, P., Erdmann, J., Flaecher, H., ... Wood, D. (2026). Anomaly Detection for Automated Data Quality Monitoring in the CMS Detector. EPJ Research Infrastructures, 10, Article 4. https://doi.org/10.1007/s41781-025-00147-2

@article{d0b3499be1a145349135ce455b53f434,

title = "Anomaly Detection for Automated Data Quality Monitoring in the CMS Detector",

abstract = "Successful operation of large particle detectors like the Compact Muon Solenoid (CMS) at the CERN Large Hadron Collider requires rapid, in-depth assessment of data quality. We introduce the “AutoDQM” system for Automated Data Quality Monitoring using advanced statistical techniques and unsupervised machine learning. Anomaly detection algorithms based on the beta-binomial probability function and principal component analysis are tested on the full set of proton-proton collision data collected by CMS in 2022. AutoDQM identifies anomalous “bad” data affected by significant detector malfunction at a rate 4 – 6 times higher than “good” data, demonstrating its effectiveness as a general data quality monitoring tool.",

keywords = "Data Quality Monitoring, PCA, Anomoly Detection, Particle Physics",

author = "\{the CMS Muon Detector Collaboration\} and Andrew Brinkerhoff and Chosila Sutantawibul and Indara Suarez and Robert White and Caio Daumann and Jonathan Guiang and Chad Freer and Samuel May and Bennett Marsh and Darin Acosta and Alex Aubuchon and Emanuela Barberis and Aaron Bundock and Claudio Campagnari and Evan Collins and Preston Epps and Johannes Erdmann and Henning Flaecher and Junshen Huang and Vivan Nguyen and Ryan Nie and Sudarshan Paramesvaran and John Rotter and Kaitlin Salyer and Siddhesh Sawant and Tanvi Sheokand and Darien Wood",

note = "{\textcopyright} The Author(s) 2026. ",

year = "2026",

month = feb,

day = "9",

doi = "10.1007/s41781-025-00147-2",

language = "English",

volume = "10",

journal = "EPJ Research Infrastructures",

issn = "3091-4558",

publisher = "Springer International Publishing Cham",

}

the CMS Muon Detector Collaboration, Brinkerhoff, A, Sutantawibul, C, Suarez, I, White, R, Daumann, C, Guiang, J, Freer, C, May, S, Marsh, B, Acosta, D, Aubuchon, A, Barberis, E, Bundock, A, Campagnari, C, Collins, E, Epps, P, Erdmann, J, Flaecher, H, Huang, J, Nguyen, V, Nie, R, Paramesvaran, S, Rotter, J, Salyer, K, Sawant, S, Sheokand, T & Wood, D 2026, 'Anomaly Detection for Automated Data Quality Monitoring in the CMS Detector', EPJ Research Infrastructures, vol. 10, 4. https://doi.org/10.1007/s41781-025-00147-2

TY - JOUR

T1 - Anomaly Detection for Automated Data Quality Monitoring in the CMS Detector

AU - the CMS Muon Detector Collaboration

AU - Brinkerhoff, Andrew

AU - Sutantawibul, Chosila

AU - Suarez, Indara

AU - White, Robert

AU - Daumann, Caio

AU - Guiang, Jonathan

AU - Freer, Chad

AU - May, Samuel

AU - Marsh, Bennett

AU - Acosta, Darin

AU - Aubuchon, Alex

AU - Barberis, Emanuela

AU - Bundock, Aaron

AU - Campagnari, Claudio

AU - Collins, Evan

AU - Epps, Preston

AU - Erdmann, Johannes

AU - Flaecher, Henning

AU - Huang, Junshen

AU - Nguyen, Vivan

AU - Nie, Ryan

AU - Paramesvaran, Sudarshan

AU - Rotter, John

AU - Salyer, Kaitlin

AU - Sawant, Siddhesh

AU - Sheokand, Tanvi

AU - Wood, Darien

PY - 2026/2/9

Y1 - 2026/2/9

N2 - Successful operation of large particle detectors like the Compact Muon Solenoid (CMS) at the CERN Large Hadron Collider requires rapid, in-depth assessment of data quality. We introduce the “AutoDQM” system for Automated Data Quality Monitoring using advanced statistical techniques and unsupervised machine learning. Anomaly detection algorithms based on the beta-binomial probability function and principal component analysis are tested on the full set of proton-proton collision data collected by CMS in 2022. AutoDQM identifies anomalous “bad” data affected by significant detector malfunction at a rate 4 – 6 times higher than “good” data, demonstrating its effectiveness as a general data quality monitoring tool.

AB - Successful operation of large particle detectors like the Compact Muon Solenoid (CMS) at the CERN Large Hadron Collider requires rapid, in-depth assessment of data quality. We introduce the “AutoDQM” system for Automated Data Quality Monitoring using advanced statistical techniques and unsupervised machine learning. Anomaly detection algorithms based on the beta-binomial probability function and principal component analysis are tested on the full set of proton-proton collision data collected by CMS in 2022. AutoDQM identifies anomalous “bad” data affected by significant detector malfunction at a rate 4 – 6 times higher than “good” data, demonstrating its effectiveness as a general data quality monitoring tool.

KW - Data Quality Monitoring

KW - PCA

KW - Anomoly Detection

KW - Particle Physics

U2 - 10.1007/s41781-025-00147-2

DO - 10.1007/s41781-025-00147-2

M3 - Article (Academic Journal)

C2 - 41726844

SN - 3091-4558

VL - 10

JO - EPJ Research Infrastructures

JF - EPJ Research Infrastructures

M1 - 4

ER -

Anomaly Detection for Automated Data Quality Monitoring in the CMS Detector

Abstract

Bibliographical note

Keywords

Access to Document

Handle.net

Fingerprint

Cite this