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, principal component analysis, and neural network autoencoder image evaluation 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.
Cite
@article{arxiv.2501.13789,
title = {Anomaly Detection for Automated Data Quality Monitoring in the CMS Detector},
author = {Andrew Brinkerhoff and Chosila Sutantawibul and Robert White and Caio Daumann and Chad Freer and Indara Suarez and Samuel May and Vivan Nguyen and Jonathan Guiang and Bennett Marsh and Darin Acosta and Alex Aubuchon and Emanuela Barberis and Aaron Bundock and Evan Collins and Preston Epps and Johannes Erdmann and Henning Flaecher and Junshen Huang and Ryan Nie and Sudarshan Paramesvaran and John Rotter and Kaitlin Salyer and Siddhesh Sawant and Tanvi Sheokand and Darien Wood},
journal= {arXiv preprint arXiv:2501.13789},
year = {2026}
}
Comments
16 pages, 14 figures