Autoencoder-based Online Data Quality Monitoring for the CMS Electromagnetic Calorimeter

TL;DR

This paper presents a real-time autoencoder-based anomaly detection system for the CMS ECAL DQM, significantly improving detection of unseen anomalies and operational efficiency during LHC Run 3.

Contribution

It introduces an unsupervised deep learning approach that enhances real-time anomaly detection in the CMS ECAL, surpassing existing benchmarks and adapting to new unforeseen issues.

Findings

Achieves false discovery rate between 10^-2 and 10^-4

Detects anomalies unseen in past data effectively

Demonstrates promising performance during LHC Run 3

Abstract

The online Data Quality Monitoring system (DQM) of the CMS electromagnetic calorimeter (ECAL) is a crucial operational tool that allows ECAL experts to quickly identify, localize, and diagnose a broad range of detector issues that would otherwise hinder physics-quality data taking. Although the existing ECAL DQM system has been continuously updated to respond to new problems, it remains one step behind newer and unforeseen issues. Using unsupervised deep learning, a real-time autoencoder-based anomaly detection system is developed that is able to detect ECAL anomalies unseen in past data. After accounting for spatial variations in the response of the ECAL and the temporal evolution of anomalies, the new system is able to efficiently detect anomalies while maintaining an estimated false discovery rate between $10^{-2}$ to $10^{-4}$, beating existing benchmarks by about two orders of magnitude. The real-world performance of the system is validated using anomalies found in 2018 and 2022 LHC collision data. Additionally, first results from deploying the autoencoder-based system in the CMS online DQM workflow for the ECAL barrel during Run 3 of the LHC are presented, showing its promising performance in detecting obscure issues that could have been missed in the existing DQM system.