Anomaly Detection Based on Machine Learning for the CMS Electromagnetic Calorimeter Online Data Quality Monitoring

TL;DR

This paper presents a real-time autoencoder-based anomaly detection system for the CMS electromagnetic calorimeter, improving online data quality monitoring by effectively identifying anomalies with low false positives during LHC operations.

Contribution

Introduces a novel semi-supervised autoencoder approach that leverages temporal and spatial detector data for enhanced anomaly detection in high-energy physics experiments.

Findings

Successfully detects anomalies in LHC data from 2018 and 2022.

Reduces false discovery rate in anomaly detection.

Identifies issues missed by existing monitoring systems during Run 3.

Abstract

A real-time autoencoder-based anomaly detection system using semi-supervised machine learning has been developed for the online Data Quality Monitoring system of the electromagnetic calorimeter of the CMS detector at the CERN LHC. 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. Additionally, 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.