Autoencoder-based time series anomaly detection for ATLAS Liquid Argon calorimeter data quality monitoring

TL;DR

This paper introduces an LSTM autoencoder method for detecting anomalies in ATLAS Liquid Argon calorimeter time series data, aiming to improve data quality monitoring in high-energy physics experiments.

Contribution

The novel application of LSTM autoencoders for real-time anomaly detection in calorimeter data enhances data quality assurance in particle physics experiments.

Findings

Successfully detects known noise burst issues

Demonstrates potential for broader anomaly detection

Validates approach with real detector data

Abstract

The ATLAS experiment at the LHC employs comprehensive data quality monitoring procedures to ensure high-quality physics data. This contribution presents a long short-term memory autoencoder-based algorithm for detecting anomalies in ATLAS Liquid Argon calorimeter data, represented as multidimensional time series of statistical moments of energy cluster properties. Trained on good-quality data, the model identifies anomalous intervals. Validation is performed using a known short-term issue of noise bursts, and the potential for broader application to transient calorimeter issues is discussed.