SciPost Submission Page
Autoencoder-based time series anomaly detection for ATLAS Liquid Argon calorimeter data quality monitoring
by Vilius Cepaitis, Steven Schramm
Submission summary
| Authors (as registered SciPost users): | Vilius Cepaitis |
| Submission information | |
|---|---|
| Preprint Link: | scipost_202509_00060v1 (pdf) |
| Date submitted: | Sept. 30, 2025, 11:07 a.m. |
| Submitted by: | Vilius Cepaitis |
| Submitted to: | SciPost Physics Proceedings |
| Proceedings issue: | The 2nd European AI for Fundamental Physics Conference (EuCAIFCon2025) |
| Ontological classification | |
|---|---|
| Academic field: | Physics |
| Specialties: |
|
| Approach: | Experimental |
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.
Current status:
Awaiting resubmission
Reports on this Submission
Report
This proceeding present a proof of principle novel method based on machine learning to complement the classical data quality procedure to detect periods with poor quality data in the ATLAS Liquid Argon calorimeter. It is well written with sufficient figures and references.
I do not have any corrections and I recommend to publish the current version.
I do not have any corrections and I recommend to publish the current version.
Recommendation
Publish (easily meets expectations and criteria for this Journal; among top 50%)