Speaker
Description
The CMS Tracker in Run 3 consists of thousands of silicon modules (Pixel: 1856 modules, Strip: 15148 modules). Given the detector's aging and potential operational incidents, constant monitoring of its components is essential to ensure the highest data quality. To achieve this, the CMS Tracker group employs comprehensive Data Quality Monitoring (DQM) and Data Certification (DC) procedures and tools, both Online and Offline. DQM and DC experts assess detector performance and identify anomalies during data collection by meticulously analyzing hundreds of histograms. However, this process is limited by coarse time granularity and human error. To enhance the efficacy, speed, and granularity of data monitoring, the CMS Collaboration is developing machine learning (ML) models to assist experts in this task. Specifically, AutoEncoder models have successfully identified short anomalies (about 1 minute) hidden within hours of data, which were previously missed by human inspection. Integrating ML models into the DQM workflow has significantly improved anomaly detection, resulting in more effective and reliable data certification during Run 3.
| Experiment context, if any | CMS experiment |
|---|
