Speaker
Description
The increasing complexity and data throughput of the CMS experiment at the LHC demand scalable and intelligent tools to ensure data quality. In this talk, we present a machine learning-oriented infrastructure designed to support the offline data quality monitoring (DQM) process at CMS. The infrastructure enables the integration of ML algorithms into the DQM workflow, providing auto- mated assistance in detecting anomalies and evaluating detector performance across large volumes of data. It is built upon modular and scalable components, facilitating model training, evaluation, and inference within the CMS computing environment. We describe the architecture, data handling mechanisms, and deployment strategy, along with a discussion of the challenges in integrating ML workflows into existing high-energy physics (HEP) data processing pipelines. Preliminary results show the effectiveness of this infrastructure in streamlining the offline DQM process, reducing manual workload, and opening new possibilities for intelligent data quality assessment in HEP.
| Do you plan to submit a 4-page extended abstract on OpenReview (only for Presentations/Posters)? | Maybe |
|---|