Speaker
Description
Data quality monitoring (DQM) is essential for ensuring reliable detector performance. Hydra is an AI-enabled DQM framework developed at Jefferson Lab that leverages complementary machine learning techniques to automate the evaluation of quality assurance plots. The framework incorporates computer vision models for image classification, autoencoders for anomaly detection, clustering algorithms for identifying patterns and previously unrecognized detector states, and Siamese neural networks for similarity-based comparisons. Together, these approaches enable Hydra to support both supervised and unsupervised monitoring strategies, reducing dependence on extensive labeled training datasets while expanding its ability to identify unusual detector behavior.
This contribution will describe Hydra's architecture, machine learning methodologies, user interface, and operational experience. We will also discuss opportunities to extend these capabilities to the Electron-Ion Collider (EIC), where the scale and complexity of the ePIC detector will motivate adaptable, reliable, and increasingly autonomous data quality monitoring systems.