Machine Learning-Powered Data Cleaning for LEGEND

The Large Enriched Germanium Experiment for Neutrinoless Double-Beta Decay (LEGEND) will operate in two phases in the search for neutrinoless double-beta decay (0νββ). The first (second) stage will employ up to 200 (1000) kg of ⁷⁶Ge semiconductor detectors to achieve a half-life sensitivity of 10²⁷ (10²⁸) years. In this study, we present a data-driven approach to remove non-physical events captured by ⁷⁶Ge detectors in LEGEND-200 powered by a novel artificial intelligence model. We utilize Affinity Propagation to cluster events based on their shape and a Support Vector Machine to classify events into different categories. We demonstrate that our model efficiently classifies different categories of events, achieving a physical event sacrifice of < 0.001 %. This method will provide an automated data cleaning mechanism for LEGEND, which requires significant time and human effort when performed with traditional procedures.