Machine learning-powered data cleaning for LEGEND: a semi-supervised approach using affinity propagation and support vector machines

Abstract

Neutrinoless double-beta decay ($0\nu \beta \beta$) is a rare nuclear process that, if observed, will provide insight into the nature of neutrinos and help explain the matter-antimatter asymmetry in the universe. The Large Enriched Germanium Experiment for Neutrinoless Double-Beta Decay (LEGEND) will operate in two phases to search for $0\nu \beta \beta$. The first (second) stage will employ 200 (1000) kg of High-Purity Germanium (HPGe) enriched in ${}^{76}$Ge to achieve a half-life sensitivity of 10${}^{27}$ (10${}^{28}$) years. In this study, we present a semi-supervised data-driven approach to remove non-physical events captured by HPGe detectors powered by a novel artificial intelligence model. We utilize Affinity Propagation to cluster waveform signals based on their shape and a Support Vector Machine to classify them into different categories. We train, optimize, test our model on data taken from a natural abundance HPGe detector installed in the Full Chain Test experimental stand at the University of North Carolina at Chapel Hill. We demonstrate that our model yields a maximum sacrifice of physics events of $0.024_{-0.003}^{+0.004}\%$. Our model is being used to accelerate data cleaning development for LEGEND-200 and will serve to improve data cleaning procedures for LEGEND-1000.

17 pages, 13 figures

References in corpus (19)

• Kernel methods in machine learning
• Final Results of GERDA on the Search for Neutrinoless Double-$\beta$ Decay
• Toward the discovery of matter creation with neutrinoless double-beta decay
• Final Result of the MAJORANA DEMONSTRATOR's Search for Neutrinoless Double-$\beta$ Decay in ${}^{76}$Ge
• Production, characterization and operation of ${}^{76}$Ge enriched BEGe detectors in GERDA
• LEGEND-1000 Preconceptual Design Report
• Multi-site event discrimination for the MAJORANA DEMONSTRATOR
• Deep learning based pulse shape discrimination for germanium detectors
• Off-line data processing and analysis for the GERDA experiment
• Pulse shape analysis in GERDA Phase II
• $\alpha$-event Characterization and Rejection in Point-Contact HPGe Detectors
• The MAJORANA DEMONSTRATOR Readout Electronics System
• Characterization of inverted coaxial ${}^{76}$Ge detectors in GERDA for future double-$\beta$ decay experiments
• KamNet: An Integrated Spatiotemporal Deep Neural Network for Rare Event Search in KamLAND-Zen
• A Low Energy Rare Event Search with the Majorana Demonstrator
• MAJORANA Collaboration's Experience with Germanium Detectors
• Interpretable Boosted Decision Tree Analysis for the Majorana Demonstrator
• A novel wide-angle Compton Scanner setup to study bulk events in germanium detectors
• Ad-hoc Pulse Shape Simulation using Cyclic Positional U-Net