Interpretable Boosted Decision Tree Analysis for the Majorana Demonstrator

Abstract

The Majorana Demonstrator is a leading experiment searching for neutrinoless double-beta decay with high purity germanium detectors (HPGe). Machine learning provides a new way to maximize the amount of information provided by these detectors, but the data-driven nature makes it less interpretable compared to traditional analysis. An interpretability study reveals the machine's decision-making logic, allowing us to learn from the machine to feedback to the traditional analysis. In this work, we have presented the first machine learning analysis of the data from the Majorana Demonstrator; this is also the first interpretable machine learning analysis of any germanium detector experiment. Two gradient boosted decision tree models are trained to learn from the data, and a game-theory-based model interpretability study is conducted to understand the origin of the classification power. By learning from data, this analysis recognizes the correlations among reconstruction parameters to further enhance the background rejection performance. By learning from the machine, this analysis reveals the importance of new background categories to reciprocally benefit the standard Majorana analysis. This model is highly compatible with next-generation germanium detector experiments like LEGEND since it can be simultaneously trained on a large number of detectors.

13 pages, 9 figures

References in corpus (27)

• SMOTE: Synthetic Minority Over-sampling Technique
• Neutrinoless Double-Beta Decay: Status and Prospects
• A Search for Electron Neutrino Appearance at the Delta m**2 ~ 1 eV**2 Scale
• Neutrinoless double beta decay: 2015 review
• Final Results of GERDA on the Search for Neutrinoless Double-$\beta$ Decay
• Performance of the CMS Level-1 trigger in proton-proton collisions at $\sqrt{s}=$ 13 TeV
• A Convolutional Neural Network Neutrino Event Classifier
• Measurements of Higgs boson production and couplings in the four-lepton channel in $pp$ collisions at center-of-mass energies of 7 and 8 TeV with the ATLAS detector
• Search for Zero-Neutrino Double Beta Decay in 76Ge with the Majorana Demonstrator
• Kernel methods for interpretable machine learning of order parameters
• Evidence for production of single top quarks
• A Search for Neutrinoless Double-Beta Decay in ${}^{76}$Ge with 26 kg-yr of Exposure from the MAJORANA DEMONSTRATOR
• Convolutional Neural Networks Applied to Neutrino Events in a Liquid Argon Time Projection Chamber
• Background rejection in NEXT using deep neural networks
• Learning multiple order parameters with interpretable machines
• Search for heavy neutral leptons decaying into muon-pion pairs in the MicroBooNE detector
• Multi-site event discrimination for the MAJORANA DEMONSTRATOR
• Deep learning based pulse shape discrimination for germanium detectors
• Extracting Interpretable Physical Parameters from Spatiotemporal Systems using Unsupervised Learning
• The Processing of Enriched Germanium for the MAJORANA DEMONSTRATOR and R&D for a Possible Future Ton-Scale Ge-76 Double-Beta Decay Experiment
• The Majorana Demonstrator calibration system
• A Review on Machine Learning for Neutrino Experiments
• Suppression of Cosmic Muon Spallation Backgrounds in Liquid Scintillator Detectors Using Convolutional Neural Networks
• $\alpha$-event Characterization and Rejection in Point-Contact HPGe Detectors
• The MAJORANA DEMONSTRATOR Readout Electronics System
• ADC Nonlinearity Correction for the MAJORANA DEMONSTRATOR
• Cyclotron Radiation Emission Spectroscopy Signal Classification with Machine Learning in Project 8

Cited by in corpus (2)

• Interpretable machine learning approach for electron antineutrino selection in a large liquid scintillator detector
• Machine learning-powered data cleaning for LEGEND: a semi-supervised approach using affinity propagation and support vector machines