Deep learning based pulse shape discrimination for germanium detectors

Abstract

Experiments searching for rare processes like neutrinoless double beta decay heavily rely on the identification of background events to reduce their background level and increase their sensitivity. We present a novel machine learning based method to recognize one of the most abundant classes of background events in these experiments. By combining a neural network for feature extraction with a smaller classification network, our method can be trained with only a small number of labeled events. To validate our method, we use signals from a broad-energy germanium detector irradiated with a ${}^{228}$Th gamma source. We find that it matches the performance of state-of-the-art algorithms commonly used for this detector type. However, it requires less tuning and calibration and shows potential to identify certain types of background events missed by other methods.

Published in Eur. Phys. J. C. 9 pages, 10 figures, 3 tables

References in corpus (10)

• The GERDA experiment for the search of 0νββ decay in ^{76}Ge
• The Large Enriched Germanium Experiment for Neutrinoless Double Beta Decay (LEGEND)
• Search for Zero-Neutrino Double Beta Decay in 76Ge with the Majorana Demonstrator
• The background in the neutrinoless double beta decay experiment GERDA
• Pulse shape discrimination for GERDA Phase I data
• Digital Pulseshape Analysis by Neural Networks for the Heidelberg-Moscow-Double-Beta-Decay-Experiment
• Deep Neural Networks for Energy and Position Reconstruction in EXO-200
• Background model for the MAJORANA DEMONSTRATOR
• Signal recognition efficiencies of artificial neural-network pulse-shape discrimination in HPGe $0\nu \beta \beta$-decay searches
• Characterisation of an n-type segmented BEGe detector

Cited by in corpus (14)

• Machine Learning in Nuclear Physics
• Simulation of semiconductor detectors in 3D with SolidStateDetectors.jl
• Cosmogenic activation in double beta decay experiments
• Towards an automated data cleaning with deep learning in CRESST
• A first application of machine and deep learning for background rejection in the ALPS II TES detector
• A machine learning-based methodology for pulse classification in dual-phase xenon time projection chambers
• Digital Signal Analysis based on Convolutional Neural Networks for Active Target Time Projection Chambers
• Double Beta Decay Experiments at Canfranc Underground Laboratory
• Interpretable Boosted Decision Tree Analysis for the Majorana Demonstrator
• Performance of a convolutional autoencoder designed to remove electronic noise from p-type point contact germanium detector signals
• Novel Machine Learning and Differentiable Programming Techniques applied to the VIP-2 Underground Experiment
• Data-driven detector signal characterization with constrained bottleneck autoencoders
• Machine learning-powered data cleaning for LEGEND: a semi-supervised approach using affinity propagation and support vector machines
• Binary Classification of Light and Dark Time Traces of a Transition Edge Sensor Using Convolutional Neural Networks