Signal recognition efficiencies of artificial neural-network pulse-shape discrimination in HPGe $0\nu\beta\beta$-decay searches

TL;DR

This paper demonstrates that artificial neural networks can effectively discriminate signal from background in germanium detectors for neutrinoless double beta decay searches, with a systematic uncertainty of 5%.

Contribution

It introduces a neural network-based pulse-shape discrimination method and evaluates its efficiency and systematic uncertainties in germanium detector simulations.

Findings

Neural networks effectively identify background pulses.

Discrimination efficiency varies with training set composition.

Systematic uncertainty on signal efficiency is estimated at 5%.

Abstract

A pulse-shape discrimination method based on artificial neural networks was applied to pulses simulated for different background, signal and signal-like interactions inside a germanium detector. The simulated pulses were used to investigate variations of efficiencies as a function of used training set. It is verified that neural networks are well-suited to identify background pulses in true-coaxial high-purity germanium detectors. The systematic uncertainty on the signal recognition efficiency derived using signal-like evaluation samples from calibration measurements is estimated to be 5\%. This uncertainty is due to differences between signal and calibration samples.