Signal-background discrimination with convolutional neural networks in the PandaX-III experiment using MC simulation

Abstract

The PandaX-III experiment will search for neutrinoless double beta decay of ${}^{136}$Xe with high pressure gaseous time projection chambers at the China Jin-Ping underground Laboratory. The tracking feature of gaseous detectors helps suppress the background level, resulting in the improvement of the detection sensitivity. We study a method based on the convolutional neural networks to discriminate double beta decay signals against the background from high energy gammas generated by ${}^{214}$Bi and ${}^{208}$Tl decays based on detailed Monte Carlo simulation. Using the 2-dimensional projections of recorded tracks on two planes, the method successfully suppresses the background level by a factor larger than 100 with a high signal efficiency. An improvement of $62\%$ on the efficiency ratio of ${\epsilon }_s/\sqrt{{\epsilon }_b}$ is achieved in comparison with the baseline in the PandaX-III conceptual design report.

arXiv commentversion accepted by SCPMA, 11 pages, 10 figures and 4 tables

References in corpus (9)

• Double Beta Decay, Majorana Neutrinos, and Neutrino Mass
• Search for Majorana Neutrinos near the Inverted Mass Hierarchy Region with KamLAND-Zen
• Liquid Xenon Detectors for Particle Physics and Astrophysics
• Deep learning in color: towards automated quark/gluon jet discrimination
• Jet Substructure Classification in High-Energy Physics with Deep Neural Networks
• The event generator DECAY4 for simulation of double beta processes and decay of radioactive nuclei
• Parton Shower Uncertainties in Jet Substructure Analyses with Deep Neural Networks
• Gaseous time projection chambers for rare event detection: Results from the T-REX project. I. Double beta decay
• Pattern recognition of ${}^{136}$Xe double beta decay events and background discrimination in a high pressure Xenon TPC

Cited by in corpus (10)

• Neutral Bremsstrahlung emission in xenon unveiled
• Demonstration of background rejection using deep convolutional neural networks in the NEXT experiment
• Topological background discrimination in the PandaX-III neutrinoless double beta decay experiment
• Universal single-qubit non-adiabatic holonomic quantum gates in optomechanical system
• Signal identification with Kalman Filter towards background-free neutrinoless double beta decay searches in gaseous detectors
• Reconstruction of the event vertex in the PandaX-III experiment with convolution neural network
• Design and performance of a high-pressure xenon gas TPC as a prototype for a large-scale neutrinoless double-beta decay search
• Optimization of convolutional neural networks for background suppression in the PandaX-III experiment
• Deep learning based track reconstruction on CEPC luminometer
• Suppression of accidental backgrounds with deep neural networks in the PandaX-II experiment