Optimization of convolutional neural networks for background suppression in the PandaX-III experiment

Abstract

The tracks recorded by a gaseous detector provide a possibility for charged particle identification. For searching the neutrinoless double beta decay events of 136Xe in the PandaX-III experiment, we optimized the convolutional neural network based on the Monte Carlo simulation data to improve the signal-background discrimination power. EfficientNet is chosen as the baseline model and the optimization is performed by tuning the hyperparameters. In particular, the maximum discrimination power is achieved by optimizing the channel number of the top convolutional layer. In comparison with our previous work, the significance of discrimination has been improved by about 70%.

arXiv comment15 pages, 13 figures

References in corpus (19)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Machine learning and the physical sciences
• Final Results of GERDA on the Search for Neutrinoless Double-$\beta$ Decay
• Toward the discovery of matter creation with neutrinoless double-beta decay
• Search for Neutrinoless Double-Beta Decay with the Complete EXO-200 Dataset
• A Convolutional Neural Network Neutrino Event Classifier
• Search for the Majorana Nature of Neutrinos in the Inverted Mass Ordering Region with KamLAND-Zen
• The event generator DECAY4 for simulation of double beta processes and decay of radioactive nuclei
• Final Result of the MAJORANA DEMONSTRATOR's Search for Neutrinoless Double-$\beta$ Decay in ${}^{76}$Ge
• A Convolutional Neural Network for Multiple Particle Identification in the MicroBooNE Liquid Argon Time Projection Chamber
• Measurement of the ${}^{136}$Xe two-neutrino double beta decay half-life via direct background subtraction in NEXT
• Demonstration of background rejection using deep convolutional neural networks in the NEXT experiment
• Electron Drift and Longitudinal Diffusion in High Pressure Xenon-Helium Gas Mixtures
• REST-for-Physics, a ROOT-based framework for event oriented data analysis and combined Monte Carlo response
• Signal-background discrimination with convolutional neural networks in the PandaX-III experiment using MC simulation
• Topological background discrimination in the PandaX-III neutrinoless double beta decay experiment
• Design and commissioning of a 600 L Time Projection Chamber with Microbulk Micromegas
• The TPC detector of PandaX-III Neutrinoless Double Beta Decay experiment
• Signal identification with Kalman Filter towards background-free neutrinoless double beta decay searches in gaseous detectors