Three-dimensional convolutional neural networks for neutrinoless double-beta decay signal/background discrimination in high-pressure gaseous Time Projection Chamber

Abstract

In the search for neutrinoless double-beta decay, the high-pressure gaseous Time Projection Chamber has a distinct advantage, because the ionization charge tracks produced by particle interactions are extended and the detector captures the full three-dimensional charge distribution with appropriate charge readout systems. Such information of tracks provides a crucial extra-handle for discriminating signal events against backgrounds. In this paper, we constructed a toy model to demonstrate where the discrimination power comes from and how much of it the neural network models have already harnessed. Then we adapted 3-dimensional convolutional and residual neural networks on the simulated double-beta and background charge tracks and tested their capabilities in classifying these two types of events. We show that both the 3D structure and the overall depth of the neural networks significantly improve the accuracy of the classifier and lead to results better than previous works. We also studied their performance under various spatial granularities as well as different diffusion and noise conditions. The results indicate that the methods are stable and generalize well despite varying experimental conditions.

arXiv comment27 pages, 13 figures, 5 tables

References in corpus (20)

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• A Unified Approach to the Classical Statistical Analysis of Small Signals
• Searching for Exotic Particles in High-Energy Physics with Deep Learning
• Search for Majorana Neutrinos near the Inverted Mass Hierarchy Region with KamLAND-Zen
• On the Number of Linear Regions of Deep Neural Networks
• The LHCb Trigger and its Performance in 2011
• Efficient, reliable and fast high-level triggering using a bonsai boosted decision tree
• Jet-Images -- Deep Learning Edition
• Current Status and Future Prospects of the SNO+ Experiment
• The event generator DECAY4 for simulation of double beta processes and decay of radioactive nuclei
• Searching for neutrinoless double-beta decay of ${}^{130}$Te with CUORE
• On the number of response regions of deep feed forward networks with piece-wise linear activations
• Convolutional Neural Networks Applied to Neutrino Events in a Liquid Argon Time Projection Chamber
• Sensitivity of NEXT-100 to neutrinoless double beta decay
• A neural network clustering algorithm for the ATLAS silicon pixel detector
• Background rejection in NEXT using deep neural networks
• A Low-Noise CMOS Pixel Direct Charge Sensor, Topmetal-II-
• PandaX-III: Searching for Neutrinoless Double Beta Decay with High Pressure Gaseous Time Projection Chambers
• Test of \textit{Topmetal-${II}^{-}$} In Liquid Nitrogen For Cryogenic Temperature TPCs
• Present status and future perspectives of the NEXT experiment

Cited by in corpus (8)

• Electromagnetic Showers Beyond Shower Shapes
• 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
• Timing and characterization of shaped pulses with MHz ADCs in a detector system: a comparative study and deep learning approach
• Neural network--featured timing systems for radiation detectors: performance evaluation based on bound analysis
• Universal uncertainty estimation for nuclear detector signals with neural networks and ensemble learning
• Measurement of the ionization response of amorphous selenium with 122keV $\gamma$ rays
• Application of CNN to a fine segmented scintillator detector for a single particle and neutrino-nucleon event