Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Deep Learning-Based $^{14}$C Pile-Up Identification in the JUNO Experiment

Wenxing Fang, Weidong Li, Wuming Luo, Zhaoxiang Wu, Miao He

Abstract

Measuring neutrino mass ordering (NMO) poses a fundamental challenge in neutrino physics. To address this, the Jiangmen Underground Neutrino Observatory (JUNO) experiment is scheduled to commence data collection in late 2024, with the ambitious goal of determining the NMO at a 3-sigma confidence level within a span of 6 years. A key factor in achieving this is ensuring a high-quality energy resolution of positrons. However, the presence of residual $^{14}$C isotopes in the liquid scintillator introduces pile-up effects that can impact the positron energy resolution. Mitigating these pile-up effects requires the identification of pile-up events, which presents a significant challenge. The signal from $^{14}$C is considerably smaller compared to the positron signal, making its identification difficult. Additionally, the close event time and vertex between a positron and a $^{14}$C further compound the identification challenge. This contribution focuses on the application of deep learning models for the identification of $^{14}$C pile-up events. It encompasses a range of models, including convolution-based models and advanced transformer models. Through performance evaluation, it shows the deep learning-based methods is promising to identify the pile-up events.

Deep Learning-Based $^{14}$C Pile-Up Identification in the JUNO Experiment

Abstract

Measuring neutrino mass ordering (NMO) poses a fundamental challenge in neutrino physics. To address this, the Jiangmen Underground Neutrino Observatory (JUNO) experiment is scheduled to commence data collection in late 2024, with the ambitious goal of determining the NMO at a 3-sigma confidence level within a span of 6 years. A key factor in achieving this is ensuring a high-quality energy resolution of positrons. However, the presence of residual C isotopes in the liquid scintillator introduces pile-up effects that can impact the positron energy resolution. Mitigating these pile-up effects requires the identification of pile-up events, which presents a significant challenge. The signal from C is considerably smaller compared to the positron signal, making its identification difficult. Additionally, the close event time and vertex between a positron and a C further compound the identification challenge. This contribution focuses on the application of deep learning models for the identification of C pile-up events. It encompasses a range of models, including convolution-based models and advanced transformer models. Through performance evaluation, it shows the deep learning-based methods is promising to identify the pile-up events.
Paper Structure (8 sections, 10 figures)

This paper contains 8 sections, 10 figures.

Table of Contents

  1. Introduction
  2. Dataset
  3. Deep learning models
  4. Two-dimensional CNN
  5. One-dimensional CNN
  6. Transformer-based model
  7. Performance
  8. Summary

Figures (10)

  • Figure 1: A schematic illustrating the IBD process.
  • Figure 2: A schematic view of the JUNO detector.
  • Figure 3: A mapping between PMT ID (presented by colors) and (x, y) coordinates.
  • Figure 4: An example of the charge channel.
  • Figure 5: An example of the first hit time channel.
  • ...and 5 more figures