English

Suppression of Neutron Background using Deep Neural Network and Fourier Frequency Analysis at the KOTO Experiment

High Energy Physics - Experiment 2026-04-22 v1 Instrumentation and Detectors

Abstract

We present two analysis techniques for distinguishing background events induced by neutrons from photon signal events in the search for the rare KL0π0ννˉK^0_L\rightarrow\pi^0\nu\bar{\nu} decay at the J-PARC KOTO experiment. These techniques employed a deep convolutional neural network and Fourier frequency analysis to discriminate neutrons from photons, based on their variations in cluster shape and pulse shape, in the electromagnetic calorimeter made of undoped CsI. The results effectively suppressed the neutron background by a factor of 5.6×1055.6\times10^5, while maintaining the efficiency of KL0π0ννˉK^0_L\rightarrow\pi^0\nu\bar{\nu} at 70%70\%.

Keywords

Cite

@article{arxiv.2309.12063,
  title  = {Suppression of Neutron Background using Deep Neural Network and Fourier Frequency Analysis at the KOTO Experiment},
  author = {Y. -C. Tung and J. Li and Y. B. Hsiung and C. Lin and H. Nanjo and T. Nomura and J. C. Redeker and N. Shimizu and S. Shinohara and K. Shiomi and Y. W. Wah and T. Yamanaka},
  journal= {arXiv preprint arXiv:2309.12063},
  year   = {2026}
}

Comments

7 pages, 10 figures