This study developed a novel method for detecting hypernuclear events recorded in nuclear emulsion sheets using machine learning techniques. The artificial neural network-based object detection model was trained on surrogate images created through Monte Carlo simulations and image-style transformations using generative adversarial networks. The performance of the proposed model was evaluated using α-decay events obtained from the J-PARC E07 emulsion data. The model achieved approximately twice the detection efficiency of conventional image processing and reduced the time spent on manual visual inspection by approximately 1/17. The established method was successfully applied to the detection of hypernuclear events. This approach is a state-of-the-art tool for discovering rare events recorded in nuclear emulsion sheets without any real data for training.
@article{arxiv.2305.00884,
title = {Hypernuclear event detection in the nuclear emulsion with Monte Carlo simulation and machine learning},
author = {A. Kasagi and W. Dou and V. Drozd and H. Ekawa and S. Escrig and Y. Gao and Y. He and E. Liu and A. Muneem and M. Nakagawa and K. Nakazawa and C. Rappold and N. Saito and T. R. Saito and S. Sugimoto and M. Taki and Y. K. Tanaka and A. Yanai and J. Yoshida and M. Yoshimoto and H. Wang},
journal= {arXiv preprint arXiv:2305.00884},
year = {2023}
}