Pulse height estimation and pulse shape discrimination in pile-up neutron and gamma ray signals from an organic scintillation detector using multi-task learning

Junhyeok Kim; Byoungil Jeon; Jisung Hwang; Gyohyeok Song; Myungkook Moon; Gyuseong Cho

doi:10.1016/j.apradiso.2023.110880

Pulse height estimation and pulse shape discrimination in pile-up neutron and gamma ray signals from an organic scintillation detector using multi-task learning

Appl Radiat Isot. 2023 Sep:199:110880. doi: 10.1016/j.apradiso.2023.110880. Epub 2023 May 30.

Authors

Junhyeok Kim¹, Byoungil Jeon², Jisung Hwang¹, Gyohyeok Song¹, Myungkook Moon³, Gyuseong Cho⁴

Affiliations

¹ Department of Nuclear and Quantum Engineering, Korea Advanced Institute of Science and Technology, Daejeon, 34141, Republic of Korea.
² Artificial Intelligence Application & Strategy Team, Korea Atomic Energy Research Institute, Daejeon, 34507, Republic of Korea.
³ Neutron Science Division, Korea Atomic Energy Research Institute, Daejeon, 34507, Republic of Korea. Electronic address: [email protected].
⁴ Department of Nuclear and Quantum Engineering, Korea Advanced Institute of Science and Technology, Daejeon, 34141, Republic of Korea. Electronic address: [email protected].

PMID: 37271087
DOI: 10.1016/j.apradiso.2023.110880

Abstract

We developed a multi-tasking deep learning model for simultaneous pulse height estimation and pulse shape discrimination for pile-up n/γ signals. Compared with single-tasking models, our model showed better spectral correction performance with higher recall for neutrons. Further, it achieved more stable neutron counting with less signal loss and a lower error rate in the predicted gamma ray spectra. Our model can be applied to a dual radiation scintillation detector to discriminatively reconstruct each radiation spectrum for radioisotope identification and quantitative analysis.

Keywords: Deep learning; Multi-task learning; Organic scintillation detector; Pile-up; Pulse height estimation; Pulse shape discrimination.