Reconstruction of fast neutron direction in segmented organic detectors using deep learning

Jun Woo Bae; Tingshiuan C. Wu; Igor Jovanovic

doi:10.1016/j.nima.2023.168024

Reconstruction of fast neutron direction in segmented organic detectors using deep learning

Jun Woo Bae, Tingshiuan C. Wu, Igor Jovanovic

Research output: Contribution to journal › Article › peer-review

3 Scopus citations

Abstract

A method for reconstructing the direction of a fast neutron source using a segmented organic scintillator-based detector and deep learning model is proposed and analyzed. The model is based on recurrent neural network, which can be trained by a sequence of data obtained from an event recorded in the detector and suitably pre-processed. The performance of deep learning-based model is compared with the conventional double-scatter detection algorithm in reconstructing the direction of a fast neutron source. With the deep learning model, the uncertainty in source direction of 0.301 rad is achieved with 100 neutron detection events in a segmented cubic organic scintillator detector with a side length of 46 mm. To reconstruct the source direction with the same angular resolution as the double-scatter algorithm, the deep learning method requires 75% fewer events. Application of this method could augment the operation of segmented detectors operated in the neutron scatter camera configuration for applications such as special nuclear material detection.

Original language	English
Article number	168024
Journal	Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment
Volume	1049
DOIs	https://doi.org/10.1016/j.nima.2023.168024
State	Published - Apr 2023
Externally published	Yes

Funding

This work was supported by the Department of Energy National Nuclear Security Administration, Consortium for Monitoring, Verification and Technology ( DE-NE000863 ), Nuclear Global Fellowship Program through the Korea Nuclear International Cooperation Foundation (KONICOF) funded by the Ministry of Science and ICT, Republic of Korea ( 2018M2C7A1A03070696 ), and partially supported by the Department of Energy, Nuclear Energy University Program Fellowship .

Keywords

Deep learning
Fast neutron detection
Neutron direction
Organic detector
Recurrent neural network

Access to Document

10.1016/j.nima.2023.168024

Cite this

@article{f7242d95377a4bddbe5301ec527352ae,

title = "Reconstruction of fast neutron direction in segmented organic detectors using deep learning",

abstract = "A method for reconstructing the direction of a fast neutron source using a segmented organic scintillator-based detector and deep learning model is proposed and analyzed. The model is based on recurrent neural network, which can be trained by a sequence of data obtained from an event recorded in the detector and suitably pre-processed. The performance of deep learning-based model is compared with the conventional double-scatter detection algorithm in reconstructing the direction of a fast neutron source. With the deep learning model, the uncertainty in source direction of 0.301 rad is achieved with 100 neutron detection events in a segmented cubic organic scintillator detector with a side length of 46 mm. To reconstruct the source direction with the same angular resolution as the double-scatter algorithm, the deep learning method requires 75% fewer events. Application of this method could augment the operation of segmented detectors operated in the neutron scatter camera configuration for applications such as special nuclear material detection.",

keywords = "Deep learning, Fast neutron detection, Neutron direction, Organic detector, Recurrent neural network",

author = "Bae, {Jun Woo} and Wu, {Tingshiuan C.} and Igor Jovanovic",

note = "Publisher Copyright: {\textcopyright} 2023 Elsevier B.V.",

year = "2023",

month = apr,

doi = "10.1016/j.nima.2023.168024",

language = "English",

volume = "1049",

journal = "Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment",

issn = "0168-9002",

publisher = "Elsevier",

}

Reconstruction of fast neutron direction in segmented organic detectors using deep learning. / Bae, Jun Woo; Wu, Tingshiuan C.; Jovanovic, Igor.
In: Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 1049, 168024, 04.2023.

Research output: Contribution to journal › Article › peer-review

TY - JOUR

T1 - Reconstruction of fast neutron direction in segmented organic detectors using deep learning

AU - Bae, Jun Woo

AU - Wu, Tingshiuan C.

AU - Jovanovic, Igor

PY - 2023/4

Y1 - 2023/4

N2 - A method for reconstructing the direction of a fast neutron source using a segmented organic scintillator-based detector and deep learning model is proposed and analyzed. The model is based on recurrent neural network, which can be trained by a sequence of data obtained from an event recorded in the detector and suitably pre-processed. The performance of deep learning-based model is compared with the conventional double-scatter detection algorithm in reconstructing the direction of a fast neutron source. With the deep learning model, the uncertainty in source direction of 0.301 rad is achieved with 100 neutron detection events in a segmented cubic organic scintillator detector with a side length of 46 mm. To reconstruct the source direction with the same angular resolution as the double-scatter algorithm, the deep learning method requires 75% fewer events. Application of this method could augment the operation of segmented detectors operated in the neutron scatter camera configuration for applications such as special nuclear material detection.

AB - A method for reconstructing the direction of a fast neutron source using a segmented organic scintillator-based detector and deep learning model is proposed and analyzed. The model is based on recurrent neural network, which can be trained by a sequence of data obtained from an event recorded in the detector and suitably pre-processed. The performance of deep learning-based model is compared with the conventional double-scatter detection algorithm in reconstructing the direction of a fast neutron source. With the deep learning model, the uncertainty in source direction of 0.301 rad is achieved with 100 neutron detection events in a segmented cubic organic scintillator detector with a side length of 46 mm. To reconstruct the source direction with the same angular resolution as the double-scatter algorithm, the deep learning method requires 75% fewer events. Application of this method could augment the operation of segmented detectors operated in the neutron scatter camera configuration for applications such as special nuclear material detection.

KW - Deep learning

KW - Fast neutron detection

KW - Neutron direction

KW - Organic detector

KW - Recurrent neural network

UR - http://www.scopus.com/inward/record.url?scp=85146437190&partnerID=8YFLogxK

U2 - 10.1016/j.nima.2023.168024

DO - 10.1016/j.nima.2023.168024

M3 - Article

AN - SCOPUS:85146437190

SN - 0168-9002

VL - 1049

JO - Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment

JF - Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment

M1 - 168024

ER -

Reconstruction of fast neutron direction in segmented organic detectors using deep learning

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this