Artificial neural networks for neutron/γ discrimination in the neutron detectors of NEDA

X. Fabian; G. Baulieu; L. Ducroux; O. Stézowski; A. Boujrad; E. Clément; S. Coudert; G. de France; N. Erduran; S. Ertürk; V. González; G. Jaworski; J. Nyberg; D. Ralet; E. Sanchis; R. Wadsworth

doi:10.1016/j.nima.2020.164750

Artificial neural networks for neutron/γ discrimination in the neutron detectors of NEDA

X. Fabian, G. Baulieu, L. Ducroux, O. Stézowski^*, A. Boujrad, E. Clément, S. Coudert, G. de France, N. Erduran, S. Ertürk, V. González, G. Jaworski, J. Nyberg, D. Ralet, E. Sanchis, R. Wadsworth

^*Corresponding author for this work

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

Abstract

Three different Artificial Neural Network architectures have been applied to perform neutron/γ discrimination in NEDA based on waveform and time-of-flight information. Using the coincident γ-rays from AGATA, we have been able to measure and compare on real data the performances of the Artificial Neural Networks as classifiers. While the general performances are quite similar for the data set we used, differences, in particular related to the computing times, have been highlighted. One of the Artificial Neural Network architecture has also been found more robust to time misalignment of the waveforms. Such a feature is of great interest for online processing of waveforms.

Original language	English
Article number	164750
Number of pages	9
Journal	Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment
Volume	986
DOIs	https://doi.org/10.1016/j.nima.2020.164750
Publication status	Published - 11 Jan 2021

Keywords

Artificial neural networks
Machine learning
n-γ discrimination
Neutron detector
Pulse-shape discrimination
γ-ray spectroscopy

Access to Document

10.1016/j.nima.2020.164750

Cite this

Fabian, X., Baulieu, G., Ducroux, L., Stézowski, O., Boujrad, A., Clément, E., Coudert, S., de France, G., Erduran, N., Ertürk, S., González, V., Jaworski, G., Nyberg, J., Ralet, D., Sanchis, E., & Wadsworth, R. (2021). Artificial neural networks for neutron/γ discrimination in the neutron detectors of NEDA. Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 986, Article 164750. https://doi.org/10.1016/j.nima.2020.164750

@article{c1623646e0f14fa9b21bcd6298ad1de6,

title = "Artificial neural networks for neutron/γ discrimination in the neutron detectors of NEDA",

abstract = "Three different Artificial Neural Network architectures have been applied to perform neutron/γ discrimination in NEDA based on waveform and time-of-flight information. Using the coincident γ-rays from AGATA, we have been able to measure and compare on real data the performances of the Artificial Neural Networks as classifiers. While the general performances are quite similar for the data set we used, differences, in particular related to the computing times, have been highlighted. One of the Artificial Neural Network architecture has also been found more robust to time misalignment of the waveforms. Such a feature is of great interest for online processing of waveforms.",

keywords = "Artificial neural networks, Machine learning, n-γ discrimination, Neutron detector, Pulse-shape discrimination, γ-ray spectroscopy",

author = "X. Fabian and G. Baulieu and L. Ducroux and O. St{\'e}zowski and A. Boujrad and E. Cl{\'e}ment and S. Coudert and {de France}, G. and N. Erduran and S. Ert{\"u}rk and V. Gonz{\'a}lez and G. Jaworski and J. Nyberg and D. Ralet and E. Sanchis and R. Wadsworth",

year = "2021",

month = jan,

day = "11",

doi = "10.1016/j.nima.2020.164750",

language = "English",

volume = "986",

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

issn = "0168-9002",

publisher = "Elsevier",

}

Fabian, X, Baulieu, G, Ducroux, L, Stézowski, O, Boujrad, A, Clément, E, Coudert, S, de France, G, Erduran, N, Ertürk, S, González, V, Jaworski, G, Nyberg, J, Ralet, D, Sanchis, E & Wadsworth, R 2021, 'Artificial neural networks for neutron/γ discrimination in the neutron detectors of NEDA', Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, vol. 986, 164750. https://doi.org/10.1016/j.nima.2020.164750

TY - JOUR

T1 - Artificial neural networks for neutron/γ discrimination in the neutron detectors of NEDA

AU - Fabian, X.

AU - Baulieu, G.

AU - Ducroux, L.

AU - Stézowski, O.

AU - Boujrad, A.

AU - Clément, E.

AU - Coudert, S.

AU - de France, G.

AU - Erduran, N.

AU - Ertürk, S.

AU - González, V.

AU - Jaworski, G.

AU - Nyberg, J.

AU - Ralet, D.

AU - Sanchis, E.

AU - Wadsworth, R.

PY - 2021/1/11

Y1 - 2021/1/11

N2 - Three different Artificial Neural Network architectures have been applied to perform neutron/γ discrimination in NEDA based on waveform and time-of-flight information. Using the coincident γ-rays from AGATA, we have been able to measure and compare on real data the performances of the Artificial Neural Networks as classifiers. While the general performances are quite similar for the data set we used, differences, in particular related to the computing times, have been highlighted. One of the Artificial Neural Network architecture has also been found more robust to time misalignment of the waveforms. Such a feature is of great interest for online processing of waveforms.

AB - Three different Artificial Neural Network architectures have been applied to perform neutron/γ discrimination in NEDA based on waveform and time-of-flight information. Using the coincident γ-rays from AGATA, we have been able to measure and compare on real data the performances of the Artificial Neural Networks as classifiers. While the general performances are quite similar for the data set we used, differences, in particular related to the computing times, have been highlighted. One of the Artificial Neural Network architecture has also been found more robust to time misalignment of the waveforms. Such a feature is of great interest for online processing of waveforms.

KW - Artificial neural networks

KW - Machine learning

KW - n-γ discrimination

KW - Neutron detector

KW - Pulse-shape discrimination

KW - γ-ray spectroscopy

UR - http://www.scopus.com/inward/record.url?scp=85092489481&partnerID=8YFLogxK

U2 - 10.1016/j.nima.2020.164750

DO - 10.1016/j.nima.2020.164750

M3 - Article

AN - SCOPUS:85092489481

SN - 0168-9002

VL - 986

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 - 164750

ER -

Artificial neural networks for neutron/γ discrimination in the neutron detectors of NEDA

Abstract

Keywords

Access to Document

Other files and links

Nuclear Physics Consolidated Grant

Nuclear Physics Consolidated Grant

Cite this

Artificial neural networks for neutron/γ discrimination in the neutron detectors of NEDA

Abstract

Keywords

Access to Document

Other files and links

Projects

Nuclear Physics Consolidated Grant

Nuclear Physics Consolidated Grant

Cite this