Abstract
Organic scintillation detectors like BC501A, BC519, NE213, etc. have an inherent ability to classify neutrons and \(\gamma \)-rays through a process known as pulse shape discrimination (PSD). We developed a deep neural network (DNN)-based machine learning algorithm to discriminate neutrons\(/\gamma \)-rays. The algorithm was trained with data obtained from a BC501A detector considering the Cf-252 source. Further, to assess the performance of the DNN-based PSD algorithm, the algorithm was tested with an independent data set acquired with a different source-detector set-up, namely, BC501 detector with Am–Be source and a different digitiser. Results indicate that our proposed algorithm can successfully discriminate the neutrons and \(\gamma \)-rays with reasonably good accuracy for the independent data set.
Similar content being viewed by others
References
B Sabbah and A Suhami, Nucl. Instrum. Methods 58, 102 (1968)
J Kalyna and I J Taylor, Nucl Instrum. Methods 88, 227 (1970)
I A Pawełczak et al, Nucl Instrum. Methods 711, 21 (2013)
Z Wang et al, Nucl Instrum. Methods 760, 5 (2014)
M J I Balmer et al, Nucl Instrum. Methods 788, 146 (2015)
M Nakhostin, IEEE Trans. Nucl. Sci. 66(5), 838 (2019)
E Doucet et al, Nucl Instrum. Methods 954, 161201 (2020)
E Ronchi et al, Nucl Instrum. Methods 610(2), 534 (2009)
T S Sanderson et al, IEEE Nucl. Sci. Symp. Conf. Record. 199 (2012)
S Akkoyun, Ann. Nucl. Energy 55, 297 (2013)
C Fu et al, Ann. Nucl. Energy 120, 410 (2018)
R Wurtz et al, Nucl Instrum. Methods 901, 46 (2018)
M Durbin et al, Nucl Instrum. Methods 987, 164826 (2021)
BC501, BC501A and BC519 scintillation detectors data sheet, https://www.crystals.saint-gobain.com/sites/imdf.crystals.com/files/documents/bc501-501a-519-data-sheet.pdf
H Mohsen et al, Future Comput. Inform. J. 3(1), 68 (2018)
S C Leemann et al, Phys. Rev. Lett. 123(19), 194801 (2019)
J M Adams and G White, Nucl. Instrum. Methods 156(3), 459 (1978)
M D Aspinall et al, Nucl. Instrum. Methods 583(2), 432 (2007)
Kerasio, https://keras.io
Tensor Flow, https://www.tensorflow.org/
Relu Activation Function, https://keras.io/api/layers/activations/#relu-function
Keras Activation Functions, https://keras.io/activations
Keras Optimizer, https://keras.io/optimizers
Keras Loss Functions, https://keras.io/losses
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Karmakar, A., Pal, A., Anil Kumar, G. et al. Deep neural network-based pulse shape discrimination of neutrons and \(\gamma \)-rays in organic scintillation detectors. Pramana - J Phys 97, 157 (2023). https://doi.org/10.1007/s12043-023-02641-x
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12043-023-02641-x
Keywords
- Nuclear security and safety
- scintillation detectors
- neutrons
- \(\gamma \)-rays
- pulse shape discrimination
- deep neural network