Pulse shape discrimination and exploration of scintillation signals using convolutional neural networks
Publication Date
2020Journal Title
Machine Learning: Science and Technology
ISSN
2632-2153
Publisher
IOP Publishing
Volume
1
Issue
4
Language
en
Type
Article
This Version
VoR
Metadata
Show full item recordCitation
Griffiths, J., Kleinegesse, S., Saunders, D., Taylor, R., & Vacheret, A. (2020). Pulse shape discrimination and exploration of scintillation signals using convolutional neural networks. Machine Learning: Science and Technology, 1 (4) https://doi.org/10.1088/2632-2153/abb781
Abstract
<jats:title>Abstract</jats:title>
<jats:p>We demonstrate the use of a convolutional neural network to perform neutron-gamma pulse shape discrimination, where the only inputs to the network are the raw digitised silicon photomultiplier signals from a dual scintillator detector element made of <jats:sup>6</jats:sup>Li F:ZnS(Ag) scintillator and PVT plastic. A realistic labelled dataset was created to train the network by exposing the detector to an AmBe source, and a data-driven method utilising a separate photomultiplier tube was used to assign labels to the recorded signals. This approach is compared to the charge integration and continuous wavelet transform methods and a simpler artificial neural net. It is found to provide superior levels of discrimination, achieving an area under the curve of 0.996 ± 0.003. We find that the neural network is capable of extracting interpretable features directly from the raw data. In addition, by visualising the high-dimensional representations of the network with the t-SNE algorithm, we discover that not only is this method robust to minor mislabeling of the training dataset but that it is possible to identify an underlying substructure within the signals that goes beyond the original labelling. This technique could be utilised to explore and cluster complex, raw detector data in a novel way that may reveal more insights than standard analysis methods.</jats:p>
Keywords
Paper, machine learning, convolutional neural networks, pulse shape discrimination, 6Li F:ZnS(Ag), t-SNE
Sponsorship
H2020 European Research Council (682474)
Identifiers
mlstabb781, abb781, mlst-100166.r1
External DOI: https://doi.org/10.1088/2632-2153/abb781
This record's URL: https://www.repository.cam.ac.uk/handle/1810/333209
Rights
Licence:
http://creativecommons.org/licenses/by/4.0
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.