Issue |
EPJ Web of Conf.
Volume 295, 2024
26th International Conference on Computing in High Energy and Nuclear Physics (CHEP 2023)
|
|
---|---|---|
Article Number | 09031 | |
Number of page(s) | 7 | |
Section | Artificial Intelligence and Machine Learning | |
DOI | https://doi.org/10.1051/epjconf/202429509031 | |
Published online | 06 May 2024 |
https://doi.org/10.1051/epjconf/202429509031
The Neutron-Gamma Pulse Shape Discrimination of CLLB Detector
1 Key Laboratory of Radiation Physics and Technology of the Ministry of Education, 610064 Sichuan University, China
2 Institute of High Energy Physics, 100049 Chinese Academy of Sciences, China
3 College of Materials and Chemistry, 3100118 China Jiliang University, China
* Corresponding author: qians@ihep.ac.cn
Published online: 6 May 2024
Cs2LiLaBr6: Ce (CLLB) scintillator with the size of Φ 21mm × 25 mm coupled with PMT was used to detect neutron and gamma rays. The pulse shape discrimination (PSD) of neutrons and gamma rays by charge comparison method, the neutrons and gamma rays from AmBe source and fast neutron beam can be separated with figure-of-merit (FOM) values of 0.9 and 1.3, respectively. However, some neutron and gamma rays are difficult to distinguish, so new algorithms need to be investigated to improve the PSD performance of neutron and gamma. Artificial neural networks (ANN) have a very good image recognition capability, thus the ANN model was constructed to discriminate the waveforms of neutron and gamma rays. After ANN model training, the neutron and gamma signals of the CLLB detector were recognized with an accuracy of 98%, and the FOM value of the ANN method was calculated to be 19.4. This result is much higher than the charge comparison method, indicating better discrimination between neutrons and gamma rays with the ANN method.
© The Authors, published by EDP Sciences, 2024
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.