Suppression of cosmic muon spallation backgrounds in liquid scintillator detectors using convolutional neural networks
© 2019 Cosmic muon spallation backgrounds are ubiquitous in low-background experiments. For liquid scintillator-based experiments searching for neutrinoless double-beta decay, the spallation product 10C is an important background in the region of interest between 2–3MeV and determines the depth requ...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Elsevier BV
2021
|
| Online Access: | https://hdl.handle.net/1721.1/136413 |
| _version_ | 1826200667115487232 |
|---|---|
| author | Li, A Elagin, A Fraker, S Grant, C Winslow, L |
| author2 | Massachusetts Institute of Technology. Laboratory for Nuclear Science |
| author_facet | Massachusetts Institute of Technology. Laboratory for Nuclear Science Li, A Elagin, A Fraker, S Grant, C Winslow, L |
| author_sort | Li, A |
| collection | MIT |
| description | © 2019 Cosmic muon spallation backgrounds are ubiquitous in low-background experiments. For liquid scintillator-based experiments searching for neutrinoless double-beta decay, the spallation product 10C is an important background in the region of interest between 2–3MeV and determines the depth requirement for the experiment. We have developed an algorithm based on a convolutional neural network (CNN) that uses the temporal and spatial correlations in light emissions to identify 10C background events. Using a simple Monte Carlo simulation of a monolithic liquid scintillator detector like KamLAND, we find that the algorithm is capable of identifying 61.6% of the 10C at 90% signal acceptance, with a total uncertainty of 2.7%. A detector with perfect light collection can identify 98.2% at 90% signal acceptance. The algorithm is independent of vertex and energy reconstruction, so it is complementary to other frequently-used methods and can be expanded to other background sources. This work forms the foundation for more in depth studies of detector-dependent effects and more advanced CNN-based algorithms. |
| first_indexed | 2024-09-23T11:39:59Z |
| format | Article |
| id | mit-1721.1/136413 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T11:39:59Z |
| publishDate | 2021 |
| publisher | Elsevier BV |
| record_format | dspace |
| spelling | mit-1721.1/1364132023-02-24T18:42:45Z Suppression of cosmic muon spallation backgrounds in liquid scintillator detectors using convolutional neural networks Li, A Elagin, A Fraker, S Grant, C Winslow, L Massachusetts Institute of Technology. Laboratory for Nuclear Science © 2019 Cosmic muon spallation backgrounds are ubiquitous in low-background experiments. For liquid scintillator-based experiments searching for neutrinoless double-beta decay, the spallation product 10C is an important background in the region of interest between 2–3MeV and determines the depth requirement for the experiment. We have developed an algorithm based on a convolutional neural network (CNN) that uses the temporal and spatial correlations in light emissions to identify 10C background events. Using a simple Monte Carlo simulation of a monolithic liquid scintillator detector like KamLAND, we find that the algorithm is capable of identifying 61.6% of the 10C at 90% signal acceptance, with a total uncertainty of 2.7%. A detector with perfect light collection can identify 98.2% at 90% signal acceptance. The algorithm is independent of vertex and energy reconstruction, so it is complementary to other frequently-used methods and can be expanded to other background sources. This work forms the foundation for more in depth studies of detector-dependent effects and more advanced CNN-based algorithms. 2021-10-27T20:35:15Z 2021-10-27T20:35:15Z 2019 2020-11-18T14:57:25Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/136413 en 10.1016/J.NIMA.2019.162604 Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment Creative Commons Attribution-NonCommercial-NoDerivs License http://creativecommons.org/licenses/by-nc-nd/4.0/ application/pdf Elsevier BV arXiv |
| spellingShingle | Li, A Elagin, A Fraker, S Grant, C Winslow, L Suppression of cosmic muon spallation backgrounds in liquid scintillator detectors using convolutional neural networks |
| title | Suppression of cosmic muon spallation backgrounds in liquid scintillator detectors using convolutional neural networks |
| title_full | Suppression of cosmic muon spallation backgrounds in liquid scintillator detectors using convolutional neural networks |
| title_fullStr | Suppression of cosmic muon spallation backgrounds in liquid scintillator detectors using convolutional neural networks |
| title_full_unstemmed | Suppression of cosmic muon spallation backgrounds in liquid scintillator detectors using convolutional neural networks |
| title_short | Suppression of cosmic muon spallation backgrounds in liquid scintillator detectors using convolutional neural networks |
| title_sort | suppression of cosmic muon spallation backgrounds in liquid scintillator detectors using convolutional neural networks |
| url | https://hdl.handle.net/1721.1/136413 |
| work_keys_str_mv | AT lia suppressionofcosmicmuonspallationbackgroundsinliquidscintillatordetectorsusingconvolutionalneuralnetworks AT elagina suppressionofcosmicmuonspallationbackgroundsinliquidscintillatordetectorsusingconvolutionalneuralnetworks AT frakers suppressionofcosmicmuonspallationbackgroundsinliquidscintillatordetectorsusingconvolutionalneuralnetworks AT grantc suppressionofcosmicmuonspallationbackgroundsinliquidscintillatordetectorsusingconvolutionalneuralnetworks AT winslowl suppressionofcosmicmuonspallationbackgroundsinliquidscintillatordetectorsusingconvolutionalneuralnetworks |