Using machine learning to improve neutron identification in water Cherenkov detectors
Water Cherenkov detectors like Super-Kamiokande, and the next generation Hyper-Kamiokande are adding gadolinium to their water to improve the detection of neutrons. By detecting neutrons in addition to the leptons in neutrino interactions, an improved separation between neutrino and anti-neutrinos,...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-09-01
|
| Series: | Frontiers in Big Data |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fdata.2022.978857/full |
| _version_ | 1797997731990470656 |
|---|---|
| author | Blair Jamieson Matt Stubbs Sheela Ramanna John Walker John Walker Nick Prouse Ryosuke Akutsu Patrick de Perio Patrick de Perio Wojciech Fedorko |
| author_facet | Blair Jamieson Matt Stubbs Sheela Ramanna John Walker John Walker Nick Prouse Ryosuke Akutsu Patrick de Perio Patrick de Perio Wojciech Fedorko |
| author_sort | Blair Jamieson |
| collection | DOAJ |
| description | Water Cherenkov detectors like Super-Kamiokande, and the next generation Hyper-Kamiokande are adding gadolinium to their water to improve the detection of neutrons. By detecting neutrons in addition to the leptons in neutrino interactions, an improved separation between neutrino and anti-neutrinos, and reduced backgrounds for proton decay searches can be expected. The neutron signal itself is still small and can be confused with muon spallation and other background sources. In this paper, machine learning techniques are employed to optimize the neutron capture detection capability in the new intermediate water Cherenkov detector (IWCD) for Hyper-K. In particular, boosted decision tree (XGBoost), graph convolutional network (GCN), and dynamic graph convolutional neural network (DGCNN) models are developed and benchmarked against a statistical likelihood-based approach, achieving up to a 10% increase in classification accuracy. Characteristic features are also engineered from the datasets and analyzed using SHAP (SHapley Additive exPlanations) to provide insight into the pivotal factors influencing event type outcomes. The dataset used in this research consisted of roughly 1.6 million simulated particle gun events, divided nearly evenly between neutron capture and a background electron source. The current samples used for training are representative only, and more realistic samples will need to be made for the analyses of real data. The current class split is 50/50, but there is expected to be a difference between the classes in the real experiment, and one might consider using resampling techniques to address the issue of serious imbalances in the class distribution in real data if necessary. |
| first_indexed | 2024-04-11T10:37:19Z |
| format | Article |
| id | doaj.art-eb9e502a042f4ce884be8b8560353d96 |
| institution | Directory Open Access Journal |
| issn | 2624-909X |
| language | English |
| last_indexed | 2024-04-11T10:37:19Z |
| publishDate | 2022-09-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Big Data |
| spelling | doaj.art-eb9e502a042f4ce884be8b8560353d962022-12-22T04:29:16ZengFrontiers Media S.A.Frontiers in Big Data2624-909X2022-09-01510.3389/fdata.2022.978857978857Using machine learning to improve neutron identification in water Cherenkov detectorsBlair Jamieson0Matt Stubbs1Sheela Ramanna2John Walker3John Walker4Nick Prouse5Ryosuke Akutsu6Patrick de Perio7Patrick de Perio8Wojciech Fedorko9Physics Department, University of Winnipeg, Winnipeg, MB, CanadaApplied Computer Science Department, University of Winnipeg, Winnipeg, MB, CanadaApplied Computer Science Department, University of Winnipeg, Winnipeg, MB, CanadaPhysics Department, University of Winnipeg, Winnipeg, MB, CanadaScience Division, TRIUMF, Vancouver, BC, CanadaScience Division, TRIUMF, Vancouver, BC, CanadaScience Division, TRIUMF, Vancouver, BC, CanadaScience Division, TRIUMF, Vancouver, BC, CanadaKavli IPMU (WPI), UTIAS, The University of Tokyo, Tokyo, JapanScience Division, TRIUMF, Vancouver, BC, CanadaWater Cherenkov detectors like Super-Kamiokande, and the next generation Hyper-Kamiokande are adding gadolinium to their water to improve the detection of neutrons. By detecting neutrons in addition to the leptons in neutrino interactions, an improved separation between neutrino and anti-neutrinos, and reduced backgrounds for proton decay searches can be expected. The neutron signal itself is still small and can be confused with muon spallation and other background sources. In this paper, machine learning techniques are employed to optimize the neutron capture detection capability in the new intermediate water Cherenkov detector (IWCD) for Hyper-K. In particular, boosted decision tree (XGBoost), graph convolutional network (GCN), and dynamic graph convolutional neural network (DGCNN) models are developed and benchmarked against a statistical likelihood-based approach, achieving up to a 10% increase in classification accuracy. Characteristic features are also engineered from the datasets and analyzed using SHAP (SHapley Additive exPlanations) to provide insight into the pivotal factors influencing event type outcomes. The dataset used in this research consisted of roughly 1.6 million simulated particle gun events, divided nearly evenly between neutron capture and a background electron source. The current samples used for training are representative only, and more realistic samples will need to be made for the analyses of real data. The current class split is 50/50, but there is expected to be a difference between the classes in the real experiment, and one might consider using resampling techniques to address the issue of serious imbalances in the class distribution in real data if necessary.https://www.frontiersin.org/articles/10.3389/fdata.2022.978857/fullmachine learninggraph neural networkswater Cherenkov detectorparticle physicsneutrino physics |
| spellingShingle | Blair Jamieson Matt Stubbs Sheela Ramanna John Walker John Walker Nick Prouse Ryosuke Akutsu Patrick de Perio Patrick de Perio Wojciech Fedorko Using machine learning to improve neutron identification in water Cherenkov detectors Frontiers in Big Data machine learning graph neural networks water Cherenkov detector particle physics neutrino physics |
| title | Using machine learning to improve neutron identification in water Cherenkov detectors |
| title_full | Using machine learning to improve neutron identification in water Cherenkov detectors |
| title_fullStr | Using machine learning to improve neutron identification in water Cherenkov detectors |
| title_full_unstemmed | Using machine learning to improve neutron identification in water Cherenkov detectors |
| title_short | Using machine learning to improve neutron identification in water Cherenkov detectors |
| title_sort | using machine learning to improve neutron identification in water cherenkov detectors |
| topic | machine learning graph neural networks water Cherenkov detector particle physics neutrino physics |
| url | https://www.frontiersin.org/articles/10.3389/fdata.2022.978857/full |
| work_keys_str_mv | AT blairjamieson usingmachinelearningtoimproveneutronidentificationinwatercherenkovdetectors AT mattstubbs usingmachinelearningtoimproveneutronidentificationinwatercherenkovdetectors AT sheelaramanna usingmachinelearningtoimproveneutronidentificationinwatercherenkovdetectors AT johnwalker usingmachinelearningtoimproveneutronidentificationinwatercherenkovdetectors AT johnwalker usingmachinelearningtoimproveneutronidentificationinwatercherenkovdetectors AT nickprouse usingmachinelearningtoimproveneutronidentificationinwatercherenkovdetectors AT ryosukeakutsu usingmachinelearningtoimproveneutronidentificationinwatercherenkovdetectors AT patrickdeperio usingmachinelearningtoimproveneutronidentificationinwatercherenkovdetectors AT patrickdeperio usingmachinelearningtoimproveneutronidentificationinwatercherenkovdetectors AT wojciechfedorko usingmachinelearningtoimproveneutronidentificationinwatercherenkovdetectors |