Deep Learning the Effects of Photon Sensors on the Event Reconstruction Performance in an Antineutrino Detector

We provide a fast approach incorporating the usage of deep learning for studying the effects of the number of photon sensors in an antineutrino detector on the event reconstruction performance therein. This work is a first attempt to harness the power of deep learning for detector designing and upgr...

Full description

Saved in:
Bibliographic Details
Main Authors: Chang-Wei Loh, Zhi-Qiang Qian, Rui Zhang, You-Hang Liu, De-Wen Cao, Wei Wang, Hai-Bo Yang, Ming Qi
Format: Article
Language:English
Published: Wiley 2018-01-01
Series:Advances in High Energy Physics
Online Access:http://dx.doi.org/10.1155/2018/7024309
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849434720138428416
author Chang-Wei Loh
Zhi-Qiang Qian
Rui Zhang
You-Hang Liu
De-Wen Cao
Wei Wang
Hai-Bo Yang
Ming Qi
author_facet Chang-Wei Loh
Zhi-Qiang Qian
Rui Zhang
You-Hang Liu
De-Wen Cao
Wei Wang
Hai-Bo Yang
Ming Qi
author_sort Chang-Wei Loh
collection DOAJ
description We provide a fast approach incorporating the usage of deep learning for studying the effects of the number of photon sensors in an antineutrino detector on the event reconstruction performance therein. This work is a first attempt to harness the power of deep learning for detector designing and upgrade planning. Using the Daya Bay detector as a case study and the vertex reconstruction performance as the objective for the deep neural network, we find that the photomultiplier tubes (PMTs) at Daya Bay have different relative importance to the vertex reconstruction. More importantly, the vertex position resolutions for the Daya Bay detector follow approximately a multiexponential relationship with respect to the number of PMTs and, hence, the coverage. This could also assist in deciding on the merits of installing additional PMTs for future detector plans. The approach could easily be used with other objectives in place of vertex reconstruction.
format Article
id doaj-art-e3e806d037cf4917bb9f126f7f3e67b3
institution Kabale University
issn 1687-7357
1687-7365
language English
publishDate 2018-01-01
publisher Wiley
record_format Article
series Advances in High Energy Physics
spelling doaj-art-e3e806d037cf4917bb9f126f7f3e67b32025-08-20T03:26:33ZengWileyAdvances in High Energy Physics1687-73571687-73652018-01-01201810.1155/2018/70243097024309Deep Learning the Effects of Photon Sensors on the Event Reconstruction Performance in an Antineutrino DetectorChang-Wei Loh0Zhi-Qiang Qian1Rui Zhang2You-Hang Liu3De-Wen Cao4Wei Wang5Hai-Bo Yang6Ming Qi7Physics Department, Nanjing University, 22 Hankou Road, Nanjing, Jiangsu, ChinaPhysics Department, Nanjing University, 22 Hankou Road, Nanjing, Jiangsu, ChinaPhysics Department, Nanjing University, 22 Hankou Road, Nanjing, Jiangsu, ChinaPhysics Department, Nanjing University, 22 Hankou Road, Nanjing, Jiangsu, ChinaPhysics Department, Nanjing University, 22 Hankou Road, Nanjing, Jiangsu, ChinaPhysics Department, Nanjing University, 22 Hankou Road, Nanjing, Jiangsu, ChinaPhysics Department, Nanjing University, 22 Hankou Road, Nanjing, Jiangsu, ChinaPhysics Department, Nanjing University, 22 Hankou Road, Nanjing, Jiangsu, ChinaWe provide a fast approach incorporating the usage of deep learning for studying the effects of the number of photon sensors in an antineutrino detector on the event reconstruction performance therein. This work is a first attempt to harness the power of deep learning for detector designing and upgrade planning. Using the Daya Bay detector as a case study and the vertex reconstruction performance as the objective for the deep neural network, we find that the photomultiplier tubes (PMTs) at Daya Bay have different relative importance to the vertex reconstruction. More importantly, the vertex position resolutions for the Daya Bay detector follow approximately a multiexponential relationship with respect to the number of PMTs and, hence, the coverage. This could also assist in deciding on the merits of installing additional PMTs for future detector plans. The approach could easily be used with other objectives in place of vertex reconstruction.http://dx.doi.org/10.1155/2018/7024309
spellingShingle Chang-Wei Loh
Zhi-Qiang Qian
Rui Zhang
You-Hang Liu
De-Wen Cao
Wei Wang
Hai-Bo Yang
Ming Qi
Deep Learning the Effects of Photon Sensors on the Event Reconstruction Performance in an Antineutrino Detector
Advances in High Energy Physics
title Deep Learning the Effects of Photon Sensors on the Event Reconstruction Performance in an Antineutrino Detector
title_full Deep Learning the Effects of Photon Sensors on the Event Reconstruction Performance in an Antineutrino Detector
title_fullStr Deep Learning the Effects of Photon Sensors on the Event Reconstruction Performance in an Antineutrino Detector
title_full_unstemmed Deep Learning the Effects of Photon Sensors on the Event Reconstruction Performance in an Antineutrino Detector
title_short Deep Learning the Effects of Photon Sensors on the Event Reconstruction Performance in an Antineutrino Detector
title_sort deep learning the effects of photon sensors on the event reconstruction performance in an antineutrino detector
url http://dx.doi.org/10.1155/2018/7024309
work_keys_str_mv AT changweiloh deeplearningtheeffectsofphotonsensorsontheeventreconstructionperformanceinanantineutrinodetector
AT zhiqiangqian deeplearningtheeffectsofphotonsensorsontheeventreconstructionperformanceinanantineutrinodetector
AT ruizhang deeplearningtheeffectsofphotonsensorsontheeventreconstructionperformanceinanantineutrinodetector
AT youhangliu deeplearningtheeffectsofphotonsensorsontheeventreconstructionperformanceinanantineutrinodetector
AT dewencao deeplearningtheeffectsofphotonsensorsontheeventreconstructionperformanceinanantineutrinodetector
AT weiwang deeplearningtheeffectsofphotonsensorsontheeventreconstructionperformanceinanantineutrinodetector
AT haiboyang deeplearningtheeffectsofphotonsensorsontheeventreconstructionperformanceinanantineutrinodetector
AT mingqi deeplearningtheeffectsofphotonsensorsontheeventreconstructionperformanceinanantineutrinodetector