1. IE browser is NOT supported anymore. Please use Chrome, Firefox or Edge instead.
2. If you are a new user, please register to get an IHEP SSO account through https://login.ihep.ac.cn/registlight.jsp Any questions, please email us at helpdesk@ihep.ac.cn or call 88236855.
3. If you need to create a conference in the "Conferences, Workshops and Events" zone, please email us at helpdesk@ihep.ac.cn.
4. The max file size allowed for upload is 100 Mb.
4–7 Jun 2017
中国科学院成都情报文献中心
Asia/Shanghai timezone

Using Deep Learning in Event Reconstruction and Detector Design

6 Jun 2017, 11:20
20m
中国科学院成都情报文献中心

中国科学院成都情报文献中心

四川省成都市一环路南二段16号
Oral Presentation 高能物理计算软件 高能物理软件:JUNO

Speaker

章维 罗 (Nanjing University)

Description

In this work, we present the usage of deep learning in event reconstruction, particularly in vertex and energy reconstruction. We will use the approach on the Daya Bay antineutrino detector. Using the results therefrom, we apply deep learning to detector designs, and found that the vertex and energy resolution of the Daya Bay detector has an exponential relationship with the number of photomultiplier tubes (PMT). The placement strategy of PMTs has also been studied in this work. 在这项工作中,我们提出了使用深度学习的事例重建,特别是在顶点与能量重建。我们将使用的方法在大亚湾中微子探测器中。利用所得结果,我们将深度学习应用到探测器设计中。我们发现大亚湾探测器的顶点和能量分辨率与光电倍增管(PMT)的个数是个 e 指数关系。在此工作,我们也对光电倍增管的布局策略做出了分析。

Primary author

章维 罗 (Nanjing University)

Co-authors

Ming Qi (Nanjing University) Zhiqiang Qian (Nanjing University)

Presentation materials