x

## 留言板

 引用本文:
 Citation:

## Tag Z boson jets via convolutional neural networks

Li Jing, Sun Hao
PDF
HTML
• #### 摘要

高能物理中喷注识别任务是从背景中识别出感兴趣的特定信号, 这些信号对于在大型强子对撞机上发现新的粒子, 或者新的过程都有着非常重要的意义. 量能器中产生的能量沉积可以看做是对喷注的一种拍照, 分析这样产生的数据在机器学习领域中属于一个典型的视觉识别任务. 基于喷注图片, 本文探索了利用卷积神经网络(convolutional neural networks, CNNs)识别量子色动力学背景下的Z玻色子喷注, 并与传统的增强决策树(boosted decision trees, BDTs)方法进行了对比. 在本文利用的输入前提下, 三种相关的性能参数表明, CNN比BDT带来了约1.5倍的效果提升. 除此之外, 通过最优与最差的喷注图与混淆矩阵, 说明了CNN通过训练学习到的内容与整体识别能力.

#### Abstract

The jet tagging task in high-energy physics is to distinguish signals of interest from the background, which is of great importance for the discovery of new particles, or new processes, at the large hadron collider. The energy deposition generated in the calorimeter can be seen as a kind of picture. Based on this notion, tagging jets initiated by different processes becomes a classic image classification task in the computer vision field. We use jet images as the input built on high dimensional low-level information, energy-momentum four-vectors, to explore the potential of convolutional neural networks (CNNs). Four models of different depths are designed to make the best underlying useful features of jet images. Traditional multivariable method, boosted decision tree (BDT), is used as a baseline to determine the performance of networks. We introduce four observable quantities into BDTs: the mass, transverse momenta of fat jets, the distance between the leading and subleading jets, and N-subjettiness. Different tree numbers are adopted to build three kinds of BDTs, which is intended to have variable classifying abilities. After training and testing, the results show that the CNN 3 is the neatest and most efficient network under the design of stacking convolutional layers. Deepening the model could improve the performance to a certain extent but it is unable to work all the time. The performances of all BDTs are almost the same, which is possibly due to a small number of input observable types. The performance metrics show that the CNNs outperform the BDTs: the background rejection efficiency increases up to 150% at 50% signal efficiency. Besides, after inspecting the best and the worst samples, we conclude the characteristics of jets initiated by different processes: jets obtained by Z boson decays tend to concentrate in the center of jet images or have a clear differentiable substructure; the substructures of jets from general quantum chromodynamics processes have more random forms and not only just have two subjets. As the final step, the confusion matrix of the CNN 3 indicate that it comes to be kind of conservative. Exploring the way of keeping the balance between conservative and radical is our goal in the future work.

#### 作者及机构信息

###### 通信作者: 孙昊, haosun@dlut.edu.cn
• 基金项目: 国家自然科学基金(批准号: 11675033, 12075043)资助的课题

#### Authors and contacts

###### Corresponding author: Sun Hao, haosun@dlut.edu.cn
• Funds: Project supported by the National Natural Science Foundation of China (Grant Nos. 11675033, 12075043)

#### 施引文献

• 图 1  (a)信号平均喷注图; (b)背景平均喷注图; 横坐标$\eta$代表赝快度, 纵坐标代表方位角$\phi$.

Fig. 1.  (a) Signal average jet image; (b) background average jet image. $\eta$ and $\phi$ represent pseudo-rapidity and azimuth respectively

图 2  CNN 3结构示意图, 产生这张图片的程序来自https://github.com/gwding/draw_convnet

Fig. 2.  Architecture of the CNN 3. This figure was generated by adapting the code from https://github.com/gwding/draw_convnet.

图 3  (a)胖喷注的质量分布; (b)胖喷注的横向动量分布; (c)胖喷注含有的首要与次要喷注的距离分布; (d) N-subjettiness ${\tau }_{21}$的分布

Fig. 3.  (a) Mass distribution of fat jets; (b) transverse momentum distribution of fat jets; (c) distribution of distance between leading and subleading subjets; (d) distribution of N-subjettiness ${\tau }_{21}$.

图 4  不同模型的ROC曲线

Fig. 4.  ROC curves of different models.

图 5  CNN 3信号神经元对于信号(橘色)与背景(蓝色)的输出分布

Fig. 5.  Distribution of the signal neuron of the CNN 3 on signal and background samples.

图 6  最优与最差的信号喷注图

Fig. 6.  The best and the worst signal jet images.

图 7  最优与最差的背景喷注图

Fig. 7.  The best and the worst background jet images.

图 8  CNN 3在测试集上的混淆矩阵, 其中纵坐标代表喷注图的真实类别, 横坐标代表模型预测的类别

Fig. 8.  Confusion matrix of the CNN 3 on the test set. The true label is on the vertical axis, and the predicted label in on the horizontal axis.

• 文章访问数:  2173
• PDF下载量:  40
• 被引次数: 0
##### 出版历程
• 收稿日期:  2020-09-18
• 修回日期:  2020-11-13
• 上网日期:  2021-03-06
• 刊出日期:  2021-03-20

## 识别Z玻色子喷注的卷积神经网络方法

• 大连理工大学物理学院, 大连　116024
• ###### 通信作者: 孙昊, haosun@dlut.edu.cn
基金项目: 国家自然科学基金(批准号: 11675033, 12075043)资助的课题

/