This website requires JavaScript.

Machine Learning Classification of Fast Radio Bursts: II. Unsupervised Methods

Jia-Ming Zhu-GeJia-Wei LuoBing Zhang
Oct 2022
摘要
Fast radio bursts (FRBs) are one of the most mysterious astronomicaltransients. Observationally, they can be classified into repeaters andapparently non-repeaters. However, due to the lack of continuous observations,some apparently repeaters may have been incorrectly recognized asnon-repeaters. In a series of two papers, we intend to solve such problem withmachine learning. In this second paper of the series, we focus on an array ofunsupervised machine learning methods. We apply multiple unsupervised machinelearning algorithms to the first CHIME/FRB catalog to learn their features andclassify FRBs into different clusters without any premise about the FRBs beingrepeaters or non-repeaters. These clusters reveal the differences betweenrepeaters and non-repeaters. Then, by comparing with the identities of the FRBsin the observed classes, we evaluate the performance of various algorithms andanalyze the physical meaning behind the results. Finally, we recommend a listof most credible repeater candidates as targets for future observing campaignsto search for repeated bursts in combination of the results presented in PaperI using supervised machine learning methods.
展开全部
图表提取

暂无人提供速读十问回答

论文十问由沈向洋博士提出,鼓励大家带着这十个问题去阅读论文,用有用的信息构建认知模型。写出自己的十问回答,还有机会在当前页面展示哦。

Q1论文试图解决什么问题?
Q2这是否是一个新的问题?
Q3这篇文章要验证一个什么科学假设?
0
被引用
笔记
问答