Scholarlink

We investigate the production of axion-like particles (ALPs) at the LHC through Z boson decays, where the Z couples to an axion and a photon. The axion decays into two bottom quarks, leading to a final state with two b-tagged jets and an isolated photon. We focus on distinguishing signal events from background using kinematic features and spatial distributions, including transverse momentum, angular separation ( \(\varDelta R\) ), and invariant mass. We compared different ML models like Boosted Decision Trees (BDT), Convolutional Neural Networks (CNN), and Graph Neural Networks (GNN), using these three variables for BDT and GNN, and using images on the \(\eta -\phi \) plane with pixel intensity as pT for CNN. Our preliminary results show improved classification accuracy, with the aim of setting new upper bounds on ALP production.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Exploring Z Portal Production of Axion Like Particles at LHC with Machine Learning Approaches

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Thallapalli Tejaswini

摘要

We investigate the production of axion-like particles (ALPs) at the LHC through Z boson decays, where the Z couples to an axion and a photon. The axion decays into two bottom quarks, leading to a final state with two b-tagged jets and an isolated photon. We focus on distinguishing signal events from background using kinematic features and spatial distributions, including transverse momentum, angular separation ( \(\varDelta R\) ), and invariant mass. We compared different ML models like Boosted Decision Trees (BDT), Convolutional Neural Networks (CNN), and Graph Neural Networks (GNN), using these three variables for BDT and GNN, and using images on the \(\eta -\phi \) plane with pixel intensity as pT for CNN. Our preliminary results show improved classification accuracy, with the aim of setting new upper bounds on ALP production.