arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2609.15261astro-ph.HEastro-ph.CO

物理信息神经网络与数据驱动模型用于GRB X射线光变曲线间隙重建

Physics-Informed Neural Networks and Data-Driven Models for GRB X-ray Light-Curve Gap Reconstruction

Ayush Garg, Ritik Kumar, Maria G. Dainotti, Vipul Sharma, Amit Shukla, Dieter H. Hartmann

首次发表
浏览论文内容

中文总结 AI 辅助

本研究在545个Swift-XRT GRB上基准测试四种模型(PINN、ReFANN、Siamese网络、PQR)重建X射线光变曲线间隙,显著降低W07平台参数不确定性,其中PINN断裂幂律先验降幅最大(41-49%),为不规则采样余辉重建提供系统比较。

中文摘要 AI 辅助

Swift-XRT对伽马射线暴(GRB)的X射线余辉观测经常包含时间间隙,这限制了Willingale等人2007(W07)平台参数测量平台结束时间$T_a$、平台通量$F_a$和平台后衰减指数$\alpha$的精度。由于这些参数是Dainotti关系(Dainotti等人2008、Dainotti等人2010、Dainotti等人2017)的基础,降低其测量不确定性可直接提高GRB的宇宙学统计能力。作为光变曲线重建研究系列(Dainotti等人2023、Manchanda等人2025、Kaushal等人2026、Gupta等人2026)的第五项工作,本研究在545个Swift-XRT GRB上对四种模型进行了基准测试:(i)在七种余辉先验(Zhang等人2006、Nousek等人2006)下的物理信息神经网络(PINN);(ii)ReFANN(Wang等人2020);(iii)Siamese双分支网络(Bromley等人1993、Gal等人2016);以及(iv)多项式分位数回归(PQR;Koenker等人2005)。所有四种方法相对于原始观测均降低了$\log T_a$、$\log F_a$和$\alpha$的分数不确定性。PINN的断裂幂律先验实现了最大降幅(约41%–49%),但异常率较高(约15%–20%),而ReFANN、Siamese网络和PQR在更广泛的形态范围内提供了一致的降幅(约19%–27%),异常比例($\lesssim4\\%$)较低。一种约化$\chi^2$先验选择方案恢复了与独立标注一致的形态分类,尽管未达到最佳单一先验的降幅。这些结果为不规则采样的GRB余辉提供了物理信息与数据驱动重建策略的系统基准。

英文摘要

Swift-XRT X-ray afterglows of gamma-ray bursts (GRBs) frequently contain temporal gaps that limit the precision with which the Willingale et al. 2007 (W07) plateau parameters measure plateau end time $T_a$, plateau flux $F_a$, and post-plateau decay index $α$. Because these parameters underpin the Dainotti relations (Dainotti et al. 2008, Dainotti et al. 2010, Dainotti et al. 2017), reducing their measurement uncertainty directly improves the cosmological statistical power of GRBs. As the fifth in a series of light-curve reconstruction studies (Dainotti et al. 2023, Manchanda et al. 2025, Kaushal et al. 2026, Gupta et al. 2026), this work benchmarks four models on 545 Swift-XRT GRBs: (i) a Physics-Informed Neural Network (PINN) under seven afterglow priors (Zhang et al. 2006, Nousek et al. 2006); (ii) ReFANN (Wang et al. 2020); (iii) a Siamese dual-branch network (Bromley et al. 1993, Gal et al. 2016); and (iv) Polynomial Quantile Regression (PQR; Koenker et al. 2005). All four methods reduce the fractional uncertainties in $\log T_a$, $\log F_a$, and $α$ relative to the original observations. The PINN broken power-law prior achieves the largest reductions ($\sim41$--$49\%$) at a higher outlier rate ($\sim15$--$20\%$), while ReFANN, the Siamese network, and PQR deliver consistent reductions ($\sim19$--$27\%$) with outlier fractions ($\lesssim4\%$) across a wider morphological range. A reduced-$χ^2$ prior-selection scheme recovers a morphological classification consistent with independent labelling, though without matching the best single-prior reduction. These results provide a systematic benchmark of physics-informed and data-driven reconstruction strategies for irregularly sampled GRB afterglows.

发表机构

  • Indian Institute of Technology(印度理工学院)
  • Indian Institute of Science(印度科学学院)
  • National Astronomical Observatory of Japan(日本国立天文台)
  • The Graduate University for Advanced Studies (SOKENDAI)(高级研究院(SOKENDAI))
  • Space Science Institute(空间科学研究所)
  • Nevada Center for Astrophysics, University of Nevada(内华达大学天体物理中心)
  • Indian Institute of Science Education and Research Bhopal(印度教育研究科学学院博帕尔分校)
  • Clemson University(克莱姆森大学)

机构由 AI 辅助整理,请以论文原文为准。

补充信息

↑