Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2504.19958

Machine Learning Identification of Gravitationally Microlensed Gamma-Ray Bursts

Mohammad H. Zhoolideh Haghighi·Zeinab Kalantari·Sohrab Rahvar·Alaa Ibrahim
View original source ↗Read source document ↗Export metadata ↓

Abstract

Gravitational microlensing of gamma-ray bursts (GRBs) provides a unique opportunity to probe compact dark matter and small-scale structures in the Universe. However, identifying such microlensed GRBs within large data sets is a significant challenge. In this study, we develop a machine learning (ML) approach to distinguish lensed GRBs from their nonlensed counterparts, using simulated light curves. A comprehensive data set is generated, comprising labeled light curves for both categories. Features are extracted using the Cesium package, capturing critical temporal properties of the light curves. Multiple ML models are trained on the extracted features, with Random Forest achieving the best performance, delivering an accuracy of 86% and an F1 score of 0.86 (0.87) for the nonlensed (lensed) class. This approach successfully demonstrates the potential of ML for identifying gravitational lensing in GRBs, paving the way for future observational applications.

Explore related subjects

astro-ph.HE

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Mohammad H. Zhoolideh Haghighi, Zeinab Kalantari, Sohrab Rahvar, Alaa Ibrahim. 2025-10-17. Machine Learning Identification of Gravitationally Microlensed Gamma-Ray Bursts. https://doi.org/10.3847/1538-4357%2Fae03b1

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

ExTraSS: a Domain Decomposed 3D NLTE Radiative Transfer spectral synthesis code for nebular phase transients

In the nebular phase, supernovae are powered by radioactive decay and continuously fade, while their densities have decreased enough such that the expanding nebula becomes (largely) optically thin and the entire structure contributes to the emission. Models for the nebular phase need to take Non-Local Thermodynamic Equilibrium (NLTE) effects into account, while at the same time radiative transfer effects often cannot be ignored. To account for the asymmetric morphologies of SNe, 3D input ejecta models must be used. In this work, we present the $\texttt{ExTraSS}$ (EXplosive TRAnsient Spectral Simulator) code, which has been upgraded to be fully capable of 3D NLTE radiative transfer calculations in order to generate synthetic spectra for explosive transients in the nebular phase, with a focus on supernovae. We solve a long-standing difficulty of 3D NLTE radiative transfer -- to manage generation and storage of millions of photoexcitation rates over $\gtrsim10^{5}$ of cells -- by developing a new Domain Decomposition algorithm. We describe this new methodology and general code operations in detail, and analyse convergence and accuracy for $\texttt{ExTraSS}$.

astro-ph.HE↗
arXiv2026

Searching for Black Hole Candidates in Quiescence by Using Multi-band Observations in Globular Cluster M22 (NGC 6656)

We present a multi-wavelength investigation of radio sources in the globular cluster M22 (NGC 6656) using the Karl G. Jansky Very Large Array, Chandra and Hubble Space Telescope. By cross-matching the radio and X-ray source catalogs, we identify eight radio/X-ray counterparts, of which VLA22 is the most promising stellar-mass black hole (BH) candidate. Its radio and X-ray luminosities are consistent with the established $L_{\rm X}-L_{\rm R}$ correlation for BH low-mass X-ray binaries. The observed X-ray variability supports an accreting nature. One possible optical counterpart ($M_{\mathrm{814}} \approx 16.695 \pm 0.011$ mag) is identified. Based on its inferred stellar parameters, the estimated orbital period of $P_{\rm orb} \sim 16 \pm 6~{\rm h}$ places the proposed counterpart predominantly in the BH region rather than in the NS region in the $L_{\rm X}-P_{\rm orb}$ plane. These results demonstrate the effectiveness of joint radio, X-ray, and optical observations in identifying quiescent BH candidates in globular clusters.

astro-ph.HE↗
arXiv2026

Tidal Disruption of Blanets by Supermassive Black Holes: From Test Particles to Planetary-Mass Bodies in Kerr Spacetime

Planetary-mass bodies formed in active galactic nucleus (AGN) discs, termed "blanets", may undergo tidal disruption by the central supermassive black hole (SMBH). We analyse this process in Kerr spacetime using Mino-time geodesics and the Marck tidal tensor in a parallel-transported tetrad, treating the blanet as a test particle with finite size entering through the disruption criterion. For a blanet of $100 M_{\oplus}$ and $6 R_{\oplus}$ around a $10^7 M_{\odot}$ SMBH, the tidal radius is 0.82 AU, or 8.3 gravitational radii, requiring a non-perturbative relativistic treatment. The Hills mass depends on bulk density as $M_{\rm Hills}\proptoρ_p^{-1/2}$ and is independent of blanet mass at fixed density. Rocky compositions yield a lower Hills mass than a Sun-like star, while volatile-rich compositions yield a higher value, suggesting a potential composition diagnostic. The frozen-in fallback model gives a peak time of about 15 yr and a peak luminosity of $3.7\times10^{40}$ erg/s, about $3\times10^{-5}$ of the Eddington luminosity, predicting a faint, ultraviolet-peaked transient lasting roughly a century. Scalar resonant relaxation in the surrounding nuclear star cluster may deliver blanets to disruptive orbits over $10^8$ to $10^9$ yr, implying an estimated per-AGN event rate of $10^{-7}$ to $10^{-6}$ per year. Gravitational waves from sub-Earth-mass debris fragments remain approximately nine orders of magnitude below Laser Interferometer Space Antenna sensitivity.

astro-ph.HE↗