Estimating the peak energy of Swift gamma-ray bursts using supervised machine learning

Abstract

Gamma-ray bursts (GRBs) are among the most energetic explosive phenomena in the Universe, and their peak energy ($E_{\mathrm{p}}$) is a key physical quantity for understanding the prompt emission mechanism. However, due to the limited energy coverage of the Swift satellite, a large fraction of Swift GRBs lack reliable peak energy measurements. Therefore, developing an accurate and efficient method for estimating $E_{\mathrm{p}}$ is of great importance. In this work, we propose a method based on the SuperLearner framework that integrates multiple supervised machine learning algorithms to estimate the $E_{\mathrm{p}}$ of Swift/BAT GRBs. We used the Swift/BAT observational data from December 2004 to September 2022 as training features, and adopted the peak energies of 516 GRBs jointly detected by Swift and either Fermi/GBM or Konus-Wind as training labels. After training and testing multiple supervised models, the final SuperLearner ensemble yields a more robust and reliable predictive model. In 100 iterations of five-fold cross-validation, the estimated $E_{\mathrm{p}}^{\prime }$ values show a tight correlation with the observed $E_{\mathrm{p}}$, with an average Pearson correlation coefficient of $r=0.72$. Compared with previous Bayesian estimates, our model provides estimations that are likely closer to the true values. Based on the trained model, we further estimated the peak energies of 650 Swift GRBs, significantly increasing the number of GRBs with estimated peak energies and providing new statistical support for constraining GRB emission mechanisms and energy origins.

12 pages, 16 figures, 5 tables

References in corpus (44)

• XGBoost: A Scalable Tree Boosting System
• The Physics of Gamma-Ray Bursts
• Intrinsic spectra and energetics of BeppoSAX Gamma-Ray Bursts with known redshifts
• GRB Formation Rates inferred from the Spectral Peak Energy - Luminosity Relation
• The BATSE Gamma-Ray Burst Spectral Catalog. I. High Time Resolution Spectroscopy of Bright Bursts using High Energy Resolution Data
• The Ep,i - Eiso correlation in GRBs: updated observational status, re-analysis and main implications
• Lower Limits on Lorentz Factors in Gamma Ray Bursts
• Discerning the physical origins of cosmological Gamma-ray bursts based on multiple observational criteria: the cases of z=6.7 GRB 080913, z=8.3 GRB 090423, and some short/hard GRBs
• The Fermi GBM Gamma-Ray Burst Spectral Catalog: Four Years Of Data
• The Fourth Fermi-GBM Gamma-Ray Burst Catalog: A Decade of Data
• GRB Radiative Efficiencies Derived from the Swift Data: GRBs vs. XRFs, Long vs. Short
• A Complete Catalog of Swift GRB Spectra and Durations: Demise of a Physical Origin for Pre-Swift High-Energy Correlations
• The Second Swift BAT Gamma-Ray Burst Catalog
• Making a Short Gamma-Ray Burst from a Long one: Implications for the Nature of GRB 060614
• The First Swift BAT Gamma-Ray Burst Catalog
• Short versus Long Gamma-Ray Bursts: spectra, energetics, and luminosities
• Evidence for a Photospheric Component in the Prompt Emission of the Short GRB120323A and its Effects on the GRB Hardness-Luminosity Relation
• The Ep,i - Eiso correlation: type I gamma-ray bursts and the new classification method
• The Fermi GBM Gamma-Ray Burst Spectral Catalog: 10 Years of Data
• The Konus-Wind catalog of gamma-ray bursts with known redshifts. I. Bursts detected in the triggered mode
• A Theory of Mulicolor Black Body Emission from Relativistically Expanding Plasmas
• The Epeak-Eiso plane of long Gamma Ray Bursts and selection effects
• Revisiting the Long/Soft-Short/Hard Classification of Gamma-Ray Bursts in the Fermi Era
• Are there cosmological evolution trends on Gamma-Ray Burst features?
• The second Konus-Wind catalog of short gamma-ray bursts
• The Konus-Wind catalog of gamma-ray bursts with known redshifts. II. Waiting mode bursts simultaneously detected by Swift/BAT
• The photospheric origin of the Yonetoku relation in gamma-ray bursts
• A Tight $L_{\mathrm{p},\mathrm{iso}}-E_{\mathrm{p}}^{\prime }-{\Gamma }_0$ Correlation of Gamma-Ray Bursts
• Spectral analysis of Swift long GRBs with known redshift
• A review of unsupervised learning in astronomy
• Machine learning classification of CHIME fast radio bursts -- I. Supervised methods
• Spectral and temporal analysis of the joint Swift/BAT-Fermi/GBM GRB sample
• A comprehensive forecast for cosmological parameter estimation using joint observations of gravitational waves and short $\gamma$-ray bursts
• An analytic derivation of the empirical correlations of gamma-ray bursts
• Hardness as a Spectral Peak Estimator for Gamma-Ray Bursts
• Predicting the redshift of gamma-ray loud AGNs using supervised machine learning
• Predicting the redshift of gamma-ray loud AGNs using Supervised Machine Learning: Part 2
• Exploring the Key Features of Repeating Fast Radio Bursts with Machine Learning
• GRB Redshift Estimation using Machine Learning and the Associated Web-App
• Deep Neural Networks for Estimation of Gamma-Ray Burst Redshifts
• Revisiting the Spectral-Energy Correlations of GRBs with {\it Fermi} Data I: Model-wise Properties
• Multi-messenger standard-siren cosmology for third-generation gravitational-wave detectors: forecasts considering observations of gamma-ray bursts and kilonovae
• Unsupervised machine learning classification of gamma-ray bursts based on the rest-frame prompt emission parameters
• A Practical Framework for Estimating the Repetition Likelihood of Fast Radio Bursts from Spectral Morphology