Machine-z: Rapid Machine Learned Redshift Indicator for Swift Gamma-ray Bursts

Abstract

Studies of high-redshift gamma-ray bursts (GRBs) provide important information about the early Universe such as the rates of stellar collapsars and mergers, the metallicity content, constraints on the re-ionization period, and probes of the Hubble expansion. Rapid selection of high-z candidates from GRB samples reported in real time by dedicated space missions such as Swift is the key to identifying the most distant bursts before the optical afterglow becomes too dim to warrant a good spectrum. Here we introduce "machine-z", a redshift prediction algorithm and a "high-z" classifier for Swift GRBs based on machine learning. Our method relies exclusively on canonical data commonly available within the first few hours after the GRB trigger. Using a sample of 284 bursts with measured redshifts, we trained a randomized ensemble of decision trees (random forest) to perform both regression and classification. Cross-validated performance studies show that the correlation coefficient between machine-z predictions and the true redshift is nearly 0.6. At the same time our high-z classifier can achieve 80% recall of true high-redshift bursts, while incurring a false positive rate of 20%. With 40% false positive rate the classifier can achieve ~100% recall. The most reliable selection of high-redshift GRBs is obtained by combining predictions from both the high-z classifier and the machine-z regressor.

Accepted to the Monthly Notices of the Royal Astronomical Society Journal (10 pages, 10 figures, and 3 Tables)

References in corpus (10)

• Automated Transient Identification in the Dark Energy Survey
• Machine learning for transient discovery in Pan-STARRS1 difference imaging
• An analysis of feature relevance in the classification of astronomical transients with machine learning methods
• Investigation of Redshift- and Duration-Dependent Clustering of Gamma-ray Bursts
• On the detection of very high redshift Gamma Ray Bursts with Swift
• Near real-time selection of high redshift GRBs with Swift
• The SVOM gamma-ray burst mission
• Screening High-z GRBs with BAT Prompt Emission Properties
• Investigating the Possibility of Screening High-z GRBs based on BAT Prompt Emission Properties
• Integrating Temporal and Spectral Features of Astronomical Data Using Wavelet Analysis for Source Classification

Cited by in corpus (9)

• A Machine Learning Based Morphological Classification of 14,245 Radio AGNs Selected From The Best-Heckman Sample
• Gamma-ray Bursts as Distance Indicators by a Statistical Learning Approach
• GRB Redshift Estimation using Machine Learning and the Associated Web-App
• Gaia eclipsing binary and multiple systems. Supervised classification and self-organizing maps
• Deep Neural Networks for Estimation of Gamma-Ray Burst Redshifts
• Machine learning prediction for mean motion resonance behaviour -- The planar case
• A Tight Three-parameter Correlation and Related Classification on Gamma-Ray Bursts
• Unsupervised Domain Adaptation for Constraining Star Formation Histories
• A Concept of Assessment of LIV Tests with THESEUS Using the Gamma-Ray Bursts Detected by Fermi/GBM