skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: 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 per cent recall of true high-redshift bursts, while incurring a false positive rate of 20 per cent. With 40 per cent false positive rate the classifier can achieve ~100 per cent recall. As amore » result, the most reliable selection of high-redshift GRBs is obtained by combining predictions from both the high-z classifier and the machine-z regressor.« less

Authors:
 [1];  [1];  [2]
  1. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
  2. NASA/Goddard Space Flight Center, Greenbelt, MD (United States)
Publication Date:
Research Org.:
Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1246890
Report Number(s):
LA-UR-15-29685
Journal ID: ISSN 0035-8711
Grant/Contract Number:  
AC52-06NA25396
Resource Type:
Journal Article: Accepted Manuscript
Journal Name:
Monthly Notices of the Royal Astronomical Society
Additional Journal Information:
Journal Volume: 458; Journal Issue: 4; Journal ID: ISSN 0035-8711
Publisher:
Royal Astronomical Society
Country of Publication:
United States
Language:
English
Subject:
79 ASTRONOMY AND ASTROPHYSICS; Astronomy and Astrophysics; GRB, Machine Learning

Citation Formats

Ukwatta, T. N., Wozniak, P. R., and Gehrels, N. Machine-z: Rapid machine-learned redshift indicator for Swift gamma-ray bursts. United States: N. p., 2016. Web. doi:10.1093/mnras/stw559.
Ukwatta, T. N., Wozniak, P. R., & Gehrels, N. Machine-z: Rapid machine-learned redshift indicator for Swift gamma-ray bursts. United States. https://doi.org/10.1093/mnras/stw559
Ukwatta, T. N., Wozniak, P. R., and Gehrels, N. 2016. "Machine-z: Rapid machine-learned redshift indicator for Swift gamma-ray bursts". United States. https://doi.org/10.1093/mnras/stw559. https://www.osti.gov/servlets/purl/1246890.
@article{osti_1246890,
title = {Machine-z: Rapid machine-learned redshift indicator for Swift gamma-ray bursts},
author = {Ukwatta, T. N. and Wozniak, P. R. and Gehrels, N.},
abstractNote = {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 per cent recall of true high-redshift bursts, while incurring a false positive rate of 20 per cent. With 40 per cent false positive rate the classifier can achieve ~100 per cent recall. As a result, the most reliable selection of high-redshift GRBs is obtained by combining predictions from both the high-z classifier and the machine-z regressor.},
doi = {10.1093/mnras/stw559},
url = {https://www.osti.gov/biblio/1246890}, journal = {Monthly Notices of the Royal Astronomical Society},
issn = {0035-8711},
number = 4,
volume = 458,
place = {United States},
year = {Tue Mar 08 00:00:00 EST 2016},
month = {Tue Mar 08 00:00:00 EST 2016}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 7 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Random Forests
journal, January 2001


Near real-time selection of high redshift GRBs with Swift
journal, January 2007


Random Forests for Photometric Redshifts
journal, March 2010


A PHOTOMETRIC REDSHIFT OF z ∼ 9.4 FOR GRB 090429B
journal, June 2011


Huge explosion in the early Universe
journal, February 2006


An analysis of feature relevance in the classification of astronomical transients with machine learning methods
journal, February 2016


Machine learning classification of SDSS transient survey images
journal, October 2015


Autoclassification of the Variable 3xmm Sources Using the Random Forest Machine Learning Algorithm
journal, October 2015


An Energetic Afterglow from a Distant Stellar Explosion
journal, July 2006


The Swift Gamma‐Ray Burst Mission
journal, August 2004


Automated Transient Identification in the dark Energy Survey
journal, August 2015


An optical spectrum of the afterglow of a γ-ray burst at a redshift of z = 6.295
journal, March 2006


Multiple regression of GRB luminosity on light-curve properties
journal, July 2009


Predicting gamma-ray burster redshifts from their prompt emission properties
journal, January 2010


Gamma‐Ray Bursts as a Probe of the Very High Redshift Universe
journal, June 2000


The First Gamma-Ray Bursts in the Universe
journal, May 2014


Rapid, Machine-Learned Resource Allocation: Application to High-Redshift Gamma-Ray Burst Follow-Up
journal, February 2012


On the detection of very high redshift gamma-ray bursts with Swift
journal, September 2007


GRB 090423 at a redshift of z ≈ 8.1
journal, October 2009


A γ-ray burst at a redshift of z ≈ 8.2
journal, October 2009


Implications for Cosmic Reionization from the Optical Afterglow Spectrum of the Gamma-Ray Burst 050904 at z = 6.3
journal, June 2006


Investigation of redshift- and duration-dependent clustering of gamma-ray bursts
journal, November 2015


Investigating the Possibility of Screening High-z GRBs based on BAT Prompt Emission Properties
conference, January 2009


Probing Pre-Galactic Metal Enrichment with High-Redshift Gamma-Ray Bursts
journal, October 2012


Machine learning for transient discovery in Pan-STARRS1 difference imaging
journal, March 2015


The SVOM gamma-ray burst mission
conference, August 2015


Scikit-learn: Machine Learning in Python
text, January 2012


Works referencing / citing this record:

Methods for identifying high‐redshift galaxy cluster candidates
journal, August 2019


A Machine Learning Based Morphological Classification of 14,245 Radio AGNs Selected from the Best–Heckman Sample
journal, February 2019