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 »
- Authors:
-
- Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
- 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}
}
Web of Science
Works referenced in this record:
Near real-time selection of high redshift GRBs with Swift
journal, January 2007
- Campana, S.; Tagliaferri, G.; Malesani, D.
- Astronomy & Astrophysics, Vol. 464, Issue 3
Random Forests for Photometric Redshifts
journal, March 2010
- Carliles, Samuel; Budavári, Tamás; Heinis, Sébastien
- The Astrophysical Journal, Vol. 712, Issue 1
A PHOTOMETRIC REDSHIFT OF z ∼ 9.4 FOR GRB 090429B
journal, June 2011
- Cucchiara, A.; Levan, A. J.; Fox, D. B.
- The Astrophysical Journal, Vol. 736, Issue 1
Huge explosion in the early Universe
journal, February 2006
- Cusumano, G.; Mangano, V.; Chincarini, G.
- Nature, Vol. 440, Issue 7081
An analysis of feature relevance in the classification of astronomical transients with machine learning methods
journal, February 2016
- D'Isanto, A.; Cavuoti, S.; Brescia, M.
- Monthly Notices of the Royal Astronomical Society, Vol. 457, Issue 3
Machine learning classification of SDSS transient survey images
journal, October 2015
- du Buisson, L.; Sivanandam, N.; Bassett, Bruce A.
- Monthly Notices of the Royal Astronomical Society, Vol. 454, Issue 2
Autoclassification of the Variable 3xmm Sources Using the Random Forest Machine Learning Algorithm
journal, October 2015
- Farrell, Sean A.; Murphy, Tara; Lo, Kitty K.
- The Astrophysical Journal, Vol. 813, Issue 1
An Energetic Afterglow from a Distant Stellar Explosion
journal, July 2006
- Frail, D. A.; Cameron, P. B.; Kasliwal, M.
- The Astrophysical Journal, Vol. 646, Issue 2
The Swift Gamma‐Ray Burst Mission
journal, August 2004
- Gehrels, N.; Chincarini, G.; Giommi, P.
- The Astrophysical Journal, Vol. 611, Issue 2
Automated Transient Identification in the dark Energy Survey
journal, August 2015
- Goldstein, D. A.; D’Andrea, C. B.; Fischer, J. A.
- The Astronomical Journal, Vol. 150, Issue 3
The Cosmic Dispersion Measure from Gamma-Ray Burst Afterglows: Probing the Reionization History and the Burst Environment
journal, November 2003
- Ioka, Kunihito
- The Astrophysical Journal, Vol. 598, Issue 2
An optical spectrum of the afterglow of a γ-ray burst at a redshift of z = 6.295
journal, March 2006
- Kawai, N.; Kosugi, G.; Aoki, K.
- Nature, Vol. 440, Issue 7081
Multiple regression of GRB luminosity on light-curve properties
journal, July 2009
- Koen, Chris
- Monthly Notices of the Royal Astronomical Society, Vol. 396, Issue 3
Predicting gamma-ray burster redshifts from their prompt emission properties
journal, January 2010
- Koen, Chris
- Monthly Notices of the Royal Astronomical Society, Vol. 401, Issue 2
Gamma‐Ray Bursts as a Probe of the Very High Redshift Universe
journal, June 2000
- Lamb, Donald Q.; Reichart, Daniel E.
- The Astrophysical Journal, Vol. 536, Issue 1
The First Gamma-Ray Bursts in the Universe
journal, May 2014
- Mesler, R. A.; Whalen, Daniel J.; Smidt, Joseph
- The Astrophysical Journal, Vol. 787, Issue 1
Rapid, Machine-Learned Resource Allocation: Application to High-Redshift Gamma-Ray Burst Follow-Up
journal, February 2012
- Morgan, A. N.; Long, James; Richards, Joseph W.
- The Astrophysical Journal, Vol. 746, Issue 2
On the detection of very high redshift gamma-ray bursts with Swift
journal, September 2007
- Salvaterra, R.; Campana, S.; Chincarini, G.
- Monthly Notices of the Royal Astronomical Society: Letters, Vol. 380, Issue 1
GRB 090423 at a redshift of z ≈ 8.1
journal, October 2009
- Salvaterra, R.; Valle, M. Della; Campana, S.
- Nature, Vol. 461, Issue 7268
A γ-ray burst at a redshift of z ≈ 8.2
journal, October 2009
- Tanvir, N. R.; Fox, D. B.; Levan, A. J.
- Nature, Vol. 461, Issue 7268
Implications for Cosmic Reionization from the Optical Afterglow Spectrum of the Gamma-Ray Burst 050904 at z = 6.3
journal, June 2006
- Totani, Tomonori; Kawai, Nobuyuki; Kosugi, George
- Publications of the Astronomical Society of Japan, Vol. 58, Issue 3
Investigation of redshift- and duration-dependent clustering of gamma-ray bursts
journal, November 2015
- Ukwatta, T. N.; Woźniak, P. R.
- Monthly Notices of the Royal Astronomical Society, Vol. 455, Issue 1
Investigating the Possibility of Screening High-z GRBs based on BAT Prompt Emission Properties
conference, January 2009
- Ukwatta, T. N.; Sakamoto, T.; Dhuga, K. S.
- GAMMA-RAY BURST: Sixth Huntsville Symposium, AIP Conference Proceedings
Probing Pre-Galactic Metal Enrichment with High-Redshift Gamma-Ray Bursts
journal, October 2012
- Wang, F. Y.; Bromm, Volker; Greif, Thomas H.
- The Astrophysical Journal, Vol. 760, Issue 1
Machine learning for transient discovery in Pan-STARRS1 difference imaging
journal, March 2015
- Wright, D. E.; Smartt, S. J.; Smith, K. W.
- Monthly Notices of the Royal Astronomical Society, Vol. 449, Issue 1
The Cosmic Dispersion Measure from Gamma-Ray Burst Afterglows: Probing the Reionization History and the Burst Environment
journal, November 2003
- Ioka, Kunihito
- The Astrophysical Journal, Vol. 598, Issue 2
The SVOM gamma-ray burst mission
conference, August 2015
- Cordier, Bertrand; Wei, J.; Atteia, Jean-Luc
- Proceedings of Swift: 10 Years of Discovery — PoS(SWIFT 10)
Scikit-learn: Machine Learning in Python
text, January 2012
- Pedregosa, Fabian; Varoquaux, Gaël; Gramfort, Alexandre
- arXiv
Works referencing / citing this record:
Methods for identifying high‐redshift galaxy cluster candidates
journal, August 2019
- Pinter, Sandor; Balázs, Lajos G.; Bagoly, Zsolt
- Astronomische Nachrichten, Vol. 340, Issue 7
A Machine Learning Based Morphological Classification of 14,245 Radio AGNs Selected from the Best–Heckman Sample
journal, February 2019
- Ma, Zhixian; Xu, Haiguang; Zhu, Jie
- The Astrophysical Journal Supplement Series, Vol. 240, Issue 2
A Machine Learning Based Morphological Classification of 14,245 Radio AGNs Selected From The Best-Heckman Sample
text, January 2018
- Ma, Zhixian; Xu, Haiguang; Zhu, Jie
- arXiv