Machine-z: Rapid Machine Learned Redshift Indicator for Swift Gamma-ray Bursts
arXiv:1512.07671 · doi:10.1093/mnras/stw559
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.
arXiv commentAccepted to the Monthly Notices of the Royal Astronomical Society Journal (10 pages, 10 figures, and 3 Tables)
References in corpus (25)
- Scikit-learn: Machine Learning in Python
- A glimpse of the end of the dark ages: the gamma-ray burst of 23 April 2009 at redshift 8.3
- GRB 090423 at a redshift of z~8.1
- A Photometric Redshift of z ~ 9.4 for GRB 090429B
- Gamma-Ray Bursts as a Probe of the Very High Redshift Universe
- Gamma-Ray Bursts as a Probe of the Very High Redshift Universe
- Implications for the Cosmic Reionization from the Optical Afterglow Spectrum of the Gamma-Ray Burst 050904 at z = 6.3
- Cosmic Dispersion Measure from Gamma-Ray Burst Afterglows: Probing the Reionization History and the Burst Environment
- Automated Transient Identification in the Dark Energy Survey
- Probing Pre-galactic Metal Enrichment with High-Redshift Gamma-Ray Bursts
- Machine learning for transient discovery in Pan-STARRS1 difference imaging
- Detection of a huge explosion in the early Universe
- An Energetic Afterglow From A Distant Stellar Explosion
- Machine Learning Classification of SDSS Transient Survey Images
- An analysis of feature relevance in the classification of astronomical transients with machine learning methods
- The First Gamma-Ray Bursts in the Universe
- Investigation of Redshift- and Duration-Dependent Clustering of Gamma-ray Bursts
- On the detection of very high redshift Gamma Ray Bursts with Swift
- Rapid, Machine-Learned Resource Allocation: Application to High-redshift GRB Follow-up
- 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
- The highest redshift gamma-ray bursts
- 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