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

TL;DR

This paper introduces 'machine-z', a machine learning algorithm that rapidly predicts the redshift of Swift gamma-ray bursts using early data, aiding in the quick identification of high-redshift candidates for cosmological studies.

Contribution

The paper presents a novel machine learning approach combining regression and classification to estimate GRB redshifts and identify high-z candidates in real time.

Findings

Correlation coefficient of 0.6 between predictions and true redshifts.

80% recall of high-z bursts with 20% false positive rate.

Near 100% recall with 40% false positive rate.

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.