Identifying high-Z gamma-ray burst candidates using random forest classification

Adam N. Morgan; James Long; Tamara Broderick; Joseph W. Richards; Joshua S. Bloom

doi:10.1007/978-1-4614-3520-4_61

Identifying high-Z gamma-ray burst candidates using random forest classification

Adam N. Morgan, James Long, Tamara Broderick, Joseph W. Richards, Joshua S. Bloom

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

The growing number of observed Gamma-ray Bursts (GRBs) necessitates a more efficient use of follow-up resources in order to maximize the expected scientific returns. Studying the most distant (highest redshift) events, for instance, remain a primary goal for many in the field. Toward this goal of optimal resource allocation, we have created the Random Forests Automated Triage Estimator for GRB redshifts (RATE GRB-z) to identify high-redshift (z > 4) candidates using rapidly available metrics from the Swift satellite. Using a training set of 136 GRBs, 17 of which are high-z, our cross-validated performance metrics suggest that following up on just 20% of the GRBs will yield roughly 55% of all high-redshift events.

Original language	English (US)
Title of host publication	Statistical Challenges in Modern Astronomy V
Publisher	Springer Science and Business Media, LLC
Pages	533-534
Number of pages	2
ISBN (Print)	9781461435198
DOIs	https://doi.org/10.1007/978-1-4614-3520-4_61
State	Published - 2012
Externally published	Yes
Event	5th Statistical Challenges in Modern Astronomy Symposium, SCMA 2011 - University Park, PA, United States Duration: Jun 13 2011 → Jun 15 2011

Publication series

Name	Lecture Notes in Statistics
Volume	209
ISSN (Print)	0930-0325
ISSN (Electronic)	2197-7186

Other

Other	5th Statistical Challenges in Modern Astronomy Symposium, SCMA 2011
Country/Territory	United States
City	University Park, PA
Period	6/13/11 → 6/15/11

ASJC Scopus subject areas

Statistics and Probability
Statistics, Probability and Uncertainty

Access to Document

10.1007/978-1-4614-3520-4_61

Cite this

Identifying high-Z gamma-ray burst candidates using random forest classification. / Morgan, Adam N.; Long, James; Broderick, Tamara et al.
Statistical Challenges in Modern Astronomy V. Springer Science and Business Media, LLC, 2012. p. 533-534 (Lecture Notes in Statistics; Vol. 209).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Morgan, AN, Long, J, Broderick, T, Richards, JW & Bloom, JS 2012, Identifying high-Z gamma-ray burst candidates using random forest classification. in Statistical Challenges in Modern Astronomy V. Lecture Notes in Statistics, vol. 209, Springer Science and Business Media, LLC, pp. 533-534, 5th Statistical Challenges in Modern Astronomy Symposium, SCMA 2011, University Park, PA, United States, 6/13/11. https://doi.org/10.1007/978-1-4614-3520-4_61

@inproceedings{c639c31fa653453ea667799865360e13,

title = "Identifying high-Z gamma-ray burst candidates using random forest classification",

abstract = "The growing number of observed Gamma-ray Bursts (GRBs) necessitates a more efficient use of follow-up resources in order to maximize the expected scientific returns. Studying the most distant (highest redshift) events, for instance, remain a primary goal for many in the field. Toward this goal of optimal resource allocation, we have created the Random Forests Automated Triage Estimator for GRB redshifts (RATE GRB-z) to identify high-redshift (z > 4) candidates using rapidly available metrics from the Swift satellite. Using a training set of 136 GRBs, 17 of which are high-z, our cross-validated performance metrics suggest that following up on just 20% of the GRBs will yield roughly 55% of all high-redshift events.",

author = "Morgan, {Adam N.} and James Long and Tamara Broderick and Richards, {Joseph W.} and Bloom, {Joshua S.}",

year = "2012",

doi = "10.1007/978-1-4614-3520-4_61",

language = "English (US)",

isbn = "9781461435198",

series = "Lecture Notes in Statistics",

publisher = "Springer Science and Business Media, LLC",

pages = "533--534",

booktitle = "Statistical Challenges in Modern Astronomy V",

}

TY - GEN

T1 - Identifying high-Z gamma-ray burst candidates using random forest classification

AU - Morgan, Adam N.

AU - Long, James

AU - Broderick, Tamara

AU - Richards, Joseph W.

AU - Bloom, Joshua S.

PY - 2012

Y1 - 2012

N2 - The growing number of observed Gamma-ray Bursts (GRBs) necessitates a more efficient use of follow-up resources in order to maximize the expected scientific returns. Studying the most distant (highest redshift) events, for instance, remain a primary goal for many in the field. Toward this goal of optimal resource allocation, we have created the Random Forests Automated Triage Estimator for GRB redshifts (RATE GRB-z) to identify high-redshift (z > 4) candidates using rapidly available metrics from the Swift satellite. Using a training set of 136 GRBs, 17 of which are high-z, our cross-validated performance metrics suggest that following up on just 20% of the GRBs will yield roughly 55% of all high-redshift events.

AB - The growing number of observed Gamma-ray Bursts (GRBs) necessitates a more efficient use of follow-up resources in order to maximize the expected scientific returns. Studying the most distant (highest redshift) events, for instance, remain a primary goal for many in the field. Toward this goal of optimal resource allocation, we have created the Random Forests Automated Triage Estimator for GRB redshifts (RATE GRB-z) to identify high-redshift (z > 4) candidates using rapidly available metrics from the Swift satellite. Using a training set of 136 GRBs, 17 of which are high-z, our cross-validated performance metrics suggest that following up on just 20% of the GRBs will yield roughly 55% of all high-redshift events.

UR - http://www.scopus.com/inward/record.url?scp=84896595573&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84896595573&partnerID=8YFLogxK

U2 - 10.1007/978-1-4614-3520-4_61

DO - 10.1007/978-1-4614-3520-4_61

M3 - Conference contribution

AN - SCOPUS:84896595573

SN - 9781461435198

T3 - Lecture Notes in Statistics

SP - 533

EP - 534

BT - Statistical Challenges in Modern Astronomy V

PB - Springer Science and Business Media, LLC

T2 - 5th Statistical Challenges in Modern Astronomy Symposium, SCMA 2011

Y2 - 13 June 2011 through 15 June 2011

ER -

Identifying high-Z gamma-ray burst candidates using random forest classification

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this