CaltechAUTHORS
  A Caltech Library Service

Towards real-time classification of astronomical transients

Mahabal, A. and Djorgovski, S. G. and Williams, R. and Drake, A. and Donalek, C. and Graham, M. and Moghaddam, B. and Turmon, M. and Jewell, J. and Khosla, A. and Hensleya, B. (2008) Towards real-time classification of astronomical transients. In: International Conference on Classification and Discovery in Large Astronomical Surveys, Ringberg Castle, Germany, 14–17 October 2008. American Institute of Physics Conference Proceedings. No.1082. American Institute of Physics , Melville, NY, pp. 287-293. ISBN 9780735406131. http://resolver.caltech.edu/CaltechAUTHORS:MAHaipcp08

[img]
Preview
PDF - Published Version
See Usage Policy.

1071Kb

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:MAHaipcp08

Abstract

Exploration of time domain is now a vibrant area of research in astronomy, driven by the advent of digital synoptic sky surveys. While panoramic surveys can detect variable or transient events, typically some follow-up observations are needed; for short-lived phenomena, a rapid response is essential. Ability to automatically classify and prioritize transient events for follow-up studies becomes critical as the data rates increase. We have been developing such methods using the data streams from the Palomar-Quest survey, the Catalina Sky Survey and others, using the VOEventNet framework. The goal is to automatically classify transient events, using the new measurements, combined with archival data (previous and multi-wavelength measurements), and contextual information (e.g., Galactic or ecliptic latitude, presence of a possible host galaxy nearby, etc.); and to iterate them dynamically as the follow-up data come in (e.g., light curves or colors). We have been investigating Bayesian methodologies for classification, as well as discriminated follow-up to optimize the use of available resources, including Naive Bayesian approach, and the non-parametric Gaussian process regression. We will also be deploying variants of the traditional machine learning techniques such as Neural Nets and Support Vector Machines on datasets of reliably classified transients as they build up.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
http://link.aip.org/link/?APCPCS/1082/287/1PublisherArticle
http://dx.doi.org/10.1063/1.3059064DOIArticle
Additional Information:© 2008 American Institute of Physics. Issue Date: 5 December 2008. We are grateful to the staff of Palomar Observatory for their help, and to our collaborators in PQ and CSS survey teams. This work was supported in part by the NSF grants AST-0407448, AST-0326524, and CNS-0540369, and by the Ajax Foundation. A.K. and B.H. were supported in part by the Caltech SURF program.
Funders:
Funding AgencyGrant Number
NSFAST-0407448
NSFAST-0326524
NSFCNS-0540369
Ajax FoundationUNSPECIFIED
Caltech Summer Undergraduate Research Fellowship (SURF)UNSPECIFIED
Subject Keywords:astronomical image processing; astronomical surveys; astronomical techniques; Bayes methods; image classification; learning (artificial intelligence); neural nets; real-time systems; support vector machines
Record Number:CaltechAUTHORS:MAHaipcp08
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:MAHaipcp08
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:13283
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:10 Feb 2009 18:23
Last Modified:14 Jan 2015 06:48

Repository Staff Only: item control page