Towards an Automated Classification of Transient Events in Synoptic Sky Surveys
Abstract
We describe the development of a system for an automated, iterative, real-time classification of transient events discovered in synoptic sky surveys. The system under development incorporates a number of Machine Learning techniques, mostly using Bayesian approaches, due to the sparse nature, heterogeneity, and variable incompleteness of the available data. The classifications are improved iteratively as the new measurements are obtained. One novel feature is the development of an automated follow-up recommendation engine, that suggest those measurements that would be the most advantageous in terms of resolving classification ambiguities and/or characterization of the astrophysically most interesting objects, given a set of available follow-up assets and their cost functions. This illustrates the symbiotic relationship of astronomy and applied computer science through the emerging discipline of AstroInformatics.
Keywords
Cite
@article{arxiv.1110.4655,
title = {Towards an Automated Classification of Transient Events in Synoptic Sky Surveys},
author = {S. G. Djorgovski and C. Donalek and A. Mahabal and B. Moghaddam and M. Turmon and M. Graham and A. Drake and N. Sharma and Y. Chen},
journal= {arXiv preprint arXiv:1110.4655},
year = {2011}
}
Comments
Invited paper, 15 pages, to appear in Statistical Analysis and Data Mining (ASA journal), ref. proc. CIDU 2011 conf., eds. A. Srivasatva & N. Chawla, in press (2011)