A Caltech Library Service

Automated Real-Time Classification and Decision Making in Massive Data Streams from Synoptic Sky Surveys

Djorgovski, S. G. and Mahabal, A. A. and Donalek, C. and Graham, M. J. and Drake, A. J. and Turmon, M. and Fuchs, T. (2014) Automated Real-Time Classification and Decision Making in Massive Data Streams from Synoptic Sky Surveys. In: 2014 IEEE 10th International Conference on e-Science. IEEE , Piscataway, NJ, pp. 204-211. ISBN 978-1-4799-4288-6.

PDF - Submitted Version
See Usage Policy.


Use this Persistent URL to link to this item:


The nature of scientific and technological data collection is evolving rapidly: data volumes and rates grow exponentially, with increasing complexity and information content, and there has been a transition from static data sets to data streams that must be analyzed in real time. Interesting or anomalous phenomena must be quickly characterized and followed up with additional measurements via optimal deployment of limited assets. Modern astronomy presents a variety of such phenomena in the form of transient events in digital synoptic sky surveys, including cosmic explosions (supernovae, gamma ray bursts), relativistic phenomena (black hole formation, jets), potentially hazardous asteroids, etc. We have been developing a set of machine learning tools to detect, classify and plan a response to transient events for astronomy applications, using the Catalina Real-time Transient Survey (CRTS) as a scientific and methodological testbed. The ability to respond rapidly to the potentially most interesting events is a key bottleneck that limits the scientific returns from the current and anticipated synoptic sky surveys. Similar challenge arise in other contexts, from environmental monitoring using sensor networks to autonomous spacecraft systems. Given the exponential growth of data rates, and the time-critical response, we need a fully automated and robust approach. We describe the results obtained to date, and the possible future developments.

Item Type:Book Section
Related URLs:
URLURL TypeDescription Paper
Djorgovski, S. G.0000-0002-0603-3087
Mahabal, A. A.0000-0003-2242-0244
Graham, M. J.0000-0002-3168-0139
Turmon, M.0000-0002-6463-063X
Additional Information:© 2014 IEEE. This work was supported in part by the NASA grant 08-AISR08-0085, the NSF grants AST-0909182, IIS-1118041, and AST-1313422, by the W. M. Keck Institute for Space Studies at Caltech (KISS), and by the U.S. Virtual Astronomical Observatory, itself supported by the NSF grant AST-0834235. Some of this work was assisted by the Caltech students Nihar Sharma, Yutong Chen, Alex Ball, Victor Duan, Allison Maker, and others, supported by the Caltech SURF program. We thank numerous collaborators and colleagues, especially within the CRTS survey team, and the world-wide Virtual Observatory and astroinformatics community, for stimulating discussions.
Group:Keck Institute for Space Studies
Funding AgencyGrant Number
Keck Institute for Space Studies (KISS)UNSPECIFIED
U.S. Virtual Astronomical ObservatoryUNSPECIFIED
Subject Keywords:sky surveys; massive data streams; machine learning; Bayesian methods; automated decision making
Record Number:CaltechAUTHORS:20141217-103710003
Persistent URL:
Official Citation:S. G. Djorgovski et al., "Automated Real-Time Classification and Decision Making in Massive Data Streams from Synoptic Sky Surveys," 2014 IEEE 10th International Conference on e-Science, Sao Paulo, 2014, pp. 204-211. doi: 10.1109/eScience.2014.7
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:52955
Deposited By: Tony Diaz
Deposited On:17 Dec 2014 19:34
Last Modified:10 Nov 2021 19:46

Repository Staff Only: item control page