Donalek, C. and Mahabal, A. and Djorgovski, S. G. and Marney, S. and Drake, A. and Glikman, E. and Graham, M. J. and Williams, R. (2008) New approaches to object classification in synoptic sky surveys. In: Classification and discovery in large astronomical surveys : proceedings of the International Conference "Classification and Discovery in Large Astronomical Surveys", Ringberg Castle, Germany, 14–17 October 2008. AIP conference proceedings (1082). American Institute of Physics , Melville, NY, pp. 252-256. ISBN 9780735406131 http://resolver.caltech.edu/CaltechAUTHORS:DONaipcp08
- Published Version
See Usage Policy.
Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:DONaipcp08
Digital synoptic sky surveys pose several new object classification challenges. In surveys where real-time detection and classification of transient events is a science driver, there is a need for an effective elimination of instrument-related artifacts which can masquerade as transient sources in the detection pipeline, e.g., unremoved large cosmic rays, saturation trails, reflections, crosstalk artifacts, etc. We have implemented such an Artifact Filter, using a supervised neural network, for the real-time processing pipeline in the Palomar-Quest (PQ) survey. After the training phase, for each object it takes as input a set of measured morphological parameters and returns the probability of it being a real object. Despite the relatively low number of training cases for many kinds of artifacts, the overall artifact classification rate is around 90%, with no genuine transients misclassified during our real-time scans. Another question is how to assign an optimal star-galaxy classification in a multi-pass survey, where seeing and other conditions change between different epochs, potentially producing inconsistent classifications for the same object. We have implemented a star/galaxy multipass classifier that makes use of external and a priori knowledge to find the optimal classification from the individually derived ones. Both these techniques can be applied to other, similar surveys and data sets.
|Item Type:||Book Section|
|Additional Information:||© 2008 American Institute of Physics PACS: 95.80.+p This work was supported in part by the NSF grants AST-0407448, AST-0326524, CNS-0540369, and by the Ajax Foundation. S.M. was supported in part by a Caltech SURF program. We are thankful to numerous collaborators, and especially the PQ survey team.|
|Subject Keywords:||astronomical atlases; neural nets; galaxies; survey; data mining; neural network; transient; classification|
|Usage Policy:||No commercial reproduction, distribution, display or performance rights in this work are provided.|
|Deposited By:||Arun Sannuti|
|Deposited On:||06 Jul 2009 22:11|
|Last Modified:||26 Dec 2012 10:52|
Repository Staff Only: item control page