A transient search using combined human and machine classifications
| Autor: | Chris Lintott, Richard J. Wainscoat, K. C. Chambers, Grant Miller, Will Granger, Amy Boyer, Adam McMaster, Darryl Wright, Mark C. Bouslog, Campbell Allen, Melanie Beck, Mark Willman, L. Trouille, John L. Tonry, H. Flewelling, James E. O'Donnell, Dave R. Young, Brooke Simmons, Marten Veldthuis, Lucy Fortson, K. W. Smith, Christopher Waters, Eugene A. Magnier, Stephen Smartt, Zach Wolfenbarger, Helen Spiers |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2017 |
| Předmět: |
Physics
business.industry FOS: Physical sciences Astronomy and Astrophysics Large Synoptic Survey Telescope Machine learning computer.software_genre 01 natural sciences Convolutional neural network Methods statistical Identification (information) Space and Planetary Science Software deployment 0103 physical sciences Citizen science Transient (computer programming) Noise (video) Artificial intelligence 010306 general physics business Astrophysics - Instrumentation and Methods for Astrophysics 010303 astronomy & astrophysics computer Instrumentation and Methods for Astrophysics (astro-ph.IM) |
| Zdroj: | NASA Astrophysics Data System |
| DOI: | 10.1093/mnras/stx1812 |
| Popis: | Large modern surveys require efficient review of data in order to find transient sources such as supernovae, and to distinguish such sources from artefacts and noise. Much effort has been put into the development of automatic algorithms, but surveys still rely on human review of targets. This paper presents an integrated system for the identification of supernovae in data from Pan-STARRS1, combining classifications from volunteers participating in a citizen science project with those from a convolutional neural network. The unique aspect of this work is the deployment, in combination, of both human and machine classifications for near real-time discovery in an astronomical project. We show that the combination of the two methods outperforms either one used individually. This result has important implications for the future development of transient searches, especially in the era of LSST and other large-throughput surveys. Comment: 10 pages, 9 figures, submitted to MNRAS |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|