Mong, Y.-L., Ackley, K., Galloway, D. et al. (45 more authors) (Submitted: 2020) Machine learning for transient recognition in difference imaging with minimum sampling effort. arXiv. (Submitted)
Abstract
The amount of observational data produced by time-domain astronomy is exponentially in-creasing. Human inspection alone is not an effective way to identify genuine transients fromthe data. An automatic real-bogus classifier is needed and machine learning techniques are commonly used to achieve this goal. Building a training set with a sufficiently large number of verified transients is challenging, due to the requirement of human verification. We presentan approach for creating a training set by using all detections in the science images to be thesample of real detections and all detections in the difference images, which are generated by the process of difference imaging to detect transients, to be the samples of bogus detections. This strategy effectively minimizes the labour involved in the data labelling for supervised machine learning methods. We demonstrate the utility of the training set by using it to train several classifiers utilizing as the feature representation the normalized pixel values in 21-by-21pixel stamps centered at the detection position, observed with the Gravitational-wave Optical Transient Observer (GOTO) prototype. The real-bogus classifier trained with this strategy can provide up to 95% prediction accuracy on the real detections at a false alarm rate of 1%.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2020 The Author(s). For reuse permissions, please contact the Author(s). |
Keywords: | astro-ph.IM; astro-ph.IM |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Science (Sheffield) > Department of Physics and Astronomy (Sheffield) |
Funding Information: | Funder Grant number Science and Technology Facilities Council ST/M001350/1; ST/R000964/1 |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 03 Sep 2020 10:48 |
Last Modified: | 03 Sep 2020 10:48 |
Published Version: | https://arxiv.org/abs/2008.10178v1 |
Status: | Submitted |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:165092 |