Optimizing a magnitude-limited spectroscopic training sample for photometric classification of supernovae

In preparation for photometric classification of transients from the Legacy Survey of Space and Time (LSST) we run tests with different training data sets. Using estimates of the depth to which the 4-m Multi-Object Spectroscopic Telescope (4MOST) Time Domain Extragalactic Survey (TiDES) can classify transients, we simulate a magnitude-limited sample reaching rAB ≈ 22.5 mag. We run our simulations with the software SNMACHINE, a photometric classification pipeline using machine learning. The machine-learning algorithms struggle to classify supernovae when the training sample is magnitude limited, in contrast to representative training samples. Classification performance noticeably improves when we combine the magnitude-limited training sample with a simulated realistic sample of faint high-redshift supernovae observed from larger spectroscopic facilities; the algorithms’ range of average area under receiver operator characteristic curve (AUC) scores over 10 runs increases from 0.547–0.628 to 0.946–0.969 and purity of the classified sample reaches 95 per cent in all runs for two of the four algorithms. By creating new, artificial light curves using the augmentation software AVOCADO, we achieve a purity in our classified sample of 95 per cent in all 10 runs performed for all machine-learning algorithms considered. We also reach a highest average AUC score of 0.986 with the artificial neural network algorithm. Having ‘true’ faint supernovae to complement our magnitude-limited sample is a crucial requirement in optimization of a 4MOST spectroscopic sample. However, our results are a proof of concept that augmentation is also necessary to achieve the best classification results.

Cosmology: observations, Methods: data analysis, Supernovae: general

10.1093/mnras/stab2343

1365-2966

1-18

Sullivan, Mark

2f31f9fa-8e79-4b35-98e2-0cb38f503850

Carrick, Jonathan E.

63c744e6-0e8b-4176-ae87-f33a1416a1a5

Hook, Isobel M.

04fa422c-dcb3-408d-ad5b-fa5d6742cfc2

Swann, Elizabeth

e3ef4037-8343-4f74-8a25-601270d0eb91

Boone, Kyle

84ed1971-c9c2-44fc-8090-dff1b4857de3

Frohmaier, C.

0888fc8a-7dd0-4096-bd7f-bd3a2d192f19

Kim, A.G.

ff0b30a1-124d-4a70-beaf-64126ca7791e

1 November 2021

Sullivan, Mark

2f31f9fa-8e79-4b35-98e2-0cb38f503850

Carrick, Jonathan E.

63c744e6-0e8b-4176-ae87-f33a1416a1a5

Hook, Isobel M.

04fa422c-dcb3-408d-ad5b-fa5d6742cfc2

Swann, Elizabeth

e3ef4037-8343-4f74-8a25-601270d0eb91

Boone, Kyle

84ed1971-c9c2-44fc-8090-dff1b4857de3

Frohmaier, C.

0888fc8a-7dd0-4096-bd7f-bd3a2d192f19

Kim, A.G.

ff0b30a1-124d-4a70-beaf-64126ca7791e

Sullivan, Mark, Carrick, Jonathan E., Hook, Isobel M., Swann, Elizabeth, Boone, Kyle, Frohmaier, C. and Kim, A.G. (2021) Optimizing a magnitude-limited spectroscopic training sample for photometric classification of supernovae. Monthly Notices of the Royal Astronomical Society, 508 (1), 1-18. (doi:10.1093/mnras/stab2343).

Record type: Article

Abstract

Text

2012.12122 - Accepted Manuscript

Available under License University of Southampton Accepted Manuscript Licence.

Download (1MB)

More information

Accepted/In Press date: 10 August 2021

Published date: 1 November 2021

Additional Information: Funding Information: JEC acknowledges support from a Science and Technology Facilities Council (STFC) Data Science studentship and funding of training through the STFC 4IR Centre for Doctoral Training. IMH acknowledges support for this work from STFC (consolidated grant numbers ST/R000514/1 and ST/P00038X/1). AGK is supported by the U.S. Department of Energy, Office of Science, Office of High Energy Physics, under contract No. DE-AC02-05CH11231. We thank Emille E. O. Ishida for useful discussions and for her very helpful comments in preparing this paper. We also thank the reviewer at MNRAS for providing helpful and detailed comments that have significantly improved this paper. We thank Lancaster University?s High End Computing Cluster service for providing access to conduct our high performance computing needs in this work. This work would not have been possible without the software SNMACHINE, and so we also thank the developers Michelle Lochner, Jason D. McEwen, and Hiranya Peiris. The DESC acknowledges ongoing support from the Institut National de Physique Nucl?aire et de Physique des Particules in France; the Science & Technology Facilities Council in the United Kingdom; and the Department of Energy, the National Science Foundation, and the LSST Corporation in the United States. DESC uses resources of the IN2P3 Computing Center (CC-IN2P3?Lyon/Villeurbanne - France) funded by the Centre National de la Recherche Scientifique; the National Energy Research Scientific Computing Center, a DOE Office of Science User Facility supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC02-05CH11231; STFC DiRAC HPC Facilities, funded by UK BIS National E-infrastructure capital grants; and the UK particle physics grid, supported by the GridPP Collaboration. This work was performed in part under DOE Contract DE-AC02-76SF00515. This work has made use of the development effort for 4MOST, an instrument under construction by the 4MOST Consortium (https://www.4most.eu/cms/consortium/) for the European Southern Observatory (ESO). Publisher Copyright: © 2021 The Author(s).

Keywords: Cosmology: observations, Methods: data analysis, Supernovae: general

Learn more about School of Physics and Astronomy research