Home > Research > Publications & Outputs > Optimising a magnitude-limited spectroscopic tr...

Associated organisational unit

Electronic data

  • 2012.12122

    Accepted author manuscript, 1.54 MB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

Links

Text available via DOI:

View graph of relations

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

Research output: Contribution to journalJournal articlepeer-review

Published

Standard

Optimising a magnitude-limited spectroscopic training sample for photometric classification of supernovae. / The LSST Dark Energy Science Collaboration.

In: Monthly Notices of the Royal Astronomical Society, Vol. 508, No. 1, 30.11.2021, p. 1-18.

Research output: Contribution to journalJournal articlepeer-review

Harvard

The LSST Dark Energy Science Collaboration 2021, 'Optimising a magnitude-limited spectroscopic training sample for photometric classification of supernovae', Monthly Notices of the Royal Astronomical Society, vol. 508, no. 1, pp. 1-18. https://doi.org/10.1093/mnras/stab2343

APA

The LSST Dark Energy Science Collaboration (2021). Optimising a magnitude-limited spectroscopic training sample for photometric classification of supernovae. Monthly Notices of the Royal Astronomical Society, 508(1), 1-18. https://doi.org/10.1093/mnras/stab2343

Vancouver

The LSST Dark Energy Science Collaboration. Optimising a magnitude-limited spectroscopic training sample for photometric classification of supernovae. Monthly Notices of the Royal Astronomical Society. 2021 Nov 30;508(1):1-18. https://doi.org/10.1093/mnras/stab2343

Author

The LSST Dark Energy Science Collaboration. / Optimising a magnitude-limited spectroscopic training sample for photometric classification of supernovae. In: Monthly Notices of the Royal Astronomical Society. 2021 ; Vol. 508, No. 1. pp. 1-18.

Bibtex

@article{9e531a5d19844ca395625a73160f189f,
title = "Optimising a magnitude-limited spectroscopic training sample for photometric classification of supernovae",
abstract = "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-metre Multi-Object Spectroscopic Telescope (4MOST) Time Domain Extragalactic Survey (TiDES) can classify transients, we simulate a magnitude-limited sample reaching $r_{\textrm{AB}} \approx$ 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 ROC 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 2 of the 4 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 optimisation of a 4MOST spectroscopic sample. However, our results are a proof of concept that augmentation is also necessary to achieve the best classification results. ",
author = "{The LSST Dark Energy Science Collaboration} and Jon Carrick and Isobel Hook and Elizabeth Swann and Kyle Boone and Chris Frohmaier and Alex Kim and Mark Sullivan",
year = "2021",
month = nov,
day = "30",
doi = "10.1093/mnras/stab2343",
language = "English",
volume = "508",
pages = "1--18",
journal = "Monthly Notices of the Royal Astronomical Society",
issn = "0035-8711",
publisher = "OXFORD UNIV PRESS",
number = "1",

}

RIS

TY - JOUR

T1 - Optimising a magnitude-limited spectroscopic training sample for photometric classification of supernovae

AU - The LSST Dark Energy Science Collaboration

AU - Carrick, Jon

AU - Hook, Isobel

AU - Swann, Elizabeth

AU - Boone, Kyle

AU - Frohmaier, Chris

AU - Kim, Alex

AU - Sullivan, Mark

PY - 2021/11/30

Y1 - 2021/11/30

N2 - 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-metre Multi-Object Spectroscopic Telescope (4MOST) Time Domain Extragalactic Survey (TiDES) can classify transients, we simulate a magnitude-limited sample reaching $r_{\textrm{AB}} \approx$ 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 ROC 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 2 of the 4 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 optimisation of a 4MOST spectroscopic sample. However, our results are a proof of concept that augmentation is also necessary to achieve the best classification results.

AB - 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-metre Multi-Object Spectroscopic Telescope (4MOST) Time Domain Extragalactic Survey (TiDES) can classify transients, we simulate a magnitude-limited sample reaching $r_{\textrm{AB}} \approx$ 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 ROC 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 2 of the 4 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 optimisation of a 4MOST spectroscopic sample. However, our results are a proof of concept that augmentation is also necessary to achieve the best classification results.

U2 - 10.1093/mnras/stab2343

DO - 10.1093/mnras/stab2343

M3 - Journal article

VL - 508

SP - 1

EP - 18

JO - Monthly Notices of the Royal Astronomical Society

JF - Monthly Notices of the Royal Astronomical Society

SN - 0035-8711

IS - 1

ER -