Skip to main content

Research Repository

Advanced Search

Machine learning for transient discovery in Pan-STARRS1 difference imaging

Wright, D.E.; Smartt, S.J.; Smith, K.W.; Miller, P.; Kotak, R.; Rest, A.; Burgett, W.S.; Chambers, K.C.; Flewelling, H.; Hodapp, K.W.; Huber, M.; Jedicke, R.; Kaiser, N.; Metcalfe, N.; Price, P.A.; Tonry, J.L.; Wainscoat, R.J.; Waters, C.

Machine learning for transient discovery in Pan-STARRS1 difference imaging Thumbnail


D.E. Wright

S.J. Smartt

K.W. Smith

P. Miller

R. Kotak

A. Rest

W.S. Burgett

K.C. Chambers

H. Flewelling

K.W. Hodapp

M. Huber

R. Jedicke

N. Kaiser

P.A. Price

J.L. Tonry

R.J. Wainscoat

C. Waters


Efficient identification and follow-up of astronomical transients is hindered by the need for humans to manually select promising candidates from data streams that contain many false positives. These artefacts arise in the difference images that are produced by most major ground-based time-domain surveys with large format CCD cameras. This dependence on humans to reject bogus detections is unsustainable for next generation all-sky surveys and significant effort is now being invested to solve the problem computationally. In this paper, we explore a simple machine learning approach to real–bogus classification by constructing a training set from the image data of ∼32 000 real astrophysical transients and bogus detections from the Pan-STARRS1 Medium Deep Survey. We derive our feature representation from the pixel intensity values of a 20 × 20 pixel stamp around the centre of the candidates. This differs from previous work in that it works directly on the pixels rather than catalogued domain knowledge for feature design or selection. Three machine learning algorithms are trained (artificial neural networks, support vector machines and random forests) and their performances are tested on a held-out subset of 25 per cent of the training data. We find the best results from the random forest classifier and demonstrate that by accepting a false positive rate of 1 per cent, the classifier initially suggests a missed detection rate of around 10 per cent. However, we also find that a combination of bright star variability, nuclear transients and uncertainty in human labelling means that our best estimate of the missed detection rate is approximately 6 per cent.


Wright, D., Smartt, S., Smith, K., Miller, P., Kotak, R., Rest, A., …Waters, C. (2015). Machine learning for transient discovery in Pan-STARRS1 difference imaging. Monthly Notices of the Royal Astronomical Society, 449(1), 451-466.

Journal Article Type Article
Acceptance Date Feb 9, 2015
Publication Date May 1, 2015
Deposit Date Aug 3, 2015
Publicly Available Date Sep 4, 2015
Journal Monthly Notices of the Royal Astronomical Society
Print ISSN 0035-8711
Electronic ISSN 1365-2966
Publisher Royal Astronomical Society
Peer Reviewed Peer Reviewed
Volume 449
Issue 1
Pages 451-466
Keywords Methods: data analysis, Methods: statistical, Techniques: image processing surveys, Supernovae: general.


Published Journal Article (3.8 Mb)

Copyright Statement
This article has been accepted for publication in Monthly Notices of the Royal Astronomical Society ©: 2015 The Authors Published by Oxford University Press on behalf of the Royal Astronomical Society. All rights reserved.

You might also like

Downloadable Citations