Skip to main content

Research Repository

See what's under the surface

Advanced Search

Deep recurrent neural networks for supernovae classification

Charnock, Tom; Moss, Adam


Tom Charnock

Adam Moss


We apply deep recurrent neural networks, which are capable of learning complex sequential information, to classify supernovae (code available at The observational time and filter fluxes are used as inputs to the network, but since the inputs are agnostic, additional data such as host galaxy information can also be included. Using the Supernovae Photometric Classification Challenge (SPCC) data, we find that deep networks are capable of learning about light curves, however the performance of the network is highly sensitive to the amount of training data. For a training size of 50% of the representational SPCC data set (around 104 supernovae) we obtain a type-Ia versus non-type-Ia classification accuracy of 94.7%, an area under the Receiver Operating Characteristic curve AUC of 0.986 and an SPCC figure-of-merit F 1 = 0.64. When using only the data for the early-epoch challenge defined by the SPCC, we achieve a classification accuracy of 93.1%, AUC of 0.977, and F 1 = 0.58, results almost as good as with the whole light curve. By employing bidirectional neural networks, we can acquire impressive classification results between supernovae types I, II and III at an accuracy of 90.4% and AUC of 0.974. We also apply a pre-trained model to obtain classification probabilities as a function of time and show that it can give early indications of supernovae type. Our method is competitive with existing algorithms and has applications for future large-scale photometric surveys.

Journal Article Type Article
Publication Date Mar 10, 2017
Journal Astrophysical Journal
Print ISSN 0004-637X
Electronic ISSN 1538-4357
Publisher American Astronomical Society
Peer Reviewed Peer Reviewed
Volume 837
Issue 2
APA6 Citation Charnock, T., & Moss, A. (2017). Deep recurrent neural networks for supernovae classification. Astrophysical Journal, 837(2), doi:10.3847/2041-8213/aa603d
Keywords methods: data analysis – supernovae: general – techniques: miscellaneous
Publisher URL
Copyright Statement Copyright information regarding this work can be found at the following address: http://eprints.nottingh.../end_user_agreement.pdf


Charnock_2017_ApJL_837_L28.pdf (375 Kb)

Copyright Statement
Copyright information regarding this work can be found at the following address:

You might also like

Downloadable Citations