DASH: Deep Learning for the Automated Spectral Classification of Supernovae and their Hosts. (arXiv:1903.02557v1 [astro-ph.IM])
<a href="http://arxiv.org/find/astro-ph/1/au:+Muthukrishna_D/0/1/0/all/0/1">Daniel Muthukrishna</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Parkinson_D/0/1/0/all/0/1">David Parkinson</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Tucker_B/0/1/0/all/0/1">Brad Tucker</a>
We present {tt DASH} (Deep Automated Supernova and Host classifier), a novel
software package that automates the classification of the type, age, redshift,
and host galaxy of supernova spectra. {tt DASH} makes use of a new approach
which does not rely on iterative template matching techniques like all previous
software, but instead classifies based on the learned features of each
supernova type and age bin. It has achieved this by employing a deep
convolutional neural network to train a matching algorithm. This approach has
enabled {tt DASH} to be orders of magnitude faster than previous tools, being
able to accurately classify hundreds or thousands of objects within seconds. We
have tested its performance on the last four years of data from the ongoing
Australian Dark Energy Survey (OzDES). The deep learning models were developed
using {tt TensorFlow}, and were trained using over 4000 supernova templates
taken from the CfA Supernova Program and the Berkeley SN Ia Program as used in
{tt SNID} (Supernova Identification software, Blondin & Tonry (2007)). The
trained models are independent of the number of templates, which allows for
{tt DASH}’s unprecedented speed. We have developed both a graphical interface
for easy visual classification and analysis of supernovae, and a {tt Python}
library for the autonomous and quick classification of several supernova
spectra. The speed, accuracy, user-friendliness, and versatility of {tt DASH}
presents an advancement to existing spectral classification tools. We have made
the code publicly available on {tt GitHub} and PyPI ({tt pip install
astrodash}) to allow for further contributions and development. The package
documentation is available at url{https://astrodash.readthedocs.io}.
We present {tt DASH} (Deep Automated Supernova and Host classifier), a novel
software package that automates the classification of the type, age, redshift,
and host galaxy of supernova spectra. {tt DASH} makes use of a new approach
which does not rely on iterative template matching techniques like all previous
software, but instead classifies based on the learned features of each
supernova type and age bin. It has achieved this by employing a deep
convolutional neural network to train a matching algorithm. This approach has
enabled {tt DASH} to be orders of magnitude faster than previous tools, being
able to accurately classify hundreds or thousands of objects within seconds. We
have tested its performance on the last four years of data from the ongoing
Australian Dark Energy Survey (OzDES). The deep learning models were developed
using {tt TensorFlow}, and were trained using over 4000 supernova templates
taken from the CfA Supernova Program and the Berkeley SN Ia Program as used in
{tt SNID} (Supernova Identification software, Blondin & Tonry (2007)). The
trained models are independent of the number of templates, which allows for
{tt DASH}’s unprecedented speed. We have developed both a graphical interface
for easy visual classification and analysis of supernovae, and a {tt Python}
library for the autonomous and quick classification of several supernova
spectra. The speed, accuracy, user-friendliness, and versatility of {tt DASH}
presents an advancement to existing spectral classification tools. We have made
the code publicly available on {tt GitHub} and PyPI ({tt pip install
astrodash}) to allow for further contributions and development. The package
documentation is available at url{https://astrodash.readthedocs.io}.
http://arxiv.org/icons/sfx.gif
