Deriving star cluster parameters with convolutional neural networks. II. Extinction and cluster/background classification. (arXiv:1911.10059v1 [astro-ph.GA])
<a href="http://arxiv.org/find/astro-ph/1/au:+Bialopetravicius_J/0/1/0/all/0/1">J. Bialopetravičius</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Narbutis_D/0/1/0/all/0/1">D. Narbutis</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Vansevicius_V/0/1/0/all/0/1">V. Vansevičius</a>
Context. Convolutional neural networks (CNNs) have been established as the
go-to method for fast object detection and classification on natural images.
This opens the door for astrophysical parameter inference on the exponentially
increasing amount of sky survey data. Until now, star cluster analysis was
based on integral or resolved stellar photometry, which limits the amount of
information that can be extracted from individual pixels of cluster images.
Aims. We aim to create a CNN capable of inferring star cluster evolutionary,
structural, and environmental parameters from multi-band images, as well to
demonstrate its capabilities in discriminating genuine clusters from galactic
stellar backgrounds.
Methods. A CNN based on the deep residual network (ResNet) architecture was
created and trained to infer cluster ages, masses, sizes, and extinctions, with
respect to the degeneracies between them. Mock clusters placed on M83 Hubble
Space Telescope (HST) images utilizing three photometric passbands (F336W,
F438W, and F814W) were used. The CNN is also capable of predicting the
likelihood of a cluster’s presence in an image, as well as quantifying its
visibility (signal-to-noise).
Results. The CNN was tested on mock images of artificial clusters and has
demonstrated reliable inference results for clusters of ages $lesssim$100 Myr,
extinctions $A_V$ between 0 and 3 mag, masses between $3times10^3$ and
$3times10^5$ ${rm M_odot}$, and sizes between 0.04 and 0.4 arcsec at the
distance of the M83 galaxy. Real M83 galaxy cluster parameter inference tests
were performed with objects taken from previous studies and have demonstrated
consistent results.
Context. Convolutional neural networks (CNNs) have been established as the
go-to method for fast object detection and classification on natural images.
This opens the door for astrophysical parameter inference on the exponentially
increasing amount of sky survey data. Until now, star cluster analysis was
based on integral or resolved stellar photometry, which limits the amount of
information that can be extracted from individual pixels of cluster images.
Aims. We aim to create a CNN capable of inferring star cluster evolutionary,
structural, and environmental parameters from multi-band images, as well to
demonstrate its capabilities in discriminating genuine clusters from galactic
stellar backgrounds.
Methods. A CNN based on the deep residual network (ResNet) architecture was
created and trained to infer cluster ages, masses, sizes, and extinctions, with
respect to the degeneracies between them. Mock clusters placed on M83 Hubble
Space Telescope (HST) images utilizing three photometric passbands (F336W,
F438W, and F814W) were used. The CNN is also capable of predicting the
likelihood of a cluster’s presence in an image, as well as quantifying its
visibility (signal-to-noise).
Results. The CNN was tested on mock images of artificial clusters and has
demonstrated reliable inference results for clusters of ages $lesssim$100 Myr,
extinctions $A_V$ between 0 and 3 mag, masses between $3times10^3$ and
$3times10^5$ ${rm M_odot}$, and sizes between 0.04 and 0.4 arcsec at the
distance of the M83 galaxy. Real M83 galaxy cluster parameter inference tests
were performed with objects taken from previous studies and have demonstrated
consistent results.
http://arxiv.org/icons/sfx.gif
