CLOVER: Convnet Line-fitting Of Velocities in Emission-line Regions. (arXiv:1909.08727v1 [astro-ph.SR])
<a href="http://arxiv.org/find/astro-ph/1/au:+Keown_J/0/1/0/all/0/1">Jared Keown</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Francesco_J/0/1/0/all/0/1">James Di Francesco</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Teimoorinia_H/0/1/0/all/0/1">Hossen Teimoorinia</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Rosolowsky_E/0/1/0/all/0/1">Erik Rosolowsky</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Chen_M/0/1/0/all/0/1">Michael Chun-Yuan Chen</a>
When multiple star-forming gas structures overlap along the line-of-sight and
emit optically thin emission at significantly different radial velocities, the
emission can become non-Gaussian and often exhibits two distinct peaks.
Traditional line-fitting techniques can fail to account adequately for these
double-peaked profiles, providing inaccurate cloud kinematics measurements. We
present a new method called Convnet Line-fitting Of Velocities in Emission-line
Regions (CLOVER) for distinguishing between one-component, two-component, and
noise-only emission lines using 1D convolutional neural networks trained with
synthetic spectral cubes. CLOVER utilizes spatial information in spectral cubes
by predicting on $3times3$ pixel sub-cubes, using both the central pixel’s
spectrum and the average spectrum over the $3times3$ grid as input. On an
unseen set of 10,000 synthetic spectral cubes in each predicted class, CLOVER
has classification accuracies of $sim99%$ for the one-component class and
$sim97%$ for the two-component class. For the noise-only class, which is
analogous to a signal-to-noise cutoff of four for traditional line-fitting
methods, CLOVER has classification accuracy of $100%$. CLOVER also has
exceptional performance on real observations, correctly distinguishing between
the three classes across a variety of star-forming regions. In addition, CLOVER
quickly and accurately extracts kinematics directly from spectra identified as
two-component class members. Moreover, we show that CLOVER is easily scalable
to emission lines with hyperfine splitting, making it an attractive tool in the
new era of large-scale NH$_3$ and N$_2$H$^+$ mapping surveys.
When multiple star-forming gas structures overlap along the line-of-sight and
emit optically thin emission at significantly different radial velocities, the
emission can become non-Gaussian and often exhibits two distinct peaks.
Traditional line-fitting techniques can fail to account adequately for these
double-peaked profiles, providing inaccurate cloud kinematics measurements. We
present a new method called Convnet Line-fitting Of Velocities in Emission-line
Regions (CLOVER) for distinguishing between one-component, two-component, and
noise-only emission lines using 1D convolutional neural networks trained with
synthetic spectral cubes. CLOVER utilizes spatial information in spectral cubes
by predicting on $3times3$ pixel sub-cubes, using both the central pixel’s
spectrum and the average spectrum over the $3times3$ grid as input. On an
unseen set of 10,000 synthetic spectral cubes in each predicted class, CLOVER
has classification accuracies of $sim99%$ for the one-component class and
$sim97%$ for the two-component class. For the noise-only class, which is
analogous to a signal-to-noise cutoff of four for traditional line-fitting
methods, CLOVER has classification accuracy of $100%$. CLOVER also has
exceptional performance on real observations, correctly distinguishing between
the three classes across a variety of star-forming regions. In addition, CLOVER
quickly and accurately extracts kinematics directly from spectra identified as
two-component class members. Moreover, we show that CLOVER is easily scalable
to emission lines with hyperfine splitting, making it an attractive tool in the
new era of large-scale NH$_3$ and N$_2$H$^+$ mapping surveys.
http://arxiv.org/icons/sfx.gif
