CASI: A Convolutional Neural Network Approach for Shell Identification. (arXiv:1905.09310v1 [astro-ph.IM])
<a href="http://arxiv.org/find/astro-ph/1/au:+Oort_C/0/1/0/all/0/1">Colin M. Van Oort</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Xu_D/0/1/0/all/0/1">Duo Xu</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Offner_S/0/1/0/all/0/1">Stella S.R. Offner</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Gutermuth_R/0/1/0/all/0/1">Robert A. Gutermuth</a>
We utilize techniques from deep learning to identify signatures of stellar
feedback in simulated molecular clouds. Specifically, we implement a deep
neural network with an architecture similar to U-Net and apply it to the
problem of identifying wind-driven shells and bubbles using data from
magneto-hydrodynamic simulations of turbulent molecular clouds with embedded
stellar sources. The network is applied to two tasks, dense regression and
segmentation, on two varieties of data, simulated density and synthetic 12 CO
observations. Our Convolutional Approach for Shell Identification (CASI) is
able to obtain a true positive rate greater than 90%, while maintaining a
false positive rate of 1%, on two segmentation tasks and also performs well on
related regression tasks. The source code for CASI is available on GitLab.
We utilize techniques from deep learning to identify signatures of stellar
feedback in simulated molecular clouds. Specifically, we implement a deep
neural network with an architecture similar to U-Net and apply it to the
problem of identifying wind-driven shells and bubbles using data from
magneto-hydrodynamic simulations of turbulent molecular clouds with embedded
stellar sources. The network is applied to two tasks, dense regression and
segmentation, on two varieties of data, simulated density and synthetic 12 CO
observations. Our Convolutional Approach for Shell Identification (CASI) is
able to obtain a true positive rate greater than 90%, while maintaining a
false positive rate of 1%, on two segmentation tasks and also performs well on
related regression tasks. The source code for CASI is available on GitLab.
http://arxiv.org/icons/sfx.gif
