Identifying mass composition of ultra-high-energy cosmic rays using deep learning. (arXiv:2112.02072v1 [astro-ph.IM])
<a href="http://arxiv.org/find/astro-ph/1/au:+Kalashev_O/0/1/0/all/0/1">O. Kalashev</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Kharuk_I/0/1/0/all/0/1">I. Kharuk</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Kuznetsov_M/0/1/0/all/0/1">M. Kuznetsov</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Rubtsov_G/0/1/0/all/0/1">G. Rubtsov</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Sako_T/0/1/0/all/0/1">T. Sako</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Tsunesada_Y/0/1/0/all/0/1">Y. Tsunesada</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Zhezher_Y/0/1/0/all/0/1">Ya. Zhezher</a>
We introduce a novel method for identifying the mass composition of
ultra-high-energy cosmic rays using deep learning. The key idea of the method
is to use a chain of two neural networks. The first network predicts the type
of a primary particle for individual events, while the second infers the mass
composition of an ensemble of events. We apply this method to the Monte-Carlo
data for the Telescope Array Surface Detectors readings, on which it yields an
unprecedented low error of 7% for 4-component approximation. The statistical
error is shown to be inferior to the systematic one related to the choice of
the hadronic interaction model used for simulations.
We introduce a novel method for identifying the mass composition of
ultra-high-energy cosmic rays using deep learning. The key idea of the method
is to use a chain of two neural networks. The first network predicts the type
of a primary particle for individual events, while the second infers the mass
composition of an ensemble of events. We apply this method to the Monte-Carlo
data for the Telescope Array Surface Detectors readings, on which it yields an
unprecedented low error of 7% for 4-component approximation. The statistical
error is shown to be inferior to the systematic one related to the choice of
the hadronic interaction model used for simulations.
http://arxiv.org/icons/sfx.gif
