http://arxiv.org/abs/2201.01756
The equation of state (EoS) of the strongly interacting cold and ultra-dense matter remains a major challenge in the field of nuclear physics. With the advancements in measurements of neutron star masses, radii, and tidal deformabilities from electromagnetic and gravitational wave observations, neutron stars play an important role in constraining the ultra-dense matter EoS. In this work, we present a novel method that exploits deep learning techniques to reconstruct the neutron star EoS from mass-radius (M-R) observations. We employ neural networks (NNs) to represent the EoS in a model-independent way, within the range of 1-7.4 times the nuclear saturation density. In an unsupervised manner, we implement the Automatic Differentiation (AD) framework to optimize the EoS, as to yield through TOV equations an M-R curve that best fits the observations. We demonstrate it in rebuilding the EoS on mock data, i.e., mass-radius pairs derived from a generated set of polytropic EoSs. The results show that it is possible to reconstruct the EoS with reasonable accuracy, using just 11 mock M-R pairs observations, which is close to the current number of observations.
S. Soma, L. Wang, S. Shi, et. al.
Thu, 6 Jan 22
6/56
Comments: 12 pages, 11 figures
You must be logged in to post a comment.