EVStabilityNet: Predicting the Stability of Star Clusters in General Relativity

Abstract

We present a deep neural network which predicts the stability of isotropic steady states of the asymptotically flat, spherically symmetric Einstein-Vlasov system in Schwarzschild coordinates. The network takes as input the energy profile and the redshift of the steady state. Its architecture consists of a U-Net with a dense bridge. The network was trained on more than ten thousand steady states using an active learning scheme and has high accuracy on test data. As first applications, we analyze the validity of physical hypotheses regarding the stability of the steady states.

Figures (4)

• Figure 1: Architecture of the EVStabilityNet.
• Figure 2: An illustration of sixteen randomly generated energy profile functions following the process described in \ref{['it:random1']}--\ref{['it:random4']}.
• Figure 3: The training process for the EVStabilityNet using active learning.
• Figure 4: Performance of the EVStabilityNet on data from GueStRe21.