Physically Interpretable Machine Learning for nuclear masses

Abstract

We present a novel approach to modeling the ground state mass of atomic nuclei based directly on a probabilistic neural network constrained by relevant physics. Our Physically Interpretable Machine Learning (PIML) approach incorporates knowledge of physics by using a physically motivated feature space in addition to a soft physics constraint that is implemented as a penalty to the loss function.We train our PIML model on a random set of ∼20% of the Atomic Mass Evaluation (AME) and predict the remaining ∼80%. The success of our methodology is exhibited by the unprecedented σRMS ∼ 186 keV match to data for the training set and σRMS ∼ 316 keV for the entire AME with Z ≥ 20. We show that our general methodology can be interpreted using feature importance.

The production of actinides in neutron star mergers

“…The above discussions outline the major impact of uncertain nuclear physics inputs on the actinide production in merger ejecta. Further development in nuclear theory modeling, e.g., [79][80][81][82][83][84], will continue to improve our understanding in this aspect. In the next section, we will discuss how they can possibly leave imprints on kilonova emission of BNSMs.…”