A neural network approach based on more input neurons to predict nuclear mass

The study of nuclear mass is very important, and the neural network (NN) approach can be used to improve the prediction of nuclear mass for various models. Considering the number of valence nucleons of protons and neutrons separately in the input quantity of the NN model, the root-mean-square deviation of binding energy between data from AME2016 and liquid drop model calculations for 2314 nuclei was reduced from 2.385 MeV to 0.203 MeV. In addition, some defects in the Weizsacker-Skyrme (WS)-type model were repaired, which well reproduced the two-neutron separation energy of the nucleus synthesized recently by RIKEN RI Beam Factory [Phys. Rev. Lett. 125, (2020) 122501]. The masses of some of the new nuclei appearing in the latest atomic mass evaluation (AME2020) are also well reproduced. However, the results of neural network methods for predicting the description of regions far from known atomic nuclei need to be further improved. This study shows that such a statistical model can be a tool for systematic searching of nuclei beyond existing experimental data.