Optimization of Nuclear Mass Models Using Algorithms and Neural Networks

TL;DR

This paper introduces a new nuclear mass model optimized with a hybrid algorithm and neural networks, significantly improving prediction accuracy and capturing special nuclear interactions.

Contribution

It presents a novel hybrid optimization algorithm combined with neural network corrections for nuclear mass models, enhancing accuracy and interaction effects modeling.

Findings

Binding energy prediction error reduced to ~350 keV

Improved accuracy near magic nuclei

Good agreement with experimental data

Abstract

Taking into account nucleon-nucleon gravitational interaction, higher-order terms of symmetry energy, pairing interaction, and neural network corrections, a new BW4 mass model has been developed, which more accurately reflects the contributions of various terms to the binding energy. A novel hybrid algorithm and neural network correction method has been implemented to optimize the discrepancy between theoretical and experimental results, significantly improving the model's binding energy predictions (reduced to around 350 keV). At the same time, the theoretical accuracy near magic nuclei has been marginally enhanced, effectively capturing the special interaction effects around magic nuclei and showing good agreement with experimental data.