A deep neural network (DNN) was developed to accurately predict the nuclear charge density distributions for nuclei with proton numbers \(Z \ge 8\) . By incorporating essential nuclear structure features, the model achieved a significant improvement in predictive accuracy over conventional methods. The charge density distributions were analyzed using a Fourier–Bessel (FB) series expansion, and the DNN was trained on a comprehensive dataset derived from relativistic continuum Hartree–Bogoliubov (RCHB) theory calculations. The model demonstrated exceptional performance, with root-mean-square deviations of 0.0123 fm and 0.0198 fm for the charge radii on the training and validation sets, respectively, which remarkably surpassed the precision of the original RCHB calculations. In addition to advancing nuclear physics research, this high-precision model provides critical data for applications in atomic physics, nuclear astrophysics, and related fields.
