Deep learning approaches for nuclear binding energy prediction: a comparative study of RNN, GRU and LSTM Models

This study investigates the application of deep learning models-recurrent neural networks, gated recurrent units, and long short-term memory networks-for predicting nuclear binding energies. Utilizing data from the Atomic Mass Evaluation (AME2020), we incorporate key nuclear structure features, including proton and neutron numbers, as well as additional terms from the liquid drop model and shell effects. Our comparative analysis demonstrates that the gated recurrent units model achieves the lowest root-mean-square error ({\sigma}RMSE) of 0.326 MeV, surpassing traditional regression-based approaches. To assess model reliability, we validate predictions using the GarveyKelson relations, obtaining an error of 0.202 MeV, and further test extrapolation capabilities using the WS, WS3, and WS4 models. The extrapolation analysis confirms the robustness of our approach, particularly in predicting binding energies for nuclei near the driplines. These results highlight the effectiveness of deep learning in nuclear BE predictions, highlighting its potential to enhance the accuracy and reliability of theoretical nuclear models.