Nuclear binding energy predictions based on BP neural network
arXiv:1812.03254 · doi:10.1142/S021830132050024X
Abstract
Nuclear masses are of great importance in nuclear physics and astrophysics. Descriptive experimental data on nuclear masses and the prediction of unknown masses based on residual proton-neutron interactions are a focus in nuclear physics. The accuracy of the residual interaction determines the accuracy of the nuclear mass values, so the study of residual interactions is essential. Before we carry out this study, there are many papers using artificial neural networks in nuclear physics. But no one uses BP neural network to study residual interactions. In this paper, we obtained a description and prediction model for residual interactions based on BP neural network. By combining experimental values with residual interactions model, we successfully calculate the nuclear masses of . Results demonstrate that the differences between our calculated values and experimental values (AME2003, AME2012 and AME2016) show that the root-mean-squared deviations (RMSDs) are small (comparing with AME2003, the odd-A nuclei RMSD and the even-A nuclei RMSD are 112 keV and 128 keV; comparing with AME2012, the odd-A nuclei RMSD and the even-A nuclei RMSD are 103 keV and 121 keV; comparing with AME2016, the RMSD of odd-A nuclei and even-A nuclei are 106 keV and 122 keV, respectively). In addition, we obtained some predicted masses based on AME2003 and AME2012, the predicted values have good accuracy and compared well with experimental values (AME2012 and AME2016). The results show that the study of residual interactions using the proposed BP neural network method is feasible and accurate. This method is helpful for analyzing and extracting useful information from a large number of experimental values and then providing a reference for discovering physical laws and support for physical experiments.
arXiv comment13 pages, 2 figures
References in corpus (18)
- Nuclear Ground-State Masses and Deformations
- Microscopic mass formulae
- Skyrme-Hartree-Fock-Bogoliubov nuclear mass formulas: Crossing the 0.6 MeV threshold with microscopically deduced pairing
- Nuclear mass predictions based on Bayesian neural network approach with pairing and shell effects
- Masses, Deformations and Charge Radii--Nuclear Ground-State Properties in the Relativistic Mean Field Model
- Nuclear Mass Predictions for the Crustal Composition of Neutron Stars: A Bayesian Neural Network Approach
- Mirror nuclei constraint in mass formula
- Refining mass formulas for astrophysical applications: a Bayesian neural network approach
- Nuclear mass systematics using neural networks
- Systematics on ground-state energies of nuclei within the neural networks
- Decoding Beta-Decay Systematics: A Global Statistical Model for Beta^- Halflives
- Validating neural-network refinements of nuclear mass models
- Application Of Support Vector Machines To Global Prediction Of Nuclear Properties
- Nucleon axial form factor from a Bayesian neural-network analysis of neutrino-scattering data
- Empirical residual neutron-proton interaction in odd-odd nuclei
- 2017 Update of the Discoveries of Nuclides
- Description and prediction of even-A nuclear masses based on residual proton-neutron interactions
- Influence of binding energies of electrons on nuclear mass predictions