- Accepted Paper
Bayesian neural network with autoencoder for model-based description of -particle preformation factor
Phys. Rev. C - Accepted 13 November, 2026
DOI: https://doi.org/10.1103/m1zc-cl7k
Phys. Rev. C - Accepted 13 November, 2026
DOI: https://doi.org/10.1103/m1zc-cl7k
decay is an important probe for studying the structure of heavy and superheavy nuclei, in which the -particle preformation probability () is a key physical quantity for describing decay half-lives. This work develops a hybrid framework that integrates Bayesian neural networks with an autoencoder (BNN-Auto), combined with the cosh potential (CPT), to systematically optimize the constraint and prediction of . The model employs variational inference for probabilistic modeling of network weights, providing robust uncertainty quantification for predictions, and utilizes an autoencoder to enhance the robustness of feature representation. Based on experimental data from 535 nuclei, the BNN-Auto method achieves relative improvements in the root mean square deviation ($\sigma_{\rm{RMS}}$) of prediction by on the training set and on the validation set. Further analysis reveals that the and half-life extracted by the model exhibit pronounced odd-even staggering and shell effects in isotopic chains with and isotones with and . Moreover, we successfully predict the decay half-lives of nuclei with and , and the predicted half-lives for show a significant increase near , consistent with the shell effect expected for the predicted ‘stable island’. This study not only provides a high-precision theoretical description for decay, but also offers a new machine learning perspective for exploring the structure of superheavy nuclei.
If the author has provided any supplemental materials with this article they will be available upon publication of the version of record.