https://doi.org/10.1051/epjconf/202430207002
Neutron resonance cross sections evaluation based on the phase shift deep neural network
Institute of Applied Physics and Computational Mathematics, 100094, Beijing, China
* Corresponding author: hu_zehua@iapcm.ac.cn
Published online: 15 October 2024
Neutron resonance cross sections are essential in many nuclear science and application fields. Evaluated nuclear libraries usually derive neutron resonance parameters using R-matrix theory. However, determining these parameters and reconstructing the pointwise cross sections required for transport calculations is a time-consuming process. This paper presents a new method for fitting neutron resonance cross sections by using a phase shift deep neural network (PhaseDNN). The network presents resonance cross sections based on its network parameters. This approach allows for the quick calculation of cross section values from the given network parameters. Additionally, PhaseDNN can fit network parameters to experimental data to obtain a smooth resonance cross section curve. Therefore, it has the potential to be an alternative to R-matrix theory.
© The Authors, published by EDP Sciences, 2024
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
