Neutron Double-Differential Cross Sections for Spallation Reactions from an ANN Model
Abstract
In this paper, we present a data-driven artificial neural network (ANN) model for describing the double differential cross sections (DDCS) of neutron emission in nuclear spallation reactions. The ANN model is found to be precise, flexible, and efficient in predicting differential cross sections of nuclear reactions and in learning the complex dependence of neutron DDCS on the projectile energy (Tp), target nucleus (A and Z), neutron energy (Tn), and neutron emission angle (θn). The model is trained on replicas of experimental data that incorporate uncertainties. Several regularization schemes are examined during ANN training. The input variables of the constructed ANN framework are also investigated, and the following six key variables are selected for the input layer of the ANN model: θn, log(Tn/Tp), Tn/Tp, log(Tp), A2/3, and N/Z. The ANN predictions are compared with training data provided by various experimental collaborations, showing excellent agreement. The resulting model is further tested on test data with projectile energies, target nuclei, and neutron emission angles different from those in the training data, indicating strong predictive power and generalization capability of the ANN framework. As an illustration, the neutron DDCS as functions of Tn, θn, and projectile energy Tp are predicted and presented for copper target. The proposed high-precision ANN model is expected to be beneficial for accelerator-driven system (ADS) design and many other applications in nuclear physics, astrophysics, and nuclear technology development.
Related
- Double-differential neutron-induced cross sections on Fe-nat at GANIL-NFS
- Production cross sections of neutron-rich nuclides near the N=126 neutron-shell closure from 1000 MeV/u Pb208 on Be9
- Probing the Size of Neutron and Proton Single-Particle Orbitals from Nucleon Knockout Reactions
- Measurement of tZq inclusive and differential cross-sections in pp collisions at √s = 13 TeV with the ATLAS detector
- The effect of the coupling between the neutron multiplicity and the fission competition on the evaporation residue cross sections of the 48Ca+244Pu reaction
BibTeX
@misc{wang2026neutron,
title = {{Neutron Double-Differential Cross Sections for Spallation Reactions from an ANN Model}},
author = {Rong Wang and Sheng-Ting Sun and Han-Jie Cai and Xun-Chao Zhang and Huan Jia and Yuan He},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.23706},
eprint = {2609.23706},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.23706},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Neutron Double-Differential Cross Sections for Spallation Reactions from an ANN Model
AU - Rong Wang
AU - Sheng-Ting Sun
AU - Han-Jie Cai
AU - Xun-Chao Zhang
AU - Huan Jia
AU - Yuan He
PY - 2026
DA - 2026/09/20
PB - arXiv
DO - 10.48550/arxiv.2609.23706
UR - https://arxiv.org/abs/2609.23706
AB - In this paper, we present a data-driven artificial neural network (ANN) model for describing the double differential cross sections (DDCS) of neutron emission in nuclear spallation reactions. The ANN model is found to be precise, flexible, and efficient in predicting differential cross sections of nuclear reactions and in learning the complex dependence of neutron DDCS on the projectile energy (T_p), target nucleus (A and Z), neutron energy (T_n), and neutron emission angle (θ_n). The model is trained on replicas of experimental data that incorporate uncertainties. Several regularization schemes are examined during ANN training. The input variables of the constructed ANN framework are also investigated, and the following six key variables are selected for the input layer of the ANN model: θ_n, log(T_n/T_p), T_n/T_p, log(T_p), A^2/3, and N/Z. The ANN predictions are compared with training data provided by various experimental collaborations, showing excellent agreement. The resulting model is further tested on test data with projectile energies, target nuclei, and neutron emission angles different from those in the training data, indicating strong predictive power and generalization capability of the ANN framework. As an illustration, the neutron DDCS as functions of T_n, θ_n, and projectile energy T_p are predicted and presented for copper target. The proposed high-precision ANN model is expected to be beneficial for accelerator-driven system (ADS) design and many other applications in nuclear physics, astrophysics, and nuclear technology development.
ER -