Neural Network Emulation of Spontaneous Fission

TL;DR

This paper demonstrates that neural networks can effectively emulate complex nuclear density functional theory calculations, enabling rapid predictions of fission properties crucial for astrophysical nucleosynthesis modeling.

Contribution

It introduces neural network emulators for potential energy surfaces and inertia tensors, significantly speeding up fission property calculations across the nuclear chart.

Findings

NNs predict potential energy within 500 keV RMS error

NNs estimate fission half-lives within a factor of 10^3

Emulators enable large-scale fission studies with reduced computational cost

Abstract

Large-scale computations of fission properties are an important ingredient for nuclear reaction network calculations simulating rapid neutron-capture process (the r process) nucleosynthesis. Due to the large number of fissioning nuclei contributing to the r process, a microscopic description of fission based on nuclear density functional theory (DFT) is computationally challenging. We explore the use of neural networks (NNs) to construct DFT emulators capable of predicting potential energy surfaces and collective inertia tensors across the whole nuclear chart. We use constrained Hartree-Fock-Boguliubov (HFB) calculations to predict the potential energy and collective inertia tensor in the axial quadrupole and octupole collective coordinates, for a set of nuclei in the r-process region. We then employ NNs to emulate the HFB energy and collective inertia tensor across the considered region of the nuclear chart. Least-action pathways characterizing spontaneous fission half-lives and fragment yields are obtained using the nudged elastic band method. The potential energy predicted by NNs agrees with the DFT value to within a root-mean-square error of 500 keV, and the collective inertia components agree to within an order of magnitude. The exit points on the outer turning line are found to be well emulated. For the spontaneous fission half-lives the NN emulation provides values that are found to agree with the DFT predictions within a factor of $10^3$ across more than 70 orders of magnitude. Neural networks are able to emulate the potential energy and collective inertia well enough to reasonably predict physical observables. Future directions of study, such as the inclusion of additional collective degrees of freedom and active learning, will improve the predictive power of microscopic theory and further enable large-scale fission studies.