Deep Learning: Extrapolation Tool for Computational Nuclear Physics
TimeSunday, November 11th2:21pm - 2:24pm
DescriptionThe goal of nuclear theory is to understand how nuclei arise from interacting nucleons based on the underlying theory of the strong interactions, quantum chromodynamics (QCD). The interactions among the nucleons inside a nucleus are dominated by the strong interaction, which is non-perturbative in the low-energy regime relevant for nuclear physics. With access to powerful High Performance Computing (HPC) systems, several ab initio approaches have been developed to study nuclear structure and reactions, such as the No-Core Shell Model (NCSM). The NCSM and other approaches require an extrapolation of the results obtained in a finite basis space to the infinite basis space limit and assessment of the uncertainty of those extrapolations. Each observable requires a separate extrapolation and most observables have no proven extrapolation method at the present time. We propose a feed-forward artificial neural network (ANN) method as an extrapolation tool to obtain the ground state energy and the ground state point proton root-mean-square (rms) radius and their extrapolation uncertainties. We have generated theoretical data for 6Li by performing ab initio NCSM calculations using basis spaces up through the largest computationally feasible basis space. The designed ANNs are sufficient to produce results for these two very different observables in ^6Li from the ab initio NCSM results in small basis spaces that satisfy the following theoretical physics condition: independence of basis space parameters in the limit of extremely large matrices. Comparisons of the ANN results with other extrapolation methods are also provided.