Data-driven analysis of dipole strength functions using artificial neural networks

TL;DR

This paper employs an artificial neural network to analyze and predict nuclear dipole strength functions, demonstrating high accuracy, identifying data inconsistencies, and aiding in extracting nuclear matter properties like symmetry energy.

Contribution

The study introduces a neural network model trained on extensive experimental data to predict dipole strength functions and assess nuclear properties, enhancing predictive capabilities in nuclear physics.

Findings

Neural network accurately reproduces experimental dipole data.

Identifies potential inconsistencies in existing datasets.

Confirms theoretical predictions for nuclei with sparse data.

Abstract

We present a data-driven analysis of dipole strength functions across the nuclear chart, employing an artificial neural network to model and predict nuclear dipole responses. We train the network on a dataset of experimentally measured dipole strength functions for 216 different nuclei. To assess its predictive capability, we test the trained model on an additional set of 10 new nuclei, where experimental data exist. Our results demonstrate that the artificial neural network not only accurately reproduces known data but also identifies potential inconsistencies in certain experimental datasets, indicating which results may warrant further review or possible rejection. Additionally, for nuclei where experimental data are sparse or unavailable, the network confirms theoretical calculations, reinforcing its utility as a predictive tool in nuclear physics. Finally, utilizing the predicted electric dipole polarizability, we extract the value of the symmetry energy at saturation density and find it consistent with results from the literature.