Description of nuclear properties using Symbolic Machine Learning

We present a novel approach employing Multi-objective Iterated Symbolic Regression (MISR) to discover analytical expressions that describe nuclear properties, focusing on nuclear binding energies and charge radii. Our method identifies relatively simple, analytical relationships between nuclear properties and the number of protons and neutrons, achieving precision comparable to state-of-the-art models. Our results demonstrate the promise of symbolic machine learning for describing complex nuclear properties, paving the way for obtaining improved and more explainable predictive nuclear models.