Nuclear Model

Nuclear models aim to describe the complex behavior of atomic nuclei, a challenge due to the many-body interactions involved. Current research focuses on developing more accurate and efficient models using machine learning techniques, such as symbolic regression and deep learning architectures with multi-task learning approaches, to predict nuclear properties like binding energies and radii. These advancements improve the precision of predictions and offer insights into underlying physical principles, like the nuclear shell model, with implications for nuclear astrophysics and the understanding of nuclear stability. The development of robust and efficient surrogate models also allows for faster exploration of the nuclear landscape using fewer computationally expensive simulations.