Skip to yearly menu bar Skip to main content


Poster
in
Workshop: The Synergy of Scientific and Machine Learning Modelling (SynS & ML) Workshop

NuCLR: Nuclear Co-Learned Representations

Niklas Nolte · Ouail Kitouni · Mike Williams · Sokratis Trifinopoulos · Subhash Kantamneni

Keywords: [ Representation Learning ] [ nuclear physics ]


Abstract:

We introduce Nuclear Co-Learned Representations (NuCLR), a deep learning model that predicts various nuclear observables, including binding and decay energies, and nuclear charge radii. The model is trained using a multi-task approach with shared representations and obtains state-of-the-art performance, achieving levels of precision that are crucial for understanding fundamental phenomena in nuclear (astro)physics. We also report an intriguing finding that the learned representation of NuCLR exhibits the prominent emergence of crucial aspects of the nuclear shell model, namely the shell structure, including the well-known magic numbers, and the Pauli Exclusion Principle. This suggests that the model is capable of capturing the underlying physical principles, and that our approach has the potential to offer valuable insights into nuclear theory.

Chat is not available.