Machine learning in nuclear physics at low and intermediate energies

TL;DR

This paper reviews how machine learning techniques are applied to low and intermediate energy nuclear physics, covering theoretical and experimental applications, and discusses future directions and improvements in the field.

Contribution

It provides a comprehensive overview of machine learning applications in nuclear physics, highlighting recent developments and potential future research directions.

Findings

Machine learning enhances nuclear structure and reaction modeling.

ML improves event identification and system control in experiments.

Potential for ML algorithm improvements in nuclear physics applications.

Abstract

Machine learning is becoming a new paradigm for scientific research in various research fields due to its exciting and powerful capability of modeling tools used for big-data processing task. In this mini-review, we first briefly introduce different methodologies of the machine learning algorithms and techniques. As a snapshot of many applications by machine learning, some selected applications are presented especially for low and intermediate energy nuclear physics, which include topics on theoretical applications in nuclear structure, nuclear reactions, properties of nuclear matter as well as experimental applications in event identification/reconstruction, complex system control and firmware performance. Finally, we also give a brief summary and outlook on the possible directions of using machine learning in low-intermediate energy nuclear physics and possible improvements in ML algorithms.