Classical and Machine Learning Methods for Event Reconstruction in NeuLAND

TL;DR

This paper compares classical and machine learning methods for reconstructing neutron event data in NeuLAND, showing that ML improves the accuracy of first interaction point detection, enhancing physical measurement resolution.

Contribution

It introduces machine learning approaches for event reconstruction in NeuLAND, demonstrating improved first interaction point identification over classical methods.

Findings

ML methods significantly improve first interaction point reconstruction.

Classical models perform similarly in multiplicity reconstruction.

Enhanced interaction point accuracy leads to better physical quantity resolution.

Abstract

NeuLAND, the New Large Area Neutron Detector, is a key component to investigate the origin of matter in the universe with experimental nuclear physics. It is a core component of the Reactions with Relativistic Radioactive Beams setup at the Facility for Antiproton and Ion Research, Germany. Neutrons emitted from these reactions create a wide range of patterns in NeuLAND. From these patterns, the number of neutrons (multiplicity) and their first interaction points must be reconstructed to determine the neutrons' four-momenta. In this paper, we detail the challenges involved in this reconstruction and present a range of possible solutions. Scikit-Learn classification models and simple Keras-based neural networks were trained on a wide range of input-scaler combinations and compared to classical models. While the improvement in multiplicity reconstruction is limited due to the overlap between features, the machine learning methods achieve a significantly better first interaction point selection, which directly improves the resolution of physical quantities.