Machine Learning Methods for Track Classification in the AT-TPC

TL;DR

This paper evaluates machine learning techniques, especially convolutional neural networks, for classifying events in a nuclear physics detector, aiming to improve accuracy and efficiency in analyzing experimental data.

Contribution

The study demonstrates the effectiveness of CNNs for event classification in the AT-TPC detector, providing insights and recommendations for future experiments.

Findings

CNN outperforms other classifiers in proton event detection

Transfer learning enhances classification accuracy

Automated event classification speeds up data analysis

Abstract

We evaluate machine learning methods for event classification in the Active-Target Time Projection Chamber detector at the National Superconducting Cyclotron Laboratory (NSCL) at Michigan State University. An automated method to single out the desired reaction product would result in more accurate physics results as well as a faster analysis process. Binary and multi-class classification methods were tested on data produced by the $^{46}$Ar(p,p) experiment run at the NSCL in September 2015. We found a Convolutional Neural Network to be the most successful classifier of proton scattering events for transfer learning. Results from this investigation and recommendations for event classification in future experiments are presented.