Machine Learning methods for event classification and vertex reconstruction of the 12C + 12C reaction with the MATE-TPC

2026-05-27

AI Summary

This study addresses the challenges of accurately classifying elastic scattering and fusion events and reconstructing reaction vertices in ¹²C+¹²C nuclear reactions measured with the MATE-TPC detector. For the first time, deep convolutional neural networks—including ResNet (18/34/50) and VGG-19—are applied to event classification for this reaction, alongside a custom-designed CNN architecture for vertex reconstruction. Evaluated on both simulated and experimental data, the proposed approach achieves classification accuracies of approximately 97% and 90%, respectively, with a 95% identification rate for multi-channel fusion events. These results significantly outperform conventional methods, thereby enhancing the automation and precision of data analysis in such experiments.

Abstract

In modern nuclear physics experiments, identifying events of interest is challenging for nuclear reaction studies with the active target Time Projection Chamber (TPC). In this work, machine learning techniques are employed to analyze the complex data of the 12C + 12C fusion reaction from a TPC named MATE (multi-purpose active-target time projection chamber for nuclear experiments). Specifically, we successfully applied Residual Neural Network (ResNet-50, ResNet-34 and ResNet-18) and Visual Geometry Group (VGG-19) to classify elastic scattering and fusion reaction events from the 12C + 12C reaction. The classification results of the four models are nearly identical, with accuracies of approximately 97% for the simulated data and 90% for the experimental data. Moreover, these approaches successfully identify some events that are misclassified by traditional methods. These models are also applied to classify events from different fusion reaction channels, with classification accuracies of approximately 95% on simulated data. In addition, a Convolutional Neural Network (CNN) model is developed to reconstruct the reaction vertex, providing an alternative strategy for vertex reconstruction. These results indicate that machine learning techniques can effectively classify reaction events from different channels and reconstruct the reaction vertex, thereby paving the way for future analyses of complex nuclear reaction data.

Problem

• event classification
• vertex reconstruction
• nuclear reaction
• active target TPC
• 12C + 12C reaction

Innovation

• Residual Neural Network
• Convolutional Neural Network
• vertex reconstruction
• event classification
• active-target TPC