Machine learning method for ${}^{12}$C event classification and reconstruction in the active target time-projection chamber

Abstract

Active target time projection chambers are important tools in low energy radioactive ion beams or gamma rays related researches. In this work, we present the application of machine learning methods to the analysis of data obtained from an active target time projection chamber. Specifically, we investigate the effectiveness of Visual Geometry Group (VGG) and the Residual neural Network (ResNet) models for event classification and reconstruction in decays from the excited $2_2^{+}$ state in ${}^{12}$C Hoyle rotation band. The results show that machine learning methods are effective in identifying ${}^{12}$C events from the background noise, with ResNet-34 achieving an impressive precision of 0.99 on simulation data, and the best performing event reconstruction model ResNet-18 providing an energy resolution of ${\sigma }_E<77$ keV and an angular reconstruction deviation of ${\sigma }_{\theta }<0.1$ rad. The promising results suggest that the ResNet model trained on Monte Carlo samples could be used for future classifying and predicting experimental data in active target time projection chambers related experiments.

arXiv comment9 pages, 10 figures, 9 tables

References in corpus (24)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Alpha cluster condensation in 12C and 16O
• Machine Learning in Nuclear Physics
• Unambiguous Identification of the Second 2+ State in 12C and the Structure of the Hoyle State
• Giant Dipole Resonance as a Fingerprint of $\alpha$ Clustering Configurations in ${}^{12}$C and ${}^{16}$O
• Machine learning the nuclear mass
• High precision probe of the fully sequential decay width of the Hoyle state in ${}^{12}$C
• Nuclear liquid-gas phase transition with machine learning
• Texas Active Target (TexAT) detector for experiments with rare isotope beams
• Vertex and Energy Reconstruction in JUNO with Machine Learning Methods
• An Optical Readout TPC (O-TPC) for Studies in Nuclear Astrophysics With Gamma-Ray Beams at HIgS
• Event vertex and time reconstruction in large volume liquid scintillator detector
• Deep Neural Networks for Energy and Position Reconstruction in EXO-200
• Machine-learning-based identification for initial clustering structure in relativistic heavy-ion collisions
• Determining the temperature in heavy-ion collisions with multiplicity distribution
• Machine Learning Methods for Track Classification in the AT-TPC
• A stringent upper limit on the direct 3$\alpha$ decay of the Hoyle State in ${}^{12}$C
• Inferring Global Dynamics of a Black-Box System Using Machine Learning
• Inferring Global Dynamics Using a Learning Machine
• Copy the dynamics using a learning machine
• Performance test of the MAIKo active target
• Almost medium-free measurement of the Hoyle state direct-decay component with a TPC
• Underground laboratory JUNA shedding light on stellar nucleosynthesis
• Classical and Machine Learning Methods for Event Reconstruction in NeuLAND