LArTPC hit-based topology classification with quantum machine learning and symmetry considerations

We present a new approach to separate tracklike and showerlike topologies in liquid argon time projection chamber (LArTPC) experiments for neutrino physics using quantum machine learning. Effective reconstruction of neutrino events in LArTPCs requires accurate and granular information about the energy deposited in the detector. These energy deposits can be viewed as 2D images. Simulated data from the MicroBooNE experiment and a simple custom dataset are used to perform pixel-level classification of the underlying particle topology. Images of the events have been studied by creating small patches around each pixel to characterize its topology based on its immediate neighborhood. This classification is achieved using convolution-based learning models, including quantum-enhanced architectures known as quanvolutional neural networks. The quanvolutional networks are extended to symmetries beyond translation. Rotational symmetry has been incorporated into a subset of the models. This study demonstrates that quantum-enhanced models perform better than their classical counterparts with a comparable number of parameters, but are outperformed by classical models with two orders of magnitude more parameters. The inclusion of rotation symmetry appears beneficial only in a small number of cases and remains to be explored further. Possible future use of quantum machine learning in the reconstruction phase is discussed, with emphasis on future LArTPC experiments such as Deep Underground Neutrino Experiment (DUNE)-far detector (FD).