Convolutional Neural Networks for Shower Energy Prediction in Liquid Argon Time Projection Chambers

When electrons with energies of O(10) MeV pass through a liquid argon time projection chamber (LArTPC), they deposit energy in the form of electromagnetic showers. Methods to reconstruct the energy of these showers in LArTPCs often rely on the combination of a clustering algorithm and a calibration between the shower energy and charge contained in the cluster. This reconstruction process could be improved through the use of a convolutional neural network (CNN). Here we discuss and compare the performance of various CNN-based models on simulated LArTPC images to that of a traditional clustering algorithm. It is shown that the CNN method is able to account for non-linearity in the charge-energy relationship of the shower and address other inefficiencies of a LArTPC.