Electromagnetic shower reconstruction and energy validation with Michel electrons and ?0 samples for the deep-learning-based analyses in MicroBooNE

This article presents the reconstruction of electromagnetic activity from electrons and photons (showers) used in MicroBooNE deep learning-based low energy electron search. The algorithm uses a combination traditional techniques to estimate shower energies. We validate these predictions using two $\nu_{\mu}$-sourced data samples: charged/neutral current interactions with final state neutral pions charged which muon stops decays within detector producing Michel electron. Both pion sample demonstrate agreement between simulation. Further, absolute scale is shown be consistent relevant physical constant each sample: mass peak cutoff.