Discrimination of pp solar neutrinos and $^{14}$C pile-up events in a large scale LS detector

As an unique probe, the precision measurement of \textit{pp} neutrinos is important for the study of the Sun's energy mechanism, thermodynamic equilibrium monitoring, and neutrino oscillation in the vacuum dominated region. For a large scale liquid scintillator detector, one of the bottleneck for \textit{pp} neutrino detection comes from the pile-up events of intrinsic $^{14}$C decays. This paper presents a few approaches to discriminate \textit{pp} neutrinos and $^{14}$C pile-up events by considering the difference in their time and spatial distributions. In this work, a Geant4-based Monte Carlo simulation was built, then multivariate analysis and deep learning technology are adopted respectively to investigate the capability of $^{14}$C pile-up reduction. As a result, VGG network and BDTG model show good performance in the discrimination of \textit{pp} solar neutrinos and $^{14}$C double pile-up events, their signal significance can achieve 15.6 and 10.3 using only one day statistics. In this case, the signal efficiency is 42.7\% for the discrimination using VGG network when rejecting 99.81\% $^{14}$C double pile-up events. And the signal efficiency is 51.1\% for the case using BDTG model when rejecting 99.18\% $^{14}$C double pile-up events.