Liquid scintillator detectors are widely used in neutrino experiments due to their low energy threshold and high energy resolution. Despite the tiny abundance of ${}^{14}\mathrm{C}$ in LS, the photons induced by the $\beta$ decay of the ${}^{14}\mathrm{C}$ isotope inevitably contaminate the signal, degrading the energy resolution. In this work, we propose three models to tag ${}^{14}\mathrm{C}$ photon hits in $e^{+}$ events with ${}^{14}\mathrm{C}$ pileup, thereby suppressing its impact on the energy resolution at the hit level: a gated spatiotemporal graph neural network and two transformer-based models with scalar and vector charge encoding. For a simulated test dataset in which each event contains one ${}^{14}\mathrm{C}$ and one ${\mathrm{e}}^{+}$ with kinetic energy below 5 MeV, the models achieve ${}^{14}\mathrm{C}$ recall rates of 25%–48% while maintaining ${\mathrm{e}}^{+}$ to ${}^{14}\mathrm{C}$ misidentification below 1%, leading to a large improvement in the resolution of total charge for events where ${\mathrm{e}}^{+}$ and ${}^{14}\mathrm{C}$ photon hits strongly overlap in space and time.

Close

PrevNext

View figure in article

• Machine learning
• Neutrino detection
• Scintillators