Speaker
Description
A proposal for the CEPC ECAL is a highly granular scintillating crystal design that uses SiPMs to measure physics signals from photons. The potential to develop particle identification methods using deep and traditional machine learning is explored. A contrastive learning technique was demonstrated to enable the separation of showering and ‘punch-through’ pions without explicit labels. A supervised PID was then trained using the results, using both a graph neural network and a boosted decision tree to distinguish electron, showering hadron, and minimum-ionizing-particle-like events. The classifier achieved an area under the receiver operating characteristic curve of greater than 99% for both cases. A SHAP analysis showed the boosted decision tree classifier matched expectations for each event type.
