000003292 001__ 3292
000003292 005__ 20221020050350.0
000003292 037__ $$aBELLE2-PUB-TE-2022-001
000003292 041__ $$aeng
000003292 100__ $$aM. Milesi
000003292 245__ $$aMachine learning-based lepton identification with the Belle II electromagnetic calorimeter
000003292 260__ $$a$$c2022-10-20
000003292 300__ $$amult. p
000003292 520__ $$aWe present a new model for lepton identification with the Belle II electromagnetic calorimeter (ECL). In the central, barrel region, we use energy-weighted CsI(Tl) crystal images in a convolutional neural network architecture to learn energy deposition patterns of electrons, muons and charged hadrons. In the forward and backward angular regions of the ECL, we exploit higher-level observables associated to the lateral energy spread, and per-crystal pulse shape discrimination information in a set of boosted decision trees trained categorically. 
000003292 6531_ $$aParticle identification
000003292 6531_ $$aECL
000003292 6531_ $$aBDT
000003292 6531_ $$aCNN
000003292 6531_ $$aCalorimeter clustering
000003292 700__ $$aM. Hohmann
000003292 700__ $$aP. Urquijo
000003292 700__ $$aA. Narimani Charan
000003292 700__ $$aA. Novosel
000003292 700__ $$aL. Santelj
000003292 700__ $$aP. Križan
000003292 700__ $$aT. Ferber
000003292 8560_ $$fmarco.milesi@unimelb.edu.au
000003292 8564_ $$uhttps://docs.belle2.org/record/3292/files/BELLE2-PUB-TE-2022-001.pdf