A simulation study to distinguish prompt photon from $π^0$ and beam halo in a granular calorimeter using deep networks
This addresses the challenge of photon identification in particle physics experiments, offering improved performance over traditional methods, though it is incremental as it applies deep learning to an existing problem.
The paper tackled the problem of identifying prompt photons from non-prompt sources like π⁰ decays and beam halo in a hadron collider environment, achieving 99.96% background rejection for beam halo and 97.7% for π⁰ at high signal efficiencies using a Convolutional Neural Network on calorimeter images.
In a hadron collider environment identification of prompt photons originating in a hard partonic scattering process and rejection of non-prompt photons coming from hadronic jets or from beam related sources, is the first step for study of processes with photons in final state. Photons coming from decay of $π_0$'s produced inside a hadronic jet and photons produced in catastrophic bremsstrahlung by beam halo muons are two major sources of non-prompt photons. In this paper the potential of deep learning methods for separating the prompt photons from beam halo and $π^0$'s in the electromagnetic calorimeter of a collider detector is investigated, using an approximate description of the CMS detector. It is shown that, using only calorimetric information as images with a Convolutional Neural Network, beam halo (and $π^{0}$) can be separated from photon with 99.96\% (97.7\%) background rejection for 99.00\% (90.0\%) signal efficiency which is much better than traditionally employed variables.