Novel Fitting Approach Based on a Neural Network for JUNO

JUNO (Jiangmen Underground Neutrino Observatory) is a neutrino experiment in South China. Its primary goals are to resolve the order of the neutrino mass eigenstates and to precisely measure the oscillation parameters sin2 θ12, ∆m221 , and ∆m231(32) by observing the oscillation pattern of electron antineutrinos produced in eight reactor cores of two commercial nuclear power plants at a distance of 52.5 km. A crucial stage in the data analysis is to fit the observed spectrum to the expected one under different oscillation scenarios taking into account realistic detector response, backgrounds, and all relevant uncertainties. This task becomes computationally challenging when a full Monte Carlo simulation of the detector is directly used to predict the detector response instead of otherwise used analytical empirical models. It is proposed to use a neural network to precisely predict the detector spectrum as a function of oscillation parameters and a set of detector response parameters. This approach drastically reduces computation time and makes it possible to fit a spectrum within a few seconds. This contribution presents the details, performance, and limitations of the method.