Machine learning technique to improve anti-neutrino detection efficiency for the ISMRAN experiment

The Indian Scintillator Matrix for Reactor Anti-Neutrino detection - ISMRAN experiment aims to detect electron anti-neutrinos ($\bar\nu_e$) emitted from a reactor via inverse beta decay reaction (IBD). The setup, consisting of 1 ton segmented Gadolinium foil wrapped plastic scintillator array, is planned for remote reactor monitoring and sterile neutrino search. The detection of prompt positron and delayed neutron from IBD will provide the signature of $\bar\nu_e$ event in ISMRAN. The number of segments with energy deposit ($\mathrm{N_{bars}}$) and sum total of these deposited energies are used as discriminants for identifying prompt positron event and delayed neutron capture event. However, a simple cut based selection of above variables leads to a low $\bar\nu_e$ signal detection efficiency due to overlapping region of $\mathrm{N_{bars}}$ and sum energy for the prompt and delayed events. Multivariate analysis (MVA) tools, employing variables suitably tuned for discrimination, can be useful in such scenarios. In this work we report the results from an application of artificial neural network -- the multilayer perceptron (MLP), particularly the Bayesian extension -- MLPBNN, to the simulated signal and background events in ISMRAN. The results from application of MLP to classify prompt positron events from delayed neutron capture events on Hydrogen, Gadolinium nuclei and also from the typical reactor $\gamma$-ray and fast neutron backgrounds is reported. An enhanced efficiency of $\sim$91$\%$ with a background rejection of $\sim$73$\%$ for prompt selection and an efficiency of $\sim$89$\%$ with a background rejection of $\sim$71$\%$ for the delayed capture event, is achieved using the MLPBNN classifier for the ISMRAN experiment.