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

Abstract

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 (${\mathrm{N}}_{\mathrm{bars}}$) 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 ${\mathrm{N}}_{\mathrm{bars}}$ 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.

arXiv comment17 pages, 10 figures

References in corpus (21)

• Observation of Reactor Electron Antineutrino Disappearance in the RENO Experiment
• The Reactor Antineutrino Anomaly
• Indication for the disappearance of reactor electron antineutrinos in the Double Chooz experiment
• Improved Predictions of Reactor Antineutrino Spectra
• Sterile neutrino search at NEOS Experiment
• Spectral measurement of electron antineutrino oscillation amplitude and frequency at Daya Bay
• Observation of Energy and Baseline Dependent Reactor Antineutrino Disappearance in the RENO Experiment
• A Convolutional Neural Network Neutrino Event Classifier
• Measurement of the Reactor Antineutrino Flux and Spectrum at Daya Bay
• Quark and Gluon Jet Substructure
• Determination of the Neutrino Mass Hierarchy at an Intermediate Baseline
• Search for a Light Sterile Neutrino at Daya Bay
• Sterile Neutrino Constraints from the STEREO Experiment with 66 days of Reactor-on Data
• The PROSPECT Physics Program
• Measurement of the Antineutrino Spectrum from ${}^{235}$U Fission at HFIR with PROSPECT
• A mobile antineutrino detector with plastic scintillators
• Performance of a full scale prototype detector at the BR2 reactor for the SoLid experiment
• Direct Measurement of Backgrounds using Reactor-Off Data in Double Chooz
• A plastic scintillator array for reactor based anti-neutrino studies
• Improved STEREO simulation with a new gamma ray spectrum of excited gadolinium isotopes using FIFRELIN
• Sensitivity to sterile neutrino mixing using reactor antineutrinos

Cited by in corpus (3)

• Measurements using a prototype array of plastic scintillator bars for reactor based electron anti-neutrino detection
• Characterization of plastic scintillator bars using fast neutrons from D-D and D-T reactions
• Measurement of cosmic muon-induced neutron background with ISMRAN detector in a non-reactor environment