Generative adversarial neural networks for simulating neutrino interactions

TL;DR

This paper introduces GAN models trained on Monte Carlo data to efficiently simulate neutrino scattering events, offering an alternative to traditional simulation methods in particle physics.

Contribution

It develops and evaluates GAN-based models for simulating neutrino interactions, specifically muon kinematics, across a range of energies, demonstrating their effectiveness.

Findings

GAN models accurately reproduce muon kinematic distributions.

Models work effectively for neutrino energies from 300 MeV to 10 GeV.

GAN approach offers a promising alternative to Monte Carlo simulations.

Abstract

We propose a new approach to simulate neutrino scattering events as an alternative to the standard Monte Carlo generator approach. Generative adversarial neural network (GAN) models are developed to simulate charged current neutrino-carbon collisions in the few-GeV energy range. We consider a simplified framework to generate muon kinematic variables, specifically its energy and scattering angle. GAN models are trained on simulation data from \nuwro{} Monte Carlo event generator. Two GAN models have been obtained: one simulating quasielastic neutrino-nucleus scatterings and another simulating all interactions at given neutrino energy. The models work for neutrino energy ranging from 300 MeV to 10 GeV. The performance of both models has been assessed using two statistical metrics. It is shown that both GAN models successfully reproduce the distribution of muon kinematics.