Generative adversarial neural networks for simulating neutrino interactions

2025-02-27

AI Summary

This work addresses the low computational efficiency of neutrino–carbon scattering event simulation in the few-GeV energy regime. We propose the first physics-informed generative simulation paradigm based on conditional generative adversarial networks (cGANs). Methodologically, we introduce cGANs to neutrino–nucleus interaction modeling for the first time, designing dedicated generators for quasielastic and inclusive reaction channels, respectively, and jointly enforcing physical constraints and data distribution fidelity. Training data are drawn from NuWro Monte Carlo simulations. Evaluation employs the Kolmogorov–Smirnov test and 1-Wasserstein distance, demonstrating that both models faithfully reproduce key kinematic distributions while accelerating event generation by three to four orders of magnitude over conventional Monte Carlo methods—enabling real-time analysis in particle physics experiments. The core contribution lies in a novel physics-embedded conditional generation framework, successfully applied for the first time to neutrino–nuclear physics.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Natural Language Processing: Generation
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

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 neutrino-carbon collisions in the few-GeV energy range. The models produce scattering events for a given neutrino energy. GAN models are trained on simulation data from NuWro Monte Carlo event generator. Two GAN models have been obtained: one simulating only quasielastic neutrino-nucleus scatterings and another simulating all interactions at given neutrino energy. The performance of both models has been assessed using two statistical metrics. It is shown that both GAN models successfully reproduce the event distributions.

Problem

• Simulates neutrino-carbon collisions using GANs
• Alternative to Monte Carlo generator approach
• Reproduces event distributions with statistical metrics

Innovation

• GAN models simulate neutrino interactions.
• Trained on NuWro Monte Carlo data.
• Reproduce event distributions accurately.