Machine Learning for neutron source distributions

2026-05-12

AI Summary

This work proposes a novel paradigm for neutron source modeling by systematically applying probabilistic generative methods—including variational autoencoders, normalizing flows, generative adversarial networks, and denoising diffusion models—to learn source distributions directly from Monte Carlo simulation data. Traditional approaches rely on raw particle lists, resulting in high computational inefficiency and substantial memory overhead. In contrast, the trained generative models can sample independently and efficiently without retaining the original data, significantly reducing both computational and storage costs. Moreover, the proposed approach achieves higher accuracy than conventional methods, offering a scalable and precise alternative for neutron transport simulations.

Abstract

In light of the recent advancements in machine learning, we propose a novel approach to neutron source distribution estimation through the utilisation of probabilistic generative models. The estimation is based on a Monte Carlo particle list, which is only required during the training stage of the machine learning model. Once the source distribution has been learned, the model is independent of the original particle list, allowing for further sampling in an efficient, rapid, and memory-costless manner. The performance of various generative models is evaluated, including a variational autoencoder, a normalizing flow, a generative adversarial network, and a denoising diffusion model. These approaches are then compared to existing source distribution estimations, and the advantages and disadvantages of each approach are discussed. The results demonstrate that source distributions can be modeled through the use of probabilistic generative models, which paves the way for further advancements in this field.

Problem

• neutron source distribution
• machine learning
• probabilistic generative models
• Monte Carlo simulation

Innovation

• probabilistic generative models
• neutron source distribution
• Monte Carlo particle list
• efficient sampling
• machine learning