Machine Learning for neutron source distributions

TL;DR

This paper introduces a machine learning-based method for neutron source distribution estimation using probabilistic generative models, enabling efficient and memory-light sampling after training.

Contribution

It evaluates various generative models for neutron source estimation and compares their performance to traditional methods, highlighting their advantages and limitations.

Findings

Probabilistic generative models can effectively model neutron source distributions.

Models like VAEs, normalizing flows, GANs, and diffusion models were tested.

The approach allows rapid, memory-efficient sampling post-training.

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.