Machine learning applied to proton radiography

TL;DR

This paper introduces a neural network-based 3-D reconstruction method for proton radiography, enabling more accurate and efficient magnetic field imaging in high energy density plasmas, even with noisy data.

Contribution

It presents a novel neural network approach for 3-D magnetic field reconstruction from proton radiographs, extending capabilities beyond previous methods that relied on simplifying assumptions.

Findings

Mean reconstruction error of less than 5% with noise

More computationally efficient than existing techniques

Highlights the importance of proton tomography for complex fields

Abstract

Proton radiography is a technique extensively used to resolve magnetic field structures in high energy density plasmas, revealing a whole variety of interesting phenomena such as magnetic reconnection and collisionless shocks found in astrophysical systems. Existing methods of analyzing proton radiographs give mostly qualitative results or specific quantitative parameters such as magnetic field strength, and recent work showed that the line-integrated transverse magnetic field can be reconstructed in specific regimes where many simplifying assumptions were needed. Using artificial neural networks, we suggest a novel 3-D reconstruction method that works for a more general case. A proof of concept is presented here, with mean reconstruction errors of less than 5 percent even after introducing noise. We demonstrate that over the long term, this approach is more computationally efficient compared to other techniques. We also highlight the need for proton tomography because (i) certain field structures cannot be reconstructed from a single radiograph and (ii) errors can be further reduced when reconstruction is performed on radiographs generated by proton beams fired in different directions.