Machine learning applied to proton radiography
arXiv:1608.05582 · doi:10.1103/PhysRevE.95.043305
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.
References in corpus (6)
- Strong magnetic fields in normal galaxies at high redshifts
- Observation of magnetic field generation via the Weibel instability in interpenetrating plasma flows
- Neural networks and separation of Cosmic Microwave Background and astrophysical signals in sky maps
- Wide Field Imaging. I. Applications of Neural Networks to object detection and star/galaxy classification
- Quantitative shadowgraphy and proton radiography for large intensity modulations
- Development of an Interpretive Simulation Tool for the Proton Radiography Technique
Cited by in corpus (5)
- Experimental observations of detached bow shock formation in the interaction of a laser-produced plasma with a magnetized obstacle
- Reconstructing magnetic deflections from sets of proton images using differential evolution
- Proton deflectometry analysis in magnetized plasmas: magnetic field reconstruction in one dimension
- Enabling the Realisation of Proton Tomography
- Methods for Extremely Sparse-Angle Proton Tomography