Machine learning applied to proton radiography of high-energy-density plasmas
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 radio...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Journal article |
| Published: |
American Physical Society
2017
|
| _version_ | 1826261232990027776 |
|---|---|
| author | Chen, N Kasim, M Ceurvorst, L Ratan, N Sadler, J Levy, M Trines, R Bingham, R Norreys, P |
| author_facet | Chen, N Kasim, M Ceurvorst, L Ratan, N Sadler, J Levy, M Trines, R Bingham, R Norreys, P |
| author_sort | Chen, N |
| collection | OXFORD |
| description | 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 demonstrate for the first time 3D reconstruction of magnetic fields in the nonlinear regime, an improvement over existing methods, which reconstruct only in 2D and in the linear regime. A proof of concept is presented here, with mean reconstruction errors of less than 5% 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. |
| first_indexed | 2024-03-06T19:18:17Z |
| format | Journal article |
| id | oxford-uuid:192f6fdf-bbdd-44ca-b6fb-6302f1f93aa1 |
| institution | University of Oxford |
| last_indexed | 2024-03-06T19:18:17Z |
| publishDate | 2017 |
| publisher | American Physical Society |
| record_format | dspace |
| spelling | oxford-uuid:192f6fdf-bbdd-44ca-b6fb-6302f1f93aa12022-03-26T10:47:30ZMachine learning applied to proton radiography of high-energy-density plasmasJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:192f6fdf-bbdd-44ca-b6fb-6302f1f93aa1Symplectic Elements at OxfordAmerican Physical Society2017Chen, NKasim, MCeurvorst, LRatan, NSadler, JLevy, MTrines, RBingham, RNorreys, PProton 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 demonstrate for the first time 3D reconstruction of magnetic fields in the nonlinear regime, an improvement over existing methods, which reconstruct only in 2D and in the linear regime. A proof of concept is presented here, with mean reconstruction errors of less than 5% 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. |
| spellingShingle | Chen, N Kasim, M Ceurvorst, L Ratan, N Sadler, J Levy, M Trines, R Bingham, R Norreys, P Machine learning applied to proton radiography of high-energy-density plasmas |
| title | Machine learning applied to proton radiography of high-energy-density plasmas |
| title_full | Machine learning applied to proton radiography of high-energy-density plasmas |
| title_fullStr | Machine learning applied to proton radiography of high-energy-density plasmas |
| title_full_unstemmed | Machine learning applied to proton radiography of high-energy-density plasmas |
| title_short | Machine learning applied to proton radiography of high-energy-density plasmas |
| title_sort | machine learning applied to proton radiography of high energy density plasmas |
| work_keys_str_mv | AT chenn machinelearningappliedtoprotonradiographyofhighenergydensityplasmas AT kasimm machinelearningappliedtoprotonradiographyofhighenergydensityplasmas AT ceurvorstl machinelearningappliedtoprotonradiographyofhighenergydensityplasmas AT ratann machinelearningappliedtoprotonradiographyofhighenergydensityplasmas AT sadlerj machinelearningappliedtoprotonradiographyofhighenergydensityplasmas AT levym machinelearningappliedtoprotonradiographyofhighenergydensityplasmas AT trinesr machinelearningappliedtoprotonradiographyofhighenergydensityplasmas AT binghamr machinelearningappliedtoprotonradiographyofhighenergydensityplasmas AT norreysp machinelearningappliedtoprotonradiographyofhighenergydensityplasmas |