Source localization for neutron imaging systems using convolutional neural networks.
| Title: | Source localization for neutron imaging systems using convolutional neural networks. |
|---|---|
| Authors: | Saavedra G; Los Alamos National Laboratory, Los Alamos, New Mexico 87545, USA.; Geppert-Kleinrath V; Los Alamos National Laboratory, Los Alamos, New Mexico 87545, USA.; Danly C; Los Alamos National Laboratory, Los Alamos, New Mexico 87545, USA.; Durocher M; Los Alamos National Laboratory, Los Alamos, New Mexico 87545, USA.; Wilde C; Los Alamos National Laboratory, Los Alamos, New Mexico 87545, USA.; Fatherley V; Los Alamos National Laboratory, Los Alamos, New Mexico 87545, USA.; Mendoza E; Los Alamos National Laboratory, Los Alamos, New Mexico 87545, USA.; Tafoya L; Los Alamos National Laboratory, Los Alamos, New Mexico 87545, USA.; Volegov P; Lawrence Livermore National Laboratory, Livermore, California 94550, USA.; Fittinghoff D; Lawrence Livermore National Laboratory, Livermore, California 94550, USA.; Rubery M; Lawrence Livermore National Laboratory, Livermore, California 94550, USA.; Freeman MS; Los Alamos National Laboratory, Los Alamos, New Mexico 87545, USA. |
| Source: | The Review of scientific instruments [Rev Sci Instrum] 2024 Jun 01; Vol. 95 (6). |
| Publication Type: | Journal Article |
| Language: | English |
| Journal Info: | Publisher: American Institute Of Physics Country of Publication: United States NLM ID: 0405571 Publication Model: Print Cited Medium: Internet ISSN: 1089-7623 (Electronic) Linking ISSN: 00346748 NLM ISO Abbreviation: Rev Sci Instrum Subsets: MEDLINE; PubMed not MEDLINE |
| Imprint Name(s): | Publication: 1933- : Woodbury, N.Y. : American Institute Of Physics; Original Publication: 1930-1932 : Menasha, WI : Optical Society of America |
| Abstract: | The nuclear imaging system at the National Ignition Facility (NIF) is a crucial diagnostic for determining the geometry of inertial confinement fusion implosions. The geometry is reconstructed from a neutron aperture image via a set of reconstruction algorithms using an iterative Bayesian inference approach. An important step in these reconstruction algorithms is finding the fusion source location within the camera field-of-view. Currently, source localization is achieved via an iterative optimization algorithm. In this paper, we introduce a machine learning approach for source localization. Specifically, we train a convolutional neural network to predict source locations given a neutron aperture image. We show that this approach decreases computation time by several orders of magnitude compared to the current optimization-based source localization while achieving similar accuracy on both synthetic data and a collection of recent NIF deuterium-tritium shots.; (© 2024 Author(s). All article content, except where otherwise noted, is licensed under a Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).) |
| Entry Date(s): | Date Created: 20240618 Latest Revision: 20240618 |
| Update Code: | 20260130 |
| DOI: | 10.1063/5.0205472 |
| PMID: | 38888398 |
| Database: | MEDLINE |
Journal Article