Source localization for neutron imaging systems using convolutional neural networks

• Published in: Review of scientific instruments Vol. 95; no. 6
• Main Authors: Saavedra, Gary, Geppert-Kleinrath, Verena, Danly, Chris, Durocher, Mora, Wilde, Carl, Fatherley, Valerie, Mendoza, Emily, Tafoya, Landon, Volegov, Petr, Fittinghoff, David, Rubery, Michael, Freeman, Matthew S.
• Format: Journal Article
• Language: English
• Published: United States 01.06.2024
• ISSN: 0034-6748; 1089-7623
• DOI: 10.1063/5.0205472

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.