Machine learning for detection of 3D features using sparse x-ray tomographic reconstruction

3D reconstruction of an inertial-confinement fusion implosion with neural networks using multiple heterogeneous data sources

3D asymmetries are major degradation mechanisms in inertial-confinement fusion implosions at the National Ignition Facility (NIF). These asymmetries can be diagnosed and reconstructed with the neutron imaging system (NIS) on three lines of sight around the NIF target chamber. Conventional tomographic reconstructions are used to reconstruct the 3D morphology of the implosion using NIS [Volegov et al., J. Appl. Phys. 127, 083301 (2020)], but the problem is ill-posed with only three imaging lines of sight. Asymmetries can also be diagnosed with the real-time neutron activation diagnostics (RTNAD) and the neutron time-of-flight (nToF) suite. Since the NIS, RTNAD, and nToF each sample a different part of the implosion using different physical principles, we propose that it is possible to overcome the limitations of too few imaging lines of sight by performing 3D reconstructions that combine information from all three heterogeneous data sources. This work presents a new machine learning-based reconstruction technique to do just this. By using a simple physics model and group of neural networks to map 3D morphologies to data, this technique can easily account for data of multiple different types. A simple proof-of-principle is presented, demonstrating that this technique can accurately reconstruct a hot-spot shape using synthetic primary neutron images and a hot-spot velocity vector. In particular, the hot-spot's asymmetry, quantified as spherical harmonic coefficients, is reconstructed to within ±4% of the radius in 90% of test cases. In the future, this technique will be applied to actual NIS, RTNAD, and nToF data to better understand 3D asymmetries at the NIF.

Neutron penumbral image reconstruction with a convolution neural network using fast Fourier transform

In Inertial Confinement Fusion (ICF), the asymmetry of a hot spot is an important influence factor in implosion performance. Neutron penumbral imaging, which serves as an encoded-aperture imaging technique, is one of the most important diagnostic methods for detecting the shape of a hot spot. The detector image is a uniformly bright range surrounded by a penumbral area, which presents the strength distribution of hot spots. The present diagnostic modality employs an indirect imaging technique, necessitating the reconstruction process to be a pivotal aspect of the imaging protocol. The accuracy of imaging and the applicable range are significantly influenced by the reconstruction algorithm employed. We develop a neural network named Fast Fourier transform Neural Network (FFTNN) to reconstruct two-dimensional neutron emission images from the penumbral area of the detector images. The FFTNN architecture consists of 16 layers that include a FFT layer, convolution layer, fully connected layer, dropout layer, and reshape layer. Due to the limitations in experimental data, we propose a phenomenological method for describing hot spots to generate datasets for training neural networks. The reconstruction performance of the trained FFTNN is better than that of the traditional Wiener filtering and Lucy-Richardson algorithm on the simulated dataset, especially when the noise level is high as indicated by the evaluation metrics, such as mean squared error and structure similar index measure. This proposed neural network provides a new perspective, paving the way for integrating neutron imaging diagnosis into ICF.

Advanced data analysis in inertial confinement fusion and high energy density physics

Bayesian analysis enables flexible and rigorous definition of statistical model assumptions with well-characterized propagation of uncertainties and resulting inferences for single-shot, repeated, or even cross-platform data. This approach has a strong history of application to a variety of problems in physical sciences ranging from inference of particle mass from multi-source high-energy particle data to analysis of black-hole characteristics from gravitational wave observations. The recent adoption of Bayesian statistics for analysis and design of high-energy density physics (HEDP) and inertial confinement fusion (ICF) experiments has provided invaluable gains in expert understanding and experiment performance. In this Review, we discuss the basic theory and practical application of the Bayesian statistics framework. We highlight a variety of studies from the HEDP and ICF literature, demonstrating the power of this technique. Due to the computational complexity of multi-physics models needed to analyze HEDP and ICF experiments, Bayesian inference is often not computationally tractable. Two sections are devoted to a review of statistical approximations, efficient inference algorithms, and data-driven methods, such as deep-learning and dimensionality reduction, which play a significant role in enabling use of the Bayesian framework. We provide additional discussion of various applications of Bayesian and machine learning methods that appear to be sparse in the HEDP and ICF literature constituting possible next steps for the community. We conclude by highlighting community needs, the resolution of which will improve trust in data-driven methods that have proven critical for accelerating the design and discovery cycle in many application areas.