Search NASA⌕ Search

SEARCH · Search NASA

Results for “Sparse Coding”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 181 records · Page 10
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

LA17-V-InverseRadTransportProblem-PD2Kb. Final Project Report

In the inverse radiation transport problem, a radiation signal emanating from an unknown object is used to reconstruct geometric and material parameters of the object , e.g., the mass of special nuclear material (SNM), the isotopic composition of the SNM (e.g., the enrichment of 235U), the thickness of shielding, etc. The inverse radiation transport problem is one of the most fundamental and important in the emergency response mission, and has been addressed in previous NA-22 and NA-42/84 investments by using derivative-free optimization methods. Our project was aimed at (i) consolidating previous work by applying polynomial chaos expansion (PCE) for reducing significantly the number of forward model simulations required by derivative-free optimization methods; (ii) developing a general-purpose framework and stand-alone software for solving the inverse radiation transport problem by applying a new “predictive modeling” methodology (predictive modeling of coupled multi-physics systems, PM_CMPS) which enables the fusing of experimental and computational information; and (iii) developing several benchmarks (for unscattered gamma rays) for demonstrating the quantification of non-Gaussian features (e.g., skewness and kurtosis, which characterize asymmetries and long tails) of response distributions by deterministically and efficiently propagating parameter uncertainties (covariances and higher-order moments, where available) using high-order sensitivities computed by the recently developed comprehensive adjoint sensitivity analysis methodology (C-ASAM). With regard to (i), application of PCE, the most significant accomplishment of this project was an implementation of PCE into INVERSE that significantly reduced computation time for the DiffeRential Evolution Adaptive Metropolis (DREAM) and Differential Evolution (DE) methods. For inverse transport problems with measurements of neutron leakage, neutron multiplication, and neutron-induced gamma-rays, the solution times for the DREAM and DE methods were reduced by factors of 30-300, reducing run times from hours to minutes while maintaining the same accuracy as the standard (non-PCE) DREAM and DE. Speedups were further improved by exploring sparse grid quadrature sets using the Toolkit for Adaptive Stochastic Modeling and Non-Intrusive ApproximatioN (Tasmanian) toolset. An initial exploration of sparse grids indicated that further speedups factors of 5-10 are obtainable. The implementation of PCE in INVERSE is not in a form that users can easily access. With regard to (ii), solving the inverse problem using a predictive modeling paradigm, the most significant accomplishment of this project were the derivation and implementation of adjoint-based second derivatives in neutron and photon transport theory. There are two codes that compute these derivatives. SENSPG computes them for uncollided gamma rays and SENSMG computes them for neutron leakage. SENSMG is open-source code available on github. Other significant accomplishments included a stand-alone code, MULTI-PRED, that implements the predictive modeling paradigm, along with a detailed manual. The code was implemented in the existing INVERSE code for inverse problems, but a head-to-head comparison of inverse methods was not achieved. We also derived and implemented the capability to compute sensitivities for multiplicity measurements into the SENSMG code, and this capability was used in a data assimilation application, but it was not used for solving inverse problems. With regard to (iii), developing benchmarks to demonstrate the importance of high-order sensitivity and uncertainty analysis, the most significant accomplishment of this project were two test problems that showed how important second-order sensitivities are.

07 ISOTOPE AND RADIATION SOURCES↗
DOE OSTI2023

Dimming the Lights: 2D Simulations of Deflagrations of Hybrid C/O/Ne White Dwarfs Using FLASH

The dimmest and most numerous outlier of the Type Ia supernova population, the Type Iax event, is increasingly being found in the results of observational campaigns. There is currently no single accepted model to describe these events. This 2D study explores the viability of modeling Type Iax events as a hybrid C/O/Ne white dwarf progenitor undergoing a deflagration using the multiphysics software FLASH. This hybrid was created using the stellar evolution code MESA, and its C-depleted core and mixed structure have demonstrated lower yields than traditional C/O progenitors in previous deflagration-to-detonation studies. To generate a sample, 30 “realizations” of this simulation were performed, the only difference being the shape of the initial match head used to start the deflagration. Consistent with earlier work, these realizations produce the familiar hot dense bound remnant surrounded by sparse ejecta. Our results indicate that the majority of the star remains unburned (∼70%) and bound (>90%). Our realizations produce total ejecta yields on the order of 10 −2 –10 −1 M ☉ , ejected 56 Ni yields on the order of 10 −4 –10 −2 M ☉ , and ejecta kinetic energies on the order of 10 48 –10 49 erg. Compared to yields inferred from recent observations of the dimmest Type Iax events—SN 2007qd, SN 2008ha, SN 2010ae, SN 2019gsc, SN 2019muj, SN 2020kyg, and SN 2021fcg—our simulation produces comparable 56 Ni yields but too-small total yields and kinetic energies. Reignition of the remnant is also seen in some realizations.

Hydrodynamical simulations↗
DOE OSTI2023

Accelerating Random Forest Classification on GPU and FPGA

Random Forests (RFs) are a commonly used machine learning method for classification and regression tasks spanning a variety of application domains, including bioinformatics, business analytics, and software optimization. While prior work has focused primarily on improving performance of the training of RFs, many applications, such as malware identification, cancer prediction, and banking fraud detection, require fast RF classification. In this work, we accelerate RF classification on GPU and FPGA. In order to provide efficient support for large datasets, we propose a hierarchical memory layout suitable to the GPU/FPGA memory hierarchy. We design three RF classification code variants based on that layout, and we investigate GPU- and FPGA-specific considerations for these kernels. Our experimental evaluation, performed on an Nvidia Xp GPU and on a Xilinx Alveo U250 FPGA accelerator card using publicly available datasets on the scale of millions of samples and tens of features, covers various aspects. First, we evaluate the performance benefits of our hierarchical data structure over the standard compressed sparse row (CSR) format. Second, we compare our GPU implementation with cuML, a machine learning library targeting Nvidia GPUs. Third, we explore the performance/accuracy tradeoff resulting from the use of different tree depths in the RF. Finally, we perform a comparative performance analysis of our GPU and FPGA implementations. Our evaluation shows that for high accuracy targets, our GPU implementation yields 5-9x speedup over CSR, and up to a 2x speedup over cuML.

FPGA, Xilinx FPGA, GPU, Random Forest classificati↗
DOE OSTI2022

Automated Crystal Orientation Mapping in py4DSTEM using Sparse Correlation Matching

Crystalline materials used in technological applications are often complex assemblies composed of multiple phases and differently oriented grains. Robust identification of the phases and orientation relationships from these samples is crucial, but the information extracted from the diffraction condition probed by an electron beam is often incomplete. We have developed an automated crystal orientation mapping (ACOM) procedure which uses a converged electron probe to collect diffraction patterns from multiple locations across a complex sample. We provide an algorithm to determine the orientation of each diffraction pattern based on a fast sparse correlation method. We demonstrate the speed and accuracy of our method by indexing diffraction patterns generated using both kinematical and dynamical simulations. We have also measured orientation maps from an experimental dataset consisting of a complex polycrystalline twisted helical AuAgPd nanowire. From these maps we identify twin planes between adjacent grains, which may be responsible for the twisted helical structure. All of our methods are made freely available as open source code, including tutorials which can be easily adapted to perform ACOM measurements on diffraction pattern datasets.

36 MATERIALS SCIENCE↗
DOE OSTI2016

An improved high-quality draft genome sequence of Carnobacterium inhibens subsp. inhibens strain K1T

Abstract Despite their ubiquity and their involvement in food spoilage, the genus Carnobacterium remains rather sparsely characterized at the genome level. Carnobacterium inhibens K1 T is a member of the Carnobacteriaceae family within the class Bacilli . This strain is a Gram-positive, rod-shaped bacterium isolated from the intestine of an Atlantic salmon. The present study determined the genome sequence and annotation of Carnobacterium inhibens K1 T . The genome comprised 2,748,608 bp with a G + C content of 34.85 %, which included 2621 protein-coding genes and 116 RNA genes. The strain contained five contigs corresponding to presumptive plasmids of sizes: 19,036; 24,250; 26,581; 65,272; and 65,904 bp.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2020

Reduced Models for Chemical Kinetics derived from Parallel Ensemble Simulations of Stirred Reactors

Detailed chemical kinetic models are essential to improve the predictive capability of computational fluid dynamics (CFD) simulations and to impact the development of next generation combustion technologies. However, such detailed kinetic models are beyond the reach of CFD codes due to the computational cost of transporting additional chemical degrees of freedom. Reduced order models for combustion kinetics exploit the presence of lower dimensional manifolds in the state space and require far fewer number of scalars to be transported as part of CFD simulations. In this paper, we describe the software infrastructure developed to allow large ensembles of stirred reactor configurations with detailed chemical kinetics. The canonical reactor simulations are incorporated in a workflow with sparse grid and data reduction methodologies aimed at development of reduced order models. We present results from analyzing the results of the stirred reactor calculations for syngas mixture using principal component analysis (PCA) and neural network methodologies. The results show that nonlinear autoencoder model can surpass PCA in representing the original dataset with far fewer degrees of freedom.

Zhang, Pei↗
DOE OSTI2022

Experimental Steps toward a Density Law for Chlorine-Crediting Criticality Models of Aqueous Plutonium solutions

Criticality accident prevention is an essential safety consideration for all operations involving fissionable and fissile materials. Predictive criticality calculations using advanced neutron transport codes, such as Monte Carlo N-Particle Transport (MCNP), are invaluable tools for designing and implementing operational limits. While indispensable, these tools are limited by the quality and accuracy of the inputs that the user provides to define the modeled system. Parameters such as atomic composition, shape, and material density must be accurately defined to obtain a meaningful result. In the case of material property details for a plutonium model, accurate material characterization data is sometimes sparse. Thus limitations in calculation accuracy can be reduced by improving our knowledge of material properties in the targeted fissile systems. One of the biggest remaining challenges to accurately defining fissile systems is the description of aqueous fissile solutions. Even simple properties, such as density, are not well-known for fissile solutions relevant to nuclear energy and security. Described here are initial efforts undertaken to improve criticality calculation inputs for fissile plutonium chloride solutions in water. This effort is focused on experimentally determining accurate solution characteristics for ternary plutonium chloride/hydrochloric acid/water systems, by measurement of water activity and solution density. The effect of inputting experimental densities for these solutions into MCNP criticality calculations is compared to the traditional approach of modeling an idealized (and fictitious) plutonium-water mixture. Expansion of these efforts to a working density law for aqueous plutonium chloride solutions is also discussed.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2026

Development of a Framework and Methodology for an Advanced Reactor Materials Environmental Effects Design Guide

Advanced non-light-water reactor components may operate at elevated temperature while experiencing cyclic loading, significant neutron irradiation, and exposure to reactor coolant. ASME Boiler and Pressure Vessel Code, Section III, Division 5, provides design rules for elevated-temperature service but does not include specific procedures to account for environmental effects on material properties. This report develops an initial framework and methodology for an Environmental Effects Design Guide (EEDG) focused on neutron irradiation; coolant-environment effects are reserved for future work. The proposed approach treats irradiation as a property-based overlay on the existing Division 5 design process, with two routes: a sparse-data route applying two reduction factors — FCR on creep-rupture strength and FF on fatigue life — for the creep-fatigue evaluations that typically control the design of advanced high-temperature reactor components, and a fuller framework developing the property-to-rule chain across the four Division 5 checks (primary load, strain limits and ratcheting, creep-fatigue, and buckling), together with swelling and weldments as scope items. Both routes are scoped by an in-pile qualification that restricts the use of post-irradiation-examination-derived properties in regimes where an in-pile mechanism could control the design outcome. Illustrative outputs derived on a compiled annealed Type 316 database — FCR ≈ 0.78–0.86 and FF ≈ 0.4 — demonstrate the calculation method within that specific dataset. The framework is an initial, testable design-rule concept; it identifies a practical path for preliminary design evaluations under sparse data and the material data and testing needed to develop the framework further.

Barua, Bipul (ORCID:0000000247184113)↗
DOE OSTI2021

Cognitive simulation models for inertial confinement fusion: Combining simulation and experimental data

The design space for inertial confinement fusion (ICF) experiments is vast, and experiments are extremely expensive. Researchers rely heavily on computer simulations to explore the design space in search of high-performing implosions. However, ICF multiphysics codes must make simplifying assumptions, and thus deviate from experimental measurements for complex implosions. For more effective design and investigation, simulations require input from past experimental data to better predict future performance. In this work, we describe a cognitive simulation method for combining simulation and experimental data into a common, predictive model. This method leverages a machine learning technique called “transfer learning,” the process of taking a model trained to solve one task, and partially retraining it on a sparse dataset to solve a different, but related task. In the context of ICF design, neural network models are trained on large simulation databases and partially retrained on experimental data, producing models that are far more accurate than simulations alone. Here, we demonstrate improved model performance for a range of ICF experiments at the National Ignition Facility and predict the outcome of recent experiments with less than 10% error for several key observables. We discuss how the methods might be used to carry out a data-driven experimental campaign to optimize performance, illustrating the key product—models that become increasingly accurate as data are acquired.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2017

Uncertainty and Sensitivity Analysis of TREAT Transient Test no. 15

The U.S. Department of Energy (DOE) is preparing for the resumption of transient testing using the Transient Reactor Test Facility (TREAT) located at the Idaho National Laboratory (INL). In order to support the analysis of TREAT operation and experiment planning, the MAMMOTH reactor physics team has recently begun development of uncertainty and sensitivity analysis for the TREAT core simulated via MAMMOTH. MAMMOTH is a high-fidelity three-dimensional transient multi-physics code developed at INL under the DOE-NE Advanced Modeling and Simulation program (NEAMS). This research is part of the development presenting some initial uncertainty and sensitivity analysis of TREAT Transient Test no. 15. In this summary, we employ the Sobol sampling strategy implemented in RAVEN to efficiently perform the sensitivity and uncertainty analysis. The idea is using Sobol functional decomposition with generalized polynomial chaos (gPC) expansions to estimate the responses of interest. The gPC coefficients are then computed via the sparse grid spectral projection method. In addition, this strategy includes evaluation of the second or higher order sensitivity indices, allowing the study of interactions between several input variables. The principal focus of this analysis is to quantify the uncertainties in the total power and maximum fuel temperatures with respect to uncertainties in the initial transient conditions, such as rated power, fuel temperature, graphite fuel density and control rod boron concentration. In addition, both the first order and second order time-dependent sensitivity indices are computed and analyzed. The results show that the interactions between initial control rod boron concentration and the rated power will contribute at most 1% to the total uncertainty of the power peak.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2023

The Kokkos OpenMPTarget Backend: Implementation and Lessons Learned

As the supercomputing landscape diversifies, solutions such as Kokkos to write vendor agnostic applications and libraries have risen in popularity. Kokkos provides a programming model designed for performance portability, which allows developers to write a single source implementation that can run efficiently on various architectures. At its heart, Kokkos maps parallel algorithms to architecture and vendor specific backends written in lower level programming models such as CUDA and HIP. Another approach to writing vendor agnostic parallel code is using OpenMP’s directives based approach, which lets developers annotate code to express parallelism. It is implemented at the compiler level and is supported by all major high performance computing vendors, as well as the primary Open Source toolchains GNU and LLVM. Since its inception, Kokkos has used OpenMP to parallelize on CPU architectures. In this paper, we explore leveraging OpenMP for a GPU backend and discuss the challenges we encountered when mapping the Kokkos APIs and semantics to OpenMP target constructs. As an exemplar workload we chose a simple conjugate gradient solver for sparse matrices. We find that performance on NVIDIA and AMD GPUs varies widely based on details of the implementation strategy and the chosen compiler. Furthermore, the performance of the OpenMP implementations decreases with increasing complexity of the investigated algorithms.

Gayatri, Rahulkumar↗
DOE OSTI2022

Dissecting Tensor Cores via Microbenchmarks: Latency, Throughput and Numeric Behaviors

Tensor Cores have been an important unit to accelerate Fused Matrix Multiplication Accumulation (MMA) in all NVIDIA GPUs since Volta Architecture. To program Tensor Cores, users have to use either legacy wmma APIs or current mma APIs. Legacy wmma APIs are more easy-to-use but can only exploit limited features and power of Tensor Cores. Specifically, wmma APIs support fewer operand shapes and can not leverage the new sparse matrix multiplication feature of the newest Ampere Tensor Cores. However, the performance of current programming interface has not been well explored. Furthermore, the computation numeric behaviors of low-precision floating points (TF32, BF16, and FP16) supported by the newest Ampere Tensor Cores are also mysterious. In this paper, we explore the throughput and latency of current programming APIs. Further, we intuitively study the numeric behaviors of Tensor Cores MMA and profile the intermediate operations including multiplication, addition of inner product, and accumulation. All codes used in this work can be found in https://github.com/sunlex0717/DissectingTensorCores.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2017

Uncertainty and Sensitivity Analysis of TREAT Transient Test #15

The U.S. Department of Energy (DOE) is preparing for the resumption of transient testing using the Transient Reactor Test Facility (TREAT) located at the Idaho National Laboratory (INL). In order to support the analysis of TREAT operation and experiment planning, the MAMMOTH reactor physics team has recently begun development of uncertainty and sensitivity analysis for the TREAT core simulated via MAMMOTH. MAMMOTH is a high-fidelity three-dimensional transient multi-physics code developed at INL under the DOE-NE Advanced Modeling and Simulation program (NEAMS) [1]. This research is part of the development presenting some initial uncertainty and sensitivity analysis of TREAT Transient Test #15 [2]. In this summary, we employ the Sobol sampling strategy implemented in RAVEN [3] to efficiently perform the sensitivity and uncertainty analysis. The idea is using Sobol functional decomposition with generalized polynomial chaos (gPC) expansions to estimate the responses of interest [4]. The gPC coefficients are then computed via the spectral projection method with sparse grid approach. In addition, this strategy includes evaluation of the second or higher order sensitivity indices, allowing the study of interactions between several input variables. The principal focus of this analysis is to quantify the uncertainties in the total power and maximum fuel temperatures with respect to uncertainties in the initial transient conditions, such as rated power, fuel temperature, graphite fuel density and control rod boron concentration. In addition, both the first order and second order time-dependent sensitivity indices are computed and analyzed. The results show that the interactions between initial control rod boron concentration and the rated power will contribute at most 1% to the total uncertainty of the power peak.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2019

Sparse, iterative simulation methods for one-dimensional laminar flames

Sparse, iterative simulation methods for one-dimensional laminar flames are proposed. The resulting steady and unsteady flame solvers exploit approximate Jacobians to greatly reduce the computational cost associated with matrix operations. The constant, non-unity Lewis number assumption is introduced to further reduce the computational cost. The solvers are also parallelized to reduce time-to-solution on distributed memory computer systems. Computed laminar flame speeds and species profiles for a range of chemical mechanisms (from 10 to 2878 species) are compared against a well-validated commercial code and are found to be consistent within solver tolerances. The computation times of both the unsteady and steady solutions increase only linearly with the number of species, which is a significant improvement over the quadratic or cubic scaling of existing steady-state flame solvers. For the largest mechanism tested, the steady-state flame solver is two orders of magnitude faster than commonly-used codes. The use of an approximate Jacobian is shown to reduce the rate of convergence for the steady-state solver, but does not significantly affect the domain of convergence. The steady-state solver with approximate Jacobian is thus well suited for computationally efficient laminar flame speed sweeps with large kinetic mechanisms.

42 ENGINEERING↗
DOE OSTI2023

Analysing the effects of heating and gas puffing in Proto-MPEX helicon and auxiliary heated plasmas

The Material Plasma Exposure Experiment (MPEX) is being constructed at Oak Ridge National Laboratory to investigate critical fusion reactor issues, such as plasma–material interactions (PMIs) under reactor-relevant conditions and time scales. The linear device Proto-MPEX was used as a test bed to address anticipated research and development issues associated with heating scenarios and establish the physics basis for MPEX. The SOLPS-ITER code suite has been applied to understand plasma and neutral transport in Proto-MPEX and to increase confidence in predictive simulations for MPEX. Coupling between COMSOL and SOLPS is performed to implement a 2D electron heating profile of the helicon source. The simulations show reasonable agreement with the experimental data for plasma with helicon and auxiliary electron cyclotron heating (ECH). Both Bohm and constant diffusion (D$_\perp$: 0.5 m 2 s –1 and $\chi_\perp$: 1 m 2 s –1 ) simulations show similar levels of agreement with respect to the sparse experimental data available, assuming a few per cent impurity concentration. ECH significantly increases the target electron temperature, however, the target electron density is reduced compared to helicon-only heated plasmas due to an increase in flow velocity and radial losses. The simulations show that further increasing the ECH power results in an increase in the target electron density due to increased recycling flux and ionization. The results indicate that ECH significantly enhances the target heat flux, with ECH power of 50 kW increasing the target heat flux from 0.4 to 17 MW m –2 . It is found that a small amount of gas puffing (GP) near the target plate can further increase the target heat fluxes at the higher ECH power cases, but the target heat flux is reduced at higher GP conditions due to a significant reduction in electron temperature via radiation. ECH and GP scenarios can generate a higher target flux, facilitating improved PMI studies with more reactor-relevant plasma conditions.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2017

Porting AMG2013 to Heterogeneous CPU+GPU Nodes

LLNL's future advanced technology system SIERRA will feature heterogeneous compute nodes that consist of IBM PowerV9 CPUs and NVIDIA Volta GPUs. Conceptually, the motivation for such an architecture is quite straightforward: While GPUs are optimized for throughput on massively parallel workloads, CPUs strive to minimize latency for rather sequential operations. Yet, making optimal use of heterogeneous architectures raises new challenges for the development of scalable parallel software, e.g., with respect to work distribution. Porting LLNL's parallel numerical libraries to upcoming heterogeneous CPU+GPU architectures is therefore a critical factor for ensuring LLNL's future success in ful lling its national mission. One of these libraries, called HYPRE, provides parallel solvers and precondi- tioners for large, sparse linear systems of equations. In the context of this intern- ship project, I consider AMG2013 which is a proxy application for major parts of HYPRE that implements a benchmark for setting up and solving di erent systems of linear equations. In the following, I describe in detail how I ported multiple parts of AMG2013 to the GPU (Section 2) and present results for di erent experiments that demonstrate a successful parallel implementation on the heterogeneous ma- chines surface and ray (Section 3). In Section 4, I give guidelines on how my code should be used. Finally, I conclude and give an outlook for future work (Section 5).

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

On a Simplified Approach to Achieve Parallel Performance and Portability Across CPU and GPU Architectures

This paper presents software advances to easily exploit computer architectures consisting of a multi-core CPU and CPU+GPU to accelerate diverse types of high-performance computing (HPC) applications using a single code implementation. The paper describes and demonstrates the performance of the open-source C++ matrix and array (MATAR) library that uniquely offers: (1) a straightforward syntax for programming productivity, (2) usable data structures for data-oriented programming (DOP) for performance, and (3) a simple interface to the open-source C++ Kokkos library for portability and memory management across CPUs and GPUs. The portability across architectures with a single code implementation is achieved by automatically switching between diverse fine-grained parallelism backends (e.g., CUDA, HIP, OpenMP, pthreads, etc.) at compile time. The MATAR library solves many longstanding challenges associated with easily writing software that can run in parallel on any computer architecture. This work benefits projects seeking to write new C++ codes while also addressing the challenges of quickly making existing Fortran codes performant and portable over modern computer architectures with minimal syntactical changes from Fortran to C++. We demonstrate the feasibility of readily writing new C++ codes and modernizing existing codes with MATAR to be performant, parallel, and portable across diverse computer architectures.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Physics consistent machine learning framework for inverse modeling with applications to ICF capsule implosions

In high energy density physics (HEDP) and inertial confinement fusion (ICF), predictive modeling is complicated by uncertainty in parameters that characterize various aspects of the modeled system, such as those characterizing material properties, equation of state (EOS), opacities, and initial conditions. Typically, however, these parameters are not directly observable. What is observed instead is a time sequence of radiographic projections using X-rays. In this work, we define a set of sparse hydrodynamic features derived from the outgoing shock profile and outer material edge, which can be obtained from radiographic measurements, to directly infer such parameters. Our machine learning (ML)-based methodology involves a pipeline of two architectures, a radiograph-to-features network (R2FNet) and a features-to-parameters network (F2PNet), that are trained independently and later combined to approximate a posterior distribution for the parameters from radiographs. We show that the machine learning architectures are able to accurately infer initial conditions and EOS parameters, and that the estimated parameters can be used in a hydrodynamics code to obtain density fields, shocks, and material interfaces that satisfy thermodynamic and hydrodynamic consistency. Finally, we demonstrate that features resulting from an unknown EOS model can be successfully mapped onto parameters of a chosen analytical EOS model, implying that network predictions are learning physics, with a degree of invariance to the underlying choice of EOS model. To the best of our knowledge, our framework is the first demonstration of recovering both thermodynamic and hydrodynamic consistent density fields from noisy radiographs.

97 MATHEMATICS AND COMPUTING↗