Search NASA⌕ Search

SEARCH · Search NASA

Results for “Model Inference”

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 1,117 records · Page 62
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

A Variational Inference Approach to Inverse Problems with Gamma Hyperpriors

Hierarchical models with gamma hyperpriors provide a flexible, sparse-promoting framework to bridge L 1 and L 2 regularizations in Bayesian formulations to inverse problems. Despite the Bayesian motivation for these models, existing methodologies are limited to maximum a posteriori estimation. The potential to perform uncertainty quantification has not yet been realized. This paper introduces a variational iterative alternating scheme for hierarchical inverse problems with gamma hyperpriors. The proposed variational inference approach yields accurate reconstruction, provides meaningful uncertainty quantification, and is easy to implement. In addition, it lends itself naturally to conduct model selection for the choice of hyperparameters. Here, we illustrate the performance of our methodology in several computed examples, including a deconvolution problem and sparse identification of dynamical systems from time series data.

Bayesian shrinkage↗
NASA NTRS2013

Parameter Estimation for Compact Binary Coalescence Signals with the First Generation Gravitational-Wave Detector Network

Compact binary systems with neutron stars or black holes are one of the most promising sources for ground-based gravitational-wave detectors. Gravitational radiation encodes rich information about source physics; thus parameter estimation and model selection are crucial analysis steps for any detection candidate events. Detailed models of the anticipated waveforms enable inference on several parameters, such as component masses, spins, sky location and distance, that are essential for new astrophysical studies of these sources. However, accurate measurements of these parameters and discrimination of models describing the underlying physics are complicated by artifacts in the data, uncertainties in the waveform models and in the calibration of the detectors. Here we report such measurements on a selection of simulated signals added either in hardware or software to the data collected by the two LIGO instruments and the Virgo detector during their most recent joint science run, including a blind injection where the signal was not initially revealed to the collaboration. We exemplify the ability to extract information about the source physics on signals that cover the neutron-star and black-hole binary parameter space over the component mass range 1M25M and the full range of spin parameters. The cases reported in this study provide a snapshot of the status of parameter estimation in preparation for the operation of advanced detectors.

Aasi, J.↗
DOE OSTI2025

wa-hls4ml and lui-gnn: A benchmark and GNN-based surrogate model for hls4ml resource and latency estimation

As machine learning (ML) increasingly serves as a tool for addressing real-time challenges in scientific applications, the development of advanced tooling has significantly reduced the time required to iterate on various designs. These advancements have solved major obstacles, but also exposed new challenges. For example, processes that were not previously considered bottlenecks, such as model synthesis, are now becoming limiting factors in the rapid iteration of designs. To reduce these emerging constraints, multiple efforts are being launched toward designing an ML-based surrogate model that estimates resource usage of synthesized accelerator architectures. This model would reduce the design iteration time, especially when designing within a set of given hardware constraints. This approach shows considerable potential, but as it stands, the effort is early and would benefit from coordination and standardization to assist future work as it emerges. We introduce wa-hls4ml, a benchmark for ML accelerator resource and latency estimation, and its corresponding initial dataset of more than 100,000 fully connected neural networks, all synthesized using hls4ml and targeting Xilinx FPGAs. In addition to the resource utilization and latency data provided, the dataset includes generated artifacts and log files for many of the synthesized neural networks, in order to support future research in ML-based code generation. The benchmark evaluates the performance of resource and latency predictors against several common ML model architectures, primarily originating from scientific domains, as exemplar models, as well as the average performance across a subset of the dataset. We measure the performance of a given predictor model through multiple metrics, including $R^2$ score and SMAPE on regression tasks, as well as inference time to further characterize the estimator under test. Additionally, we introduce the latency/utilization inference graph neural network (lui-gnn), a surrogate model that uses a graph neural network to represent input architectures in the form of a directed graph. This graph representation allows for a diverse set of model architectures to all be effectively handled by a surrogate model. We present the architecture and performance of the model, as evaluated by the new proposed benchmark, including SMAPE, $R^2$ score, and inference times, and find that lui-gnn generally predicts latency and utilization for the 75\% quantile within several percent of the synthesized resources on the synthetic test dataset, indicating that this approach of estimating resource and latency via a surrogate models has promise and warrants further research.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
NASA NTRS2008

Electron Precipitation Parameters and Ionospheric Conductances Inferred from Auroral Images Acquired by the Visible Imaging Systems (VIS) on the Polar Spacecraft

The Visible Imaging System (VIS) on the polar spacecraft provided time sequences of auroral images at multiple wavelengths that yield information of auroral dynamics on a global scale with a spatial resolution of - 20 km and temporal resolution of approx. 1 minute. Time sequences of VIS images in which the aurora was highly dynamic are used to infer global maps for the electron precipitation parameters, energy flux and characteristic energies, and ionospheric conductances. The maps are inferred from the corresponding VIS images using an auroral model (Lumerzheim et al., 1987). The temporal and spatial resolution of the VIS inferred patterns are unprecedented. The inferred patterns are highly structured and vary significantly on a time scale of less than 5 minutes. These patterns can be very beneficial for global physics-based numerical models for the high-latitude ionosphere which previously had to rely on statistical models for the electron precipitation and ionospheric conductance.

Sigwarth, John B.↗
DOE OSTI2020

Radiation Source Localization Using Surrogate Models Constructed from 3-D Monte Carlo Transport Physics Simulations

Recent research has focused on the development of surrogate models for radiation source localization in a simulated urban domain. We employ the Monte Carlo N-Particle (MCNP) code to provide high- delity simulations of radiation transport within an urban domain. The model is constructed to employ a source location (x, y, z) as input and return the estimated count rate for a set of speci ed detector locations. Because MCNP simulations are computationally expensive, we develop e cient and accurate surrogate models of the detector responses. We construct surrogate models using Gaussian processes (GP) and neural networks (NN) that we train and verify using the MCNP simulations. The trained surrogate models provide an e cient framework for Bayesian inference and experimental design. We employ Delayed Rejection Adaptive Metropolis (DRAM), a Markov Chain Monte Carlo (MCMC) algorithm, to infer the location and intensity of an unknown source. The DRAM results yield a posterior probability distribution for the source's location conditioned on the observed detector count rates. The posterior distribution exhibits regions of high and low probability within the simulated environment identifying potential source locations. In this manner, we can quantify the source location to within at least one of these regions of high probability in the considered cases. Employing these methods, we are able to reduce the space of potential source locations by at least 60%.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2023

Measuring the giant radio galaxy length distribution with the LoTSS

Many massive galaxies launch jets from the accretion disk of their central black hole, but only ~10 3 instances are known in which the associated outflows form giant radio galaxies (GRGs, or giants): luminous structures of megaparsec extent that consist of atomic nuclei, relativistic electrons, and magnetic fields. Large samples are imperative to understanding the enigmatic growth of giants, and recent systematic searches in homogeneous surveys constitute a promising development. For the first time, it is possible to perform meaningful precision statistics with GRG lengths, but a framework to do so is missing. We measured the intrinsic GRG length distribution by combining a novel statistical framework with a LOFAR Two-metre Sky Survey (LoTSS) sample of freshly discovered giants. In turn, this allowed us to answer an array of questions on giants. For example, we can now assess how rare a 5 Mpc giant is compared with one of 1 Mpc, and how much larger – given a projected length – the corresponding intrinsic length is expected to be. Notably, we can now also infer the GRG number density in the Local Universe. We assumed the intrinsic GRG length distribution to be Paretian (i.e. of power-law form) with tail index ξ, and predicted the observed distribution by modelling projection and selection effects. To infer ξ, we also systematically searched the LoTSS for hitherto unknown giants and compiled the largest catalogue of giants to date. We show that if intrinsic GRG lengths are Pareto distributed with index ξ, then projected GRG lengths are also Pareto distributed with index ξ. Selection effects induce curvature in the observed projected GRG length distribution: angular length selection flattens it towards the lower end, while surface brightness selection steepens it towards the higher end. We explicitly derived a GRG’s posterior over intrinsic lengths given its projected length, laying bare the ξ dependence. We also discovered 2060 giants within LoTSS DR2 pipeline products; our sample more than doubles the known population. Spectacular discoveries include the largest, second-largest, and fourth-largest GRG known (l p = 5.1 Mpc, l p = 5.0 Mpc, and l p = 4.8 Mpc), the largest GRG known hosted by a spiral galaxy (l p = 2.5 Mpc), and the largest secure GRG known beyond redshift 1 (l p = 3.9 Mpc). We increase the number of known giants whose angular length exceeds that of the Moon from 10 to 23; among the discoveries is the angularly largest known radio galaxy in the Northern Sky, which is also the angularly largest known GRG ($\phi$ = 2°). Combining theory and data, we determined that intrinsic GRG lengths are well described by a Pareto distribution, and measured the index ξ = –3.5 ± 0.5. This implies that, given its projected length, a GRG’s intrinsic length is expected to be just 15% larger. Finally, we determined the comoving number density of giants in the Local Universe to be n GRG = 5 ± 2(100 Mpc) –3 . We developed a practical mathematical framework that elucidates the statistics of giant radio galaxy lengths. Through a LoTSS search, we also discovered 2060 new giants. By combining both advances, we determined that intrinsic GRG lengths are well described by a Pareto distribution with index ξ = –3.5 ± 0.5, and that giants are truly rare in a cosmological sense: most clusters and filaments of the Cosmic Web are not currently home to a giant. Thus, our work yields new observational constraints for analytical models and simulations featuring radio galaxy growth.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

A Bayesian Approach to the Eagar–Tsai Model for Melt Pool Geometry Prediction with Implications in Additive Manufacturing of Metals

Here, this paper focuses on improving the melt pool geometry predictions and quantifying uncertainties using an adapted version of the Eagar–Tsai (E–T) model that incorporates temperature-dependent properties of the material as well as powder conditions. Additionally, Bayesian inference is employed to predict distributions for the E–T model input parameters of laser absorptivity and powder bed porosity by incorporating experimental results into the analysis. Monte Carlo uncertainty propagation is then used with these parameter distributions to estimate the melt pool depth and associated uncertainty. Our results for the 316L stainless steel suggest that both the absorptivity and powder bed porosity are strongly influenced by the laser power. In contrast, the scanning speed has only a marginal effect on both the absorptivity and powder bed porosity. We constructed a printability map using the Bayesian E–T model based on power-dependent input parameter values to demonstrate the merit of the approach. The Bayesian approach improved the accuracy in predicting the keyhole regions in the laser power-scan speed parameter space for the 316L stainless steel. Although applied to a specific adaptation of the E–T model, the method put forth can be extended to quantify uncertainties in other numerical models as well as in the estimation of unknown parameters.

316L Stainless Steel (SS).↗
NASA NTRS1984

Models of auroral-zone conductances

The magnetosphere-ionosphere system is strongly coupled, with magnetospheric Birkeland currents feeding ionospheric Pedersen and Hall currents. Central to any computer simulation of this system is a detailed, valid conductivity model. An accurate conductivity model is also vital in order to infer Birkeland currents and electric field patterns from inversions of magnetometer chain data. Several recent attempts at constructing conductivity models are presented and their strengths and weaknesses discussed. Incoherent scatter radar measurements can determine height profiles of electron content, from which Pedersen and Hall conductances may be calculated. These yield excellent spatial and good temporal resolution; however, they are limited in field of view. A global pattern requires either 24 hours of data or a chain of stations. Synoptic empirical models (quantized by indices such as Kp or AE) typically are limited by their large bin size (1 deg invariant latitude x 1 hour MLT), and cannot reproduce arcs. Estimating conductivity globally from Dynamics Explorer auroral images is promising, and can yield reasonable time scales (of about 10 minutes); however, this procedure is still only now being tested.

Reiff, P. H.↗
NASA NTRS2006

Theory of Radiation Transfer in Neutron Star Atmospheres

The possibility for direct investigation of thermal emission from isolated neutron stars opened about a quarter of century ago with the launch of the first X-ray observatories Einstein and EXOSAT stimulated developing models of the neutron star surface radiation which began at the end of 80's. Confronting observational data with theoretical models of thermal emission allows one to infer the surface temperatures, magnetic fields, chemical composition, and neutron star masses and radii. This information, supplemented with the model equations of state and neutron star cooling models, provides an opportunity to understand the fundamental properties of the superdense matter in the stars' interiors. Almost all available models are based on the assumption that thermal radiation emitted by a neutron star is formed in the superficial star's layers--atmosphere. The neutron star atmospheres are very different from those of usual stars due to the immense gravity and huge magnetic fields. In this presentation we review the current status of the neutron star atmosphere modeling, present most important results, discuss problems and possible future developments.

Zavlin, Vyacheslav↗
DOE OSTI2026

Low-latency Jet Tagging for HL-LHC Using Transformer Architectures

Transformers are the state-of-the-art model architectures and widely used in application areas of machine learning. However the performance of such architectures is less well explored in the ultra-low latency domains where deployment on FPGAs or ASICs is required. Such domains include the trigger and data acquisition systems of the LHC experiments. We present a transformer-based algorithm for jet tagging built with the HGQ2 framework, which is able to produce a model with heterogeneous bitwidths for fast inference on FPGAs, as required in the trigger systems at the LHC experiments. The bitwidths are acquired during training by minimizing the total bit operations as an additional parameter. By allowing a bitwidth of zero, the model is pruned in-situ during training. Using this quantization-aware approach, our algorithm achieves state-of-the-art performance while also retaining permutation invariance which is a key property for particle physics applications. Due to the strength of transformers in representation learning, our work also serves as a stepping stone for the development of a larger foundation model for trigger applications.

Laatu, Lauri [Imperial Coll., London]↗
NASA NTRS2009

Infrared and X-Ray Spectroscopy of the KES 75 Supernova Remnant Shell: Characterizing the Dust and Gas Properties

We present deep Chandra observations and Spitzer Space Telescope infrared (IR) spectroscopy of the shell in the composite supernova remnant (SNR) Kes 75 (G29.7-0.3). The remnant is composed of a central pulsar wind nebula and a bright partial shell in the south that is visible at radio, IR, and X-ray wavelengths. The X-ray emission can be modeled by either a single thermal component with a temperature of ~ 1.5 keV, or with two thermal components with temperatures of 1.5 and 0.2 keV. Previous studies suggest that the hot component may originate from reverse-shocked SN ejecta. However, our new analysis shows no definitive evidence for enhanced abundances of Si, S, Ar, Mg, and Fe, as expected from supernova (SN) ejecta, or for the IR spectral signatures characteristic of confirmed SN condensed dust, thus favoring a circumstellar or interstellar origin for the X-ray and IR emission. The X-ray and ill emission in the shell are spatially correlated, suggesting that the dust particles are collisionally heated by the X-ray emitting gas. The IR spectrum of the shell is dominated by continuum emission from dust with little, or no line emission. Modeling the IR spectrum shows that the dust is heated to a temperature of ~ 140 K by a relatively dense, hot plasma, that also gives rise to the hot X-ray emission component. The density inferred from the IR emission is significantly higher than the density inferred from the X-ray models, suggesting a low filling factor for this X-ray emitting gas. The total mass of the warm dust component is at least 1.3 x 10(exp -2) solar mass, assuming no significant dust destruction has occurred in the shell. The IR data also reveal the presence of an additional plasma component with a cooler temperature, consistent with the 0.2 keV gas component. Our IR analysis therefore provides an independent verification of the cooler component of the X-ray emission. The complementary analyses of the X-ray and IR emission provide quantitative estimates of density and filling factors of the clumpy medium swept up by the SNR.

Temim, Tea↗
NASA NTRS1984

Mesospheric H2O and H2O2 densities inferred from in situ positive ion composition measurement

A model for production and loss of oxonium ions in the high-latitude D-region is developed, based on the observed excess of 34(+) which has been interpreted as H2O2(+). The loss mechanism suggested in the study is the attachment of N2 and/or CO2 in three-body reactions. Furthermore, mesospheric water vapor and H2O2 densities are inferred from measurements of four high-latitude ion compositions, based on the oxonium model. Mixing ratios of hydrogen peroxide of up to two orders of magnitude higher than previous values were obtained. A number of reactions, reaction constants, and a block diagram of the oxonium ion chemistry in the D-region are given.

Kopp, E.↗
NASA NTRS2011

Infrared and X-Ray Spectroscopy of the Kes 75 Supernova Remnant Shell: Characterizing the Dust and Gas Properties

We present deep Chandra observations and Spitzer Space Telescope infrared (IR) spectroscopy of the shell in the composite supernova remnant (SNR) Kes 75 (G29.7-0.3). The remnant is composed of a central pulsar wind nebula and a bright partial shell in the south that is visible at radio, IR, and X-ray wavelengths. The X-ray emission can be modeled by either a single thermal component with a temperature of approximately 1.5 keY, or with two thermal components with temperatures of 1.5 and 0.2 keY. Previous studies suggest that the hot component may originate from reverse-shocked supernova (SN) ejecta. However, our new analysis shows no definitive evidence for enhanced abundances of Si, S, Ar, Mg, and Fe, as expected from SN ejecta, or for the IR spectral signatures characteristic of confirmed SN condensed dust, thus favoring a circumstellar or interstellar origin for the X-ray and IR emission. The X-ray and IR emission in the shell are spatially correlated, suggesting that the dust particles are collisionally heated by the X-ray emitting gas. The IR spectrum of the shell is dominated by continuum emission from dust with little, or no line emission. Modeling the IR spectrum shows that the dust is heated to a temperature of approximately 140 K by a relatively dense, hot plasma that also gives rise to the hot X-my emission component. The density inferred from the IR emission is significantly higher than the density inferred from the X-ray models, suggesting a low filling factor for this X-my emitting gas. The total mass of the warm dust component is at least 1.3 x 10(exp -2) x solar mass, assuming no significant dust destruction has occurred in the shell. The IR data also reveal the presence of an additional plasma component with a cooler temperature, consistent with the 0.2 keV gas component. Our IR analysis therefore provides an independent verification of the cooler component of the X-ray emission. The complementary analyses of the X-ray and IR emission provide quantitative estimates of density and filling factors of the clumpy medium swept up by the SNR.

Temim, Tea↗
NASA NTRS2012

Infrared and X-Ray Spectroscopy of the Kes 75 Supernova Shell Characterizing the Dust and Gas Properties

We present deep Chandra observations and Spitzer Space Telescope infrared (IR) spectroscopy of the shell in the composite supernova remnant (SNR) Kes 75 (G29.7-0.3). The remnant is composed of a central pulsar wind nebula and a bright partial shell in the south that is visible at radio, IR, and X-ray wavelengths. The X-ray emission can be modeled by either a single thermal component with a temperature of approx 1.5 keV, or with two thermal components with temperatures of 1.5 and 0.2 keY. Previous studies suggest that the hot component may originate from reverse-shocked SN ejecta. However, our new analysis shows no definitive evidence for enhanced abundances of Si, S, Ar, Mg, and Fe, as expected from supernova (SN) ejecta, or for the IR spectral signatures characteristic of confirmed SN condensed dust, thus favoring a circumstellar or interstellar origin for the X-ray and IR emission. The X-ray and IR emission in the shell are spatially correlated, suggesting that the dust particles are collisionally heated by the X-ray emitting gas. The IR spectrum of the shell is dominated by continuum emission from dust with little, or no line emission. Modeling the IR spectrum shows that the dust is heated to a temperature of approx 140 K by a relatively dense, hot plasma, that also gives rise to the hot X-ray emission component. The density inferred from the IR emission is significantly higher than the density inferred from the X-ray models, suggesting a low filling factor for this X-ray emitting gas. The total mass of the warm dust component is at least 1.3 x 10(exp -2) Solar Mass, assuming no significant dust destruction has occurred in the shell. The IR data also reveal the presence of an additional plasma component with a cooler temperature, consistent with the 0.2 keV gas component. Our IR analysis therefore provides an independent verification of the cooler component of the X-ray emission. The complementary analyses of the X-ray and IR emission provide quantitative estimates of density and filling factors of the clumpy medium swept up by the SNR.

Temim, Tea↗
DOE OSTI2020

Veridical data science

Building and expanding on principles of statistics, machine learning, and scientific inquiry, we propose the predictability, computability, and stability (PCS) framework for veridical data science. Our framework, composed of both a workflow and documentation, aims to provide responsible, reliable, reproducible, and transparent results across the data science life cycle. The PCS workflow uses predictability as a reality check and considers the importance of computation in data collection/storage and algorithm design. It augments predictability and computability with an overarching stability principle. Stability expands on statistical uncertainty considerations to assess how human judgment calls impact data results through data and model/algorithm perturbations. As part of the PCS workflow, we develop PCS inference procedures, namely PCS perturbation intervals and PCS hypothesis testing, to investigate the stability of data results relative to problem formulation, data cleaning, modeling decisions, and interpretations. We illustrate PCS inference through neuroscience and genomics projects of our own and others. Moreover, we demonstrate its favorable performance over existing methods in terms of receiver operating characteristic (ROC) curves in high-dimensional, sparse linear model simulations, including a wide range of misspecified models. Finally, we propose PCS documentation based on R Markdown or Jupyter Notebook, with publicly available, reproducible codes and narratives to back up human choices made throughout an analysis. The PCS workflow and documentation are demonstrated in a genomics case study available on Zenodo.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

A Markov chain Monte Carlo (MCMC) Bayesian inference approach to analyze apparent activation barriers and reaction orders from microreactor data

Statistical analysis of steady-state catalytic kinetic data is often limited by data sparsity due to the slow pace at which the data is collected. Data sparsity and limitations in statistical analysis make it difficult to differentiate between mechanistic models and catalytic sites. A Bayesian inference tool is reported for catalysis researchers to estimate error in the determination of reaction orders from steady state microreactor data. The benefits of a Bayesian inference approach are discussed, as an alternative to the more common frequentist approach. The approach incorporates prior knowledge of the system and the data collected to form an error estimate on reaction orders. We investigated the effects of three distinct data treatments—individual fitting of trials, pooled analysis, and constrained regression methods—on the precision and uncertainty of reaction order determinations. To assess the robustness of our findings, we conducted sensitivity analyses to evaluate the influence of Bayesian parameters on uncertainty estimation. Additionally, we utilized synthetic data to illustrate how data quality impacts the precision of uncertainty assessments. We show Bayesian analysis can obtain a more precise estimation of error with a sparse data set than a frequentist analysis. Finally, this work provides strong evidence that the adoption of Bayesian analysis of kinetic data may help researchers make more precise arguments as to the strength of their evidence for a particular mechanistic hypothesis, or in comparing across different catalysts.

42 ENGINEERING↗
DOE OSTI2018

Notos - a galaxy tool to analyze CpN observed expected ratios for inferring DNA methylation types

Background: DNA methylation patterns store epigenetic information in the vast majority of eukaryotic species. The relatively high costs and technical challenges associated with the detection of DNA methylation however have created a bias in the number of methylation studies towards model organisms. Consequently, it remains challenging to infer kingdom-wide general rules about the functions and evolutionary conservation of DNA methylation. Methylated cytosine is often found in specific CpN dinucleotides, and the frequency distributions of, for instance, CpG observed/expected (CpG o/e) ratios have been used to infer DNA methylation types based on higher mutability of methylated CpG. Results: Predominantly model-based approaches essentially founded on mixtures of Gaussian distributions are currently used to investigate questions related to the number and position of modes of CpG o/e ratios. These approaches require the selection of an appropriate criterion for determining the best model and will fail if empirical distributions are complex or even merely moderately skewed. We use a kernel density estimation (KDE) based technique for robust and precise characterization of complex CpN o/e distributions without a priori assumptions about the underlying distributions. Conclusions: We show that KDE delivers robust descriptions of CpN o/e distributions. For straightforward processing, we have developed a Galaxy tool, called Notos and available at the ToolShed, that calculates these ratios of input FASTA files and fits a density to their empirical distribution. Based on the estimated density the number and shape of modes of the distribution is determined, providing a rational for the prediction of the number and the types of different methylation classes. Notos is written in R and Perl.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2019

Parameter inference with deep jointly informed neural networks

Abstract A common challenge in modeling inertial confinement fusion (ICF) experiments with computer simulations is that many of the simulation inputs are unknown and cannot be directly measured. Often, parameters that are measured in the experiment are used to infer the unknown inputs by solving the inverse problem: finding the set of simulation inputs that result in outputs consistent with the experimental observations. In ICF, this process is often referred to as a “post‐shot analysis.” Post‐shot analyses are challenging as the inverse problem is often highly degenerate, the input parameter space is vast, and simulations are computationally expensive. In this work, deep neural network models equipped with model uncertainty estimates are used to train inverse models, which map directly from output to input space, to find the distribution of post‐shot simulations that are consistent with experimental observations. The inverse model approach is compared to Markov chain Monte Carlo (MCMC) sampling of the forward model, which maps from input to output space, for parameter inference tasks of varying complexity. The inverse models perform best when searching vast parameter spaces for post‐shot simulations that are consistent with a large number of observables, where MCMC sampling can be prohibitively expensive. We demonstrate how augmenting inverse models with autoencoders enable the inclusion of several dozen observables in the inverse mapping, reducing the degeneracy of the model and improving the accuracy of the post‐shot analysis.

Humbird, Kelli D.↗