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 523 records · Page 29
All sourcesNASA NTRSDOE OSTI
DOE OSTI2018

Optimizing Kernel Machines Using Deep Learning

Building highly non-linear and non-parametric models is central to several state-of-the-art machine learning systems. Kernel methods form an important class of techniques that induce a reproducing kernel Hilbert space (RKHS) for inferring non-linear models through the construction of similarity functions from data. These methods are particularly preferred in cases where the training data sizes are limited and when prior knowledge of the data similarities is available. Despite their usefulness, they are limited by the computational complexity and their inability to support end-to-end learning with a task specific objective. On the other hand, deep neural networks have become the de facto solution for end-to-end inference in several learning paradigms. In this article, we explore the idea of using deep architectures to perform kernel machine optimization, for both computational efficiency and end-to-end inferencing. To this end, we develop the DKMO (Deep Kernel Machine Optimization) framework, that creates an ensemble of dense embeddings using Nystrõm kernel approximations and utilizes deep learning to generate task-specific representations through the fusion of the embeddings. Intuitively, the filters of the network are trained to fuse information from an ensemble of linear subspaces in the RKHS. Furthermore, we introduce the kernel dropout regularization to enable improved training convergence. Finally, we extend this framework to the multiple kernel case, by coupling a global fusion layer with pre-trained deep kernel machines for each of the constituent kernels. Using case studies with limited training data, and lack of explicit feature sources, we demonstrate the effectiveness of our framework over conventional model inferencing techniques.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Reducing model error using optimized galaxy selection: weak lensing cluster mass estimation

Galaxy clusters are one of the most powerful probes to study extensions of General Relativity and the Standard Cosmological Model. Upcoming surveys like the Vera Rubin Observatory’s Legacy Survey of Space and Time are expected to revolutionise the field, by enabling the analysis of cluster samples of unprecedented size and quality. To reach this era of high-precision cluster cosmology, the mitigation of sources of systematic error is crucial. A particularly important challenge is bias in cluster mass measurements induced by the mismodelling of photometric redshift estimates of source galaxies. This work proposes a method to optimise the source sample selection in cluster weak lensing analyses drawn from wide-field survey lensing catalogs to reduce the bias on reconstructed cluster masses. We use a combinatorial optimisation scheme and methods from variational inference to select galaxies in latent space to produce a probabilistic galaxy source sample catalog for highly accurate cluster mass estimation. We show that our method reduces the critical surface mass density Σ crit relative modelling bias on the 60-70% level, while maintaining up to 90% of galaxies. We highlight that our methodology has applications beyond cluster mass estimation as an approach to jointly combine galaxy selection and model inference under sources of systematics.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2024

AEOLUS: Advances in Experimental Design, Optimal Control, and Learning for Uncertain Complex Systems

Sustained advances in the mathematics of modeling and simulation have resulted in the capability today for routine simulation of a number of large scale complex DOE-relevant systems. As remarkable as this capability for solving the so-called forward problem is, it is typically only the first step-an inner loop within an outer loop that explores the simulation model's parameter space and decision space to characterize uncertainty in the model's predictions, learn unknown model parameters from data, design the most informative experiments, determine optimal control strategies, and create optimal designs. Broadly, what unifies all of these outer loop problems is that they are, in one form or another, optimization problems over parameter/control/design space that are constrained by complex uncertain models. To fully realize the power of scientific simulation as a basis for scientific discovery, technological innovation, and rational decision-making, it is imperative to move beyond simulation to tackle the outer loop of optimization for learning from data, experimental design, and control with complex uncertain models. When the models under consideration are large-scale and complex, and when the optimization variable and uncertain parameter spaces are high (or infinite) dimensional, this constitutes a grand challenge of the highest order, and is intractable with conventional methods. To overcome these challenges, the AEOLUS Center was established to develop a unified mathematical, computational, and statistical framework for (1) Learning predictive models from complex data via Bayesian inference and optimization, and (2) Optimizing experiments, processes, and designs using the resulting uncertain models. These problems are intractable with conventional methods, for several reasons: (1) The simulation problems that govern the inner loops of the optimization problems are expensive to execute (due to severe nonlinearity, heterogeneity, multiphysics/multiscale coupling); (2) The optimization variable and uncertain parameter spaces are high dimensional, often stemming from discretizations of infinite dimensional fields such as initial conditions, sources, or material properties. We argue that the key to overcoming these challenges is to develop new mathematical, computational, and statistical methods that exploit the structure of the Bayesian inference and optimization problems mediated by their underlying complex uncertain models. This structure includes the regularity, sparsity, geometry, low intrinsic dimensionality, and multifidelity nature of the maps from uncertain parameter/optimization variable spaces to the specific objectives targeted: Bayesian inference, optimal experimental design, and optimal control design. Black box methods developed as generic tools are incapable of exploiting this structure. To be successful, we must create, integrate, and cross-fertilize ideas across multiple areas of applied math--including approximation theory, Bayesian inference, data science, experimental design, information theory, machine learning, model reduction, optimal control theory, parallel algorithms, PDE-constrained optimization, randomized algorithms, stochastic optimization, and uncertainty quantification--all while exploiting the structure of the problems at hand. With this goal in mind, we have marshaled a team of leading authorities in these areas. While the methods we develop will be broadly applicable across a wide spectrum of DOE problems in which experiments inform models and the systems those models describe must be optimized under uncertainty, we have chosen a specific area, advanced manufacturing and materials, to drive our work. AMM is characterized by complex models across multiple scales, and is a rich source of challenging problems in inference, experimental design, and optimal control, requiring multifaceted and integrated advances in applied mathematics. As such, AMM serves as an excellent vehicle to motivate and demonstrate the advances in applied mathematics developed by our center.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Quasi-Newton Variational Bayes v.3.0

SAND2024-09052O Quasi-Newton Variational Bayes (QNVB) is a training algorithm that performs high-dimensional variational inference on machine learning models. It provides mechanisms to calibrate and control model uncertainty during training. The PyTorch implementation of projective integral updates for Gaussian mean-fields supports the manuscript, "Projective Integral Updates for High-Dimensional Variational Inference." Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.

Duersch, Jed↗
DOE OSTI2024

VALIDATION, VERIFICATION, AND CALIBRATION THROUGH A CAUSAL LENS

This paper presents an alternative method based on causal inference to perform validation, verification, and calibration of simulation models. While classical validation and verification approaches focus on the identification of the associations between data elements using statistical and machine learning methods, the novel methods in this paper focus instead on the identification of causal relationships between data elements. Statistical and machine learning-based approaches are strictly data-driven, meaning that they provide quantitative comparison measures between datasets without explicitly considering the hypotheses behind them. This can lead to the erroneous conclusion that, if two data sets are close enough, then the models that generated them are similar. In addition, when experimental and simulated data differ to an extent that fails to meet the acceptance criteria, calibration techniques are used to tweak simulation model parameters to reduce the gap between the two types of data. This produces the false expectation that a simulation model will match reality. The methods presented in this paper move away from these strictly data-driven methods for validation and calibration toward more robust, model-driven methods based on causal inference. Causal inference aims to identify the possible mechanisms that might have generated data. Thus, this analysis targets the prediction of the effects when one (or more) of the identified mechanisms are altered. There are many approaches to identify, quantify and illustrate causal relationships. For the scope of this paper, directed graphs are employed as causal models. If the directed graph lacks cycles it is known as a directed acyclic graph (DAG). A node in such a graph represents an observed data element while a directed edge connecting two nodes represents a causal relationship between two variables. The developed causal methods are designed to extract causal models from simulation models and from experimental data. Causal models capture the causal relationships between data elements (e.g., simulated and experimental data). In this context, validation and verification are performed by comparing causal models. The proposed approach does not only inform system analysts on how a simulation model matches real-world data, but also identifies elements of the simulation model that should be revised when discrepancies between simulation and experimental data are observed. Through these causal methods, analysts have a means to identify the portion of the model equation(s) that are behind an edge connecting two variables. Hence, once the structural differences between causal models have been determined, model calibration can occur by changing only those model parameters that impact the identified causal relationships.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Bayes_Opt-SWMM: A Gaussian process-based Bayesian optimization tool for real-time flood modeling with SWMM

Real-time flood model plays a pivotal role in averting urban flood damage, particularly when there is minimal lead time for preparatory measures. However, urban flood modeling in real-time often contends with inherent uncertainties arising from input data uncertainty and parameter ambiguities. Here this study introduces a real-time calibration (RTC) tool called Bayes_Opt-SWMM, specifically tailored for real-time urban flood modeling and uncertainty optimization. This tool leverages the Gaussian process-based Bayesian optimization algorithm and interfaces seamlessly with the Stormwater Management Model (SWMM). It integrates real-time model forcing data and flood monitoring collected through sensors and gauges which are strategically placed within critical locations of urban drainage systems. Our approach hinges on the Surrogate Model based Uncertainty Optimization (SMUO) concept, providing an avenue for enhancing real-time flood modeling. Bayes_Opt-SWMM runs the optimization process using a surrogate model called Gaussian Process emulator with two inference methods: (1) the Gaussian Process (GP) model and (2) Markov Chain Monte Carlo (MCMC) algorithm in GP model (GP_MCMC). Furthermore, three acquisition functions, namely Expected Improvement (EI), Maximum Probability of Improvement (MPI), and Lower Confidence Bound (LCB), facilitate optimal parameter fitting within the surrogate models. The efficiency of GP-based surrogate models in learning SWMM model parameters, leads to an improved uncertainty quantification and accelerated real-time flood modeling in urban areas. Overall, Bayes_Opt-SWMM emerges as a cost-effective and valuable tool for real-time flood modeling and monitoring, with significant potential for managing intelligent storm water systems in urban environments.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Bayesian inference of electron density and ion temperature profiles from neutral beam and halo Balmer- α emission at Wendelstein 7-X

By employing Bayesian inference techniques, the full electron density profile from the plasma core to the edge of Wendelstein 7-X (W7-X) is inferred solely from neutral hydrogen beam and halo Balmer- α (H α ) emission data. The halo is a cloud of neutrals forming in the vicinity of the injected neutral beam due to multiple charge exchange reactions. W7-X is equipped with several neutral hydrogen beam heating sources and an H α spectroscopy system that views these sources from different angles and penetration depths in the plasma. As the beam and halo emission form complex spectra for each spatial point that are non-linearly dependent on the plasma density profile and other parameters, a complete model from the neutral beam injection and halo formation through to the spectroscopic measurements is required. The model is used here to infer electron density profiles for a range of common W7-X plasma scenarios. The inferred profiles show good agreement with profiles determined by the Thomson scattering and interferometry diagnostics across a broad range of absolute densities without any changes to the input or fitting parameters. The time evolution of the density profile in a discharge with continuous core density peaking is successfully reconstructed, demonstrating sufficient spatial resolution to infer strongly shaped profiles. Furthermore, it is shown as a proof of concept that the model is also able to infer the main ion temperature profile using the same data set.

forward modeling↗
DOE OSTI2020

Nonlinear sparse Bayesian learning for physics-based models

This paper addresses the issue of overfitting while calibrating unknown parameters of over-parameterized physics-based models with noisy and incomplete observations. Here, a semi-analytical Bayesian framework of nonlinear sparse Bayesian learning (NSBL) is proposed to identify sparsity among model parameters during Bayesian inversion. NSBL offers significant advantages over machine learning algorithm of sparse Bayesian learning (SBL) for physics-based models, such as 1) the likelihood function or the posterior parameter distribution is not required to be Gaussian, and 2) prior parameter knowledge is incorporated into sparse learning (i.e. not all parameters are treated as questionable). NSBL employs the concept of automatic relevance determination (ARD) to facilitate sparsity among questionable parameters through parameterized prior distributions. The analytical tractability of NSBL is enabled by employing Gaussian ARD priors and by building a Gaussian mixture-model approximation of the posterior parameter distribution that excludes the contribution of ARD priors. Subsequently, type-II maximum likelihood is executed using Newton's method whereby the evidence and its gradient and Hessian information are computed in a semi-analytical fashion. We show numerically and analytically that SBL is a special case of NSBL for linear regression models. Subsequently, a linear regression example involving multimodality in both parameter posterior pdf and model evidence is considered to demonstrate the performance of NSBL in cases where SBL is inapplicable. Next, NSBL is applied to identify sparsity among the damping coefficients of a mass-spring-damper model of a shear building frame. These numerical studies demonstrate the robustness and efficiency of NSBL in alleviating overfitting during Bayesian inversion of nonlinear physics-based models.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2025

Simple analytic fusion hot spot models for fusion reaction history

The measured fusion reaction history is a combination of the temporal evolution of the fusion hot spot temperature, mass, and volume. Depending on the mechanism of evolution in inertial confinement fusion implosions—shocks, compression, convergence, mass ablation, ignition—the evolution of the reaction history varies. Here, we derive and catalog a set of simplified inertial confinement fusion hot spot models with analytic solutions to infer the evolution of the fusion reaction history for each mechanism. The models give valuable insight into the meaning and cause of fusion reaction history and nuclear burnwidth measurements.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2023

End-to-end AI framework for interpretable prediction of molecular and crystal properties

We introduce an end-to-end computational framework that allows for hyperparameter optimization using the DeepHyper library, accelerated model training, and interpretable AI inference. The framework is based on state-of-the-art AI models including CGCNN, PhysNet, SchNet, MPNN, MPNN-transformer, and TorchMD-NET. We employ these AI models along with the benchmark QM9, hMOF, and MD17 datasets to showcase how the models can predict user-specified material properties within modern computing environments. We demonstrate transferable applications in the modeling of small molecules, inorganic crystals and nanoporous metal organic frameworks with a unified, standalone framework. We have deployed and tested this framework in the ThetaGPU supercomputer at the Argonne Leadership Computing Facility, and in the Delta supercomputer at the National Center for Supercomputing Applications to provide researchers with modern tools to conduct accelerated AI-driven discovery in leadership-class computing environments. We release these digital assets as open source scientific software in GitLab, and ready-to-use Jupyter notebooks in Google Colab.

36 MATERIALS SCIENCE↗
DOE OSTI2023

The Effect of Embedded Nanoparticles on the Phonon Spectrum of Ice: An Inelastic X-ray Scattering Study

As a contribution to the ongoing effort toward high-frequency sound manipulation in composite materials, we use Inelastic X-ray Scattering to probe the phonon spectrum of ice, either in a pure form or with a sparse amount of nanoparticles embedded in it. The study aims at elucidating the ability of nanocolloids to condition the collective atomic vibrations of the surrounding environment. We observe that a nanoparticle concentration of about 1 % in volume is sufficient to visibly affect the phonon spectrum of the icy substrate, mainly canceling its optical modes and adding nanoparticle phonon excitations to it. We highlight this phenomenon thanks to the lineshape modeling based on a Bayesian inference, which enables us to capture the finest detail of the scattering signal. The results of this study can empower new routes toward the shaping of sound propagation in materials through the control of their structural heterogeneity.

77 NANOSCIENCE AND NANOTECHNOLOGY↗
DOE OSTI2018

Survey of Multifidelity Methods in Uncertainty Propagation, Inference, and Optimization

In many situations across computational science and engineering, multiple computational models are available that describe a system of interest. These different models have varying evaluation costs and varying fidelities. Typically, a computationally expensive high-fidelity model describes the system with the accuracy required by the current application at hand, while lower-fidelity models are less accurate but computationally cheaper than the high-fidelity model. Outer-loop applications, such as optimization, inference, and uncertainty quantification, require multiple model evaluations at many different inputs, which often leads to computational demands that exceed available resources if only the high-fidelity model is used. This work surveys multifidelity methods that accelerate the solution of outer-loop applications by combining high-fidelity and low-fidelity model evaluations, where the low-fidelity evaluations arise from an explicit low-fidelity model (e.g., a simplified physics approximation, a reduced model, a data-fit surrogate) that approximates the same output quantity as the high-fidelity model. The overall premise of these multifidelity methods is that low-fidelity models are leveraged for speedup while the high-fidelity model is kept in the loop to establish accuracy and/or convergence guarantees. We categorize multifidelity methods according to three classes of strategies: adaptation, fusion, and filtering. The paper reviews multifidelity methods in the outer-loop contexts of uncertainty propagation, inference, and optimization.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2017

Do You See What I See? Exploring the Consequences of Luminosity Limits in Black Hole–Galaxy Evolution Studies

In studies of the connection between active galactic nuclei (AGNs) and their host galaxies, there is widespread disagreement on some key aspects of the connection. These disagreements largely stem from a lack of understanding of the nature of the full underlying AGN population. Recent attempts to probe this connection utilize both observations and simulations to correct for a missed population, but presently are limited by intrinsic biases and complicated models. We take a simple simulation for galaxy evolution and add a new prescription for AGN activity to connect galaxy growth to dark matter halo properties and AGN activity to star formation. We explicitly model selection effects to produce an “observed” AGN population for comparison with observations and empirically motivated models of the local universe. This allows us to bypass the difficulties inherent in models that attempt to infer the AGN population by inverting selection effects. We investigate the impact of selecting AGNs based on thresholds in luminosity or Eddington ratio on the “observed” AGN population. By limiting our model AGN sample in luminosity, we are able to recreate the observed local AGN luminosity function and specific star formation-stellar mass distribution, and show that using an Eddington ratio threshold introduces less bias into the sample by selecting the full range of growing black holes, despite the challenge of selecting low-mass black holes. We find that selecting AGNs using these various thresholds yield samples with different AGN host galaxy properties.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

Multiscale Reactive Model for 1,3,5-Triamino-2,4,6-trinitrobenzene Inferred by Reactive MD Simulations and Unsupervised Learning

When high-energy-density materials are subjected to thermal or mechanical insults at extreme conditions (shock loading), a coupled response between the thermo-mechanical and chemical behaviors is systematically induced. Herein we develop a reaction model for the fast chemistry of 1,3,5-triamino-2,4,6-trinitrobenzene (TATB) at the mesoscopic scale, where the chemical behavior is determined by underlying microscopic reactive simulations. The slow carbon cluster formation is not discussed in the present work. All-atom reactive molecular dynamics (MD) simulations are performed with the ReaxFF potential, and a reduced-order chemical kinetics model for TATB is fitted to isothermal and adiabatic simulations of single crystal chemical decomposition. Unsupervised machine learning techniques based on non-negative matrix factorization are applied to MD trajectories to model the decomposition kinetics of TATB in terms of a four-component model. The associated heats of reaction are fit to the temperature evolution from adiabatic decomposition trajectories. Using a chemical species analysis, we show that non-negative matrix factorization captures the main chemical decomposition steps of TATB and provides an accurate estimation of their evolution with temperature. The final analytical formulation, coupled to a diffusion term, is incorporated into a continuum formalism, and simulation results are compared one-to-one against MD simulations of 1D reaction propagation along different crystallographic directions and with different initial temperatures. A good agreement is found for both the temporal and spatial evolution of the temperature field.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

PyApprox: A software package for sensitivity analysis, Bayesian inference, optimal experimental design, and multi-fidelity uncertainty quantification and surrogate modeling

PyApprox is a Python-based one-stop-shop for probabilistic analysis of numerical models such as those used in the earth, environmental and engineering sciences. Easy to use and extendable tools are provided for constructing surrogates, sensitivity analysis, Bayesian inference, experimental design, and forward uncertainty quantification. The algorithms implemented represent a wide range of methods for model analysis developed over the past two decades, including recent advances in multi-fidelity approaches that use multiple model discretizations and/or simplified physics to significantly reduce the computational cost of various types of analyses. An extensive set of Benchmarks from the literature is also provided to facilitate the easy comparison of new or existing algorithms for a wide range of model analyses. Here, this paper introduces PyApprox and its various features, and presents results demonstrating the utility of PyApprox on a benchmark problem modeling the advection of a tracer in groundwater.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Fusion RF Modeling Machine Learning (FusionML_RF) v1.0

FusionML_RF consists of multiple codes and trained machine learning (ML) models that perform low-cost output modeling from the Genray-CQL3D. Three machine learning techniques (multilayer perceptron, random forest, and Gaussian process) provide fast surrogate models for lower hybrid current drive (LHCD) simulations. For example, completing a single GENRAY/CQL3D simulation without radial diffusion of fast electrons requires several minutes of wall-clock time. On the other hand, these ML models achieve ~ms of inference time with high accuracy across the input parameter space. This software collection consists of multiple components. (1) codes that use ML methods and precomputed Genray-CQL3D simulation output to build regression models that enable approximate computations of Genray-CLQ3D outputs from arbitrary but physically meaningful input parameters (surrogate modeling); (2) three trained models created by the team, using a database of 16,000+ GENRAY/CQL3D simulations, to study the performance of ML models for surrogate modeling; (3) codes that load the trained models and simulation data, and then compute mean squared error between the models' predictions and the ground truth of simulation output data. This collection is being made available in conjunction with a scientific publication about the work to promote reusability and provide an artifact of the scientific work.

Bai, Zhe↗
DOE OSTI2024

A parametric model for self-interacting dark matter halos

Abstract We propose a parametric model for studying self-interacting dark matter (SIDM) halos. The model uses an analytical density profile, calibrated using a controlled N-body SIDM simulation that covers the entire gravothermal evolution, including core-forming and -collapsing phases. By normalizing the calibrated density profile, we obtain a universal description for SIDM halos at any evolution phase. The model allows us to infer properties of SIDM halos based on their cold dark matter (CDM) counterparts. As a basic application, we only require two characteristic parameters of an isolated CDM halo atz = 0. We then extend the model to incorporate effects induced by halo mass changes, such as major mergers or tidal stripping, making it applicable to both isolated halos and subhalos. The parametric model is tested and validated using cosmological zoom-in SIDM simulations available in the literature.

Astronomy & Astrophysics↗
DOE OSTI2022

KilonovaNet : Surrogate models of kilonova spectra with conditional variational autoencoders

ABSTRACT Detailed radiative transfer simulations of kilonova spectra play an essential role in multimessenger astrophysics. Using the simulation results in parameter inference studies requires building a surrogate model from the simulation outputs to use in algorithms requiring sampling. In this work, we present kilonovanet, an implementation of conditional variational autoencoders (cVAEs) for the construction of surrogate models of kilonova spectra. This method can be trained on spectra directly, removing overhead time of pre-processing spectra, and greatly speeds up parameter inference time. We build surrogate models of three state-of-the-art kilonova simulation data sets and present in-depth surrogate error evaluation methods, which can in general be applied to any surrogate construction method. By creating synthetic photometric observations from the spectral surrogate, we perform parameter inference for the observed light-curve data of GW170817 and compare the results with previous analyses. Given the speed with which kilonovanet performs during parameter inference, it will serve as a useful tool in future gravitational wave observing runs to quickly analyse potential kilonova candidates.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗