Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Bayesian modeling”

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 883 records · Page 49
All sourcesNASA NTRSDOE OSTI
NASA NTRS2023

Efficient Calibration of Expensive Computational Models

Accounting for uncertainty when calibrating expensive computational models is a common challenge faced by scientists and engineers. Often Bayesian techniques are adopted to estimate a probability density function over the model parameters given noisy empirical data. The methods used to perform this type of probabilistic calibration are computationally prohibitive in that they require a large number of evaluations of the expensive model. In these cases, surrogate modeling -- that is, using a fast-to-evaluate, lower fidelity stand-in for the original computational model -- may be the only option to alleviate this computational burden. However, the upfront cost of generating training data to build a surrogate model can itself be expensive. As such, it is important to be judicious when selecting training points at which the full-fidelity model is evaluated. Here, an active learning approach is proposed that enables efficient selection of training points using approximate samples of the calibrated parameter probability density function. In this way, the training points can be concentrated in regions where the calibration algorithm requires high model accuracy.

active learning↗
DOE OSTI2024

A Bayesian Multi-fidelity Neural Network to Predict Nonlinear Frequency Backbone Curves

The use of structural mechanics models during the design process often leads to the development of models of varying fidelity. Often low-fidelity models are efficient to simulate but lack accuracy, while the high-fidelity counterparts are accurate with less efficiency. Here, this paper presents a multi-fidelity surrogate modeling approach that combines the accuracy of a high-fidelity finite element model with the efficiency of a low-fidelity model to train an even faster surrogate model that parameterizes the design space of interest. The objective of these models is to predict the nonlinear frequency backbone curves of the Tribomechadynamics Research Challenge benchmark structure which exhibits simultaneous nonlinearities from frictional contact and geometric nonlinearity. The surrogate model consists of an ensemble of neural networks that learn the mapping between low and high-fidelity data through nonlinear transformations. Bayesian neural networks are used to assess the surrogate model's uncertainty. Once trained, the multi-fidelity neural network is used to perform sensitivity analysis to assess the influence of the design parameters on the predicted backbone curves. Additionally, Bayesian calibration is performed to update the input parameter distributions to correlate the model parameters to the collection of experimentally measured backbone curves.

42 ENGINEERING↗
DOE OSTI2025

Dynamical Sketching for Enhanced Communication Efficiency in Federated Learning

Federated learning (FL) has revolutionized distributed machine learning by enabling collaborative model training without sharing local data. However, communication efficiency and privacy guarantees remain significant challenges. This paper introduces a dynamic sketching mechanism in FL, optimizing the trade-off between communication efficiency and model accuracy. By dynamically selecting the sketch matrix size, our approach adapts to the evolving characteristics of the data and the model, ensuring optimal performance across diverse scenarios. We leverage Bayesian optimization to systematically tune the sketch parameters, achieving an effective balance between resource efficiency and model performance. Experimental results on the MNIST dataset using a convolutional neural network (CNN) architecture validate the proposed method's efficiency and scalability. Our dynamic sketching approach significantly outperforms fixed-size sketching techniques, achieving higher compression ratios (up to 62x) and providing better privacy guarantees while maintaining high model accuracy. These findings highlight the robustness and versatility of our approach and make it a valuable solution for privacy-preserving, communication-efficient federated learning.

Afrose, Sharmin [ORNL]↗
NASA NTRS1987

A computer program for model verification of dynamic systems

Dynamic model verification is the process whereby an analytical model of a dynamic system is compared with experimental data, and then qualified for future use in predicting system response in a different dynamic environment. There are various ways to conduct model verification. The approach adopted in MOVER II employs Bayesian statistical parameter estimation. Unlike curve fitting whose objective is to minimize the difference between some analytical function and a given quantity of test data (or curve), Bayesian estimation attempts also to minimize the difference between the parameter values of that function (the model) and their initial estimates, in a least squares sense. The objectives of dynamic model verification, therefore, are to produce a model which: (1) is in agreement with test data, (2) will assist in the interpretation of test data, (3) can be used to help verify a design, (4) will reliably predict performance, and (5) in the case of space structures, facilitate dynamic control.

Chrostowski, J. D.↗
DOE OSTI2023

Optimizing training trajectories in variational autoencoders via latent Bayesian optimization approach *

Unsupervised and semi-supervised ML methods such as variational autoencoders (VAE) have become widely adopted across multiple areas of physics, chemistry, and materials sciences due to their capability in disentangling representations and ability to find latent manifolds for classification and/or regression of complex experimental data. Like other ML problems, VAEs require hyperparameter tuning, e.g. balancing the Kullback–Leibler and reconstruction terms. However, the training process and resulting manifold topology and connectivity depend not only on hyperparameters, but also their evolution during training. Because of the inefficiency of exhaustive search in a high-dimensional hyperparameter space for the expensive-to-train models, here we have explored a latent Bayesian optimization (zBO) approach for the hyperparameter trajectory optimization for the unsupervised and semi-supervised ML and demonstrated for joint-VAE with rotational invariances. We have demonstrated an application of this method for finding joint discrete and continuous rotationally invariant representations for modified national institute of standards and technology database (MNIST) and experimental data of a plasmonic nanoparticles material system. The performance of the proposed approach has been discussed extensively, where it allows for any high dimensional hyperparameter trajectory optimization of other ML models.

42 ENGINEERING↗
DOE OSTI2021

A novel probabilistic regression model for electrical peak demand estimate of commercial and manufacturing buildings

Due to the high cost of electricity in commercial and industrial sectors, demand forecast models have gained increasing attention. However, there are two unresolved issues: (1) Models are not adaptable when exposed to previously unknown data (2) The value of regression methods vs. state-of-the-art machine learning models has not been made apparent before. This study’s goal is to develop probabilistic demand estimation models. Herein, we propose a probabilistic Bayesian regression framework that can not only estimate future demands with high accuracy but also be updated once new information is available. By applying the proposed algorithm to two real-world case studies (commercial and manufacturing), we show a 40.3% and 30.8% improvement in terms of mean absolute error for the two cases. Moreover, the proposed technique outperforms powerful machine learning approaches, including support vector machine by 10.39%, random forest by 6.17%, and multilayer perceptron by 9.14% in terms of mean absolute percentage error.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2025

The decay of HIV under anti-retroviral therapy is biphasic even in humanized mice with just T cells

HIV-1 plasma viral load decays in a biphasic manner during antiretroviral therapy (ART). It was hypothesized that this is due to infection of different cell types, namely CD4+ T cells and macrophages. We studied this possibility directly by modeling the decay of HIV-1 in humanized mice. We utilized previously published data from humanized T-cell only mice (TOM) and myeloid-only mice (MOM) infected with HIV-1 and treated with a potent ART regimen. Viral load decay dynamics were modeled using either a single or a biexponential decay fitted using nonlinear mixed effects techniques. Fits were compared using the corrected Bayesian information criterion (BICc). In TOM, the biphasic model was significantly better than a single-phase decay model (ΔBICc ≈ 16) despite additional parameters. In MOM, the biphasic decay was statistically better, but there was substantial uncertainty because the virus goes below detection very fast. The first-phase half-life was consistent between groups (1.2 days in MOM and 1.3 days in TOM) and similar to the half-life estimated in human infection. The second-phase decay in these mice was minimal likely due to low initial viral loads. Additional analyses with mice containing both CD4+ T cells and macrophages or X4-tropic virus-infected MOM mice confirmed the biphasic pattern, demonstrating the robustness of this result. The biphasic decline in HIV-1 occurs, even with only CD4+ T cells, refuting the hypothesis that distinct cell populations (CD4+ T cells and macrophages) drive each decay phase. These findings support an alternative model in which the observed dynamics arise from intrinsic properties of the viral infection lifecycle rather than from cellular compartmentalization.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Stochastic Learning Approach for Binary Optimization: Application to Bayesian Optimal Design of Experiments

Here, we present a novel stochastic approach to binary optimization suited for optimal experimental design (OED) for Bayesian inverse problems governed by mathematical models such as partial differential equations. The OED utility function, namely, the regularized optimality criterion, is cast into a stochastic objective function in the form of an expectation over a multivariate Bernoulli distribution. The probabilistic objective is then solved by using a stochastic optimization routine to find an optimal observational policy. This formulation (a) is generally applicable to binary optimization problems with soft constraints and is ideal for OED and sensor placement problems; (b) does not require differentiability of the original objective function (e.g., a utility function in OED applications) with respect to the design variable, and thus it enables direct employment of sparsity-enforcing penalty functions such as $\ell_0$, without needing to utilize a continuation procedure or apply a rounding technique; (c) exhibits much lower computational cost than traditional gradient-based relaxation approaches; and (d) can be applied to both linear and nonlinear OED problems with proper choice of the utility function. The proposed approach is analyzed from an optimization perspective with detailed convergence analysis of the optimization approach and is also analyzed from a machine learning perspective with correspondence to policy gradient reinforcement learning. The approach is demonstrated numerically by using an idealized two-dimensional Bayesian linear inverse problem and validated by extensive numerical experiments carried out for sensor placement in a parameter identification setup.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Inferring the spread of COVID-19: the role of time-varying reporting rate in epidemiological modelling

The role of epidemiological models is crucial for informing public health officials during a public health emergency, such as the COVID-19 pandemic. However, traditional epidemiological models fail to capture the time-varying effects of mitigation strategies and do not account for under-reporting of active cases, thus introducing bias in the estimation of model parameters. To infer more accurate parameter estimates and to reduce the uncertainty of these estimates, we extend the SIR and SEIR epidemiological models with two time-varying parameters that capture the transmission rate and the rate at which active cases are reported to health officials. Using two real data sets of COVID-19 cases, we perform Bayesian inference via our SIR and SEIR models with time-varying transmission and reporting rates and via their standard counterparts with constant rates; our approach provides parameter estimates with more realistic interpretation, and 1-week ahead predictions with reduced uncertainty. Furthermore, we find consistent under-reporting in the number of active cases in the data that we consider, suggesting that the initial phase of the pandemic was more widespread than previously reported.

42 ENGINEERING↗
DOE OSTI2025

$\mathrm{SageNet}$: Fast Neural Network Emulation of the Stiff-amplified Gravitational Waves from Inflation

Accurate modeling of the inflationary gravitational waves (GWs) requires time-consuming, iterative numerical integrations of differential equations to take into account their backreaction on the expansion history. To improve computational efficiency while preserving accuracy, we present the Stiff-amplified Gravitational-wave Emulator Network (SageNet), a deep learning framework designed to replace conventional numerical solvers (code available at https://github.com/YifangLuo/SageNet). SageNet employs a long short-term memory architecture to emulate the present-day energy density spectrum of the inflationary GWs with possible stiff amplification, Ω GW (f). Trained on a data set of 25,689 numerically generated solutions, SageNet allows accurate reconstructions of Ω GW (f) and generalizes well to a wide range of cosmological parameters; 90.9% of the test emulations with randomly distributed parameters exhibit errors of under 4%. In addition, SageNet demonstrates its ability to learn and reproduce the artificial, adaptive sampling patterns in numerical calculations, which implement denser sampling of frequencies around changes in spectral indices in Ω GW (f). The dual capability of learning both physical and artificial features of the numerical GW spectra establishes SageNet as a robust alternative to exact numerical methods. Finally, our benchmark tests show that SageNet reduces the computation time from tens of seconds to milliseconds, achieving a speedup of ∼10 4 times over standard CPU-based numerical solvers with the potential for further acceleration on GPU hardware. These capabilities make SageNet a powerful tool for accelerating Bayesian inference procedures for extended cosmological models. In a broad sense, the SageNet framework offers a fast, accurate, and generalizable solution to modeling cosmological observables whose theoretical predictions demand costly differential equation solvers.

Astronomy data modeling↗
NASA NTRS2009

Diagnosis and Reconfiguration using Bayesian Networks: An Electrical Power System Case Study

Automated diagnosis and reconfiguration are important computational techniques that aim to minimize human intervention in autonomous systems. In this paper, we develop novel techniques and models in the context of diagnosis and reconfiguration reasoning using causal Bayesian networks (BNs). We take as starting point a successful diagnostic approach, using a static BN developed for a real-world electrical power system. We discuss in this paper the extension of this diagnostic approach along two dimensions, namely: (i) from a static BN to a dynamic BN; and (ii) from a diagnostic task to a reconfiguration task. More specifically, we discuss the auto-generation of a dynamic Bayesian network from a static Bayesian network. In addition, we discuss subtle, but important, differences between Bayesian networks when used for diagnosis versus reconfiguration. We discuss a novel reconfiguration agent, which models a system causally, including effects of actions through time, using a dynamic Bayesian network. Though the techniques we discuss are general, we demonstrate them in the context of electrical power systems (EPSs) for aircraft and spacecraft. EPSs are vital subsystems on-board aircraft and spacecraft, and many incidents and accidents of these vehicles have been attributed to EPS failures. We discuss a case study that provides initial but promising results for our approach in the setting of electrical power systems.

Knox, W. Bradley↗
DOE OSTI2022

A Micromorphic Length-Scale Coupling Framework for the Determination of Higher-Order Constitutive Models and the Multi-Scale Simulation of Heterogeneous Materials [Thesis]

Heterogeneous materials and materials with complex microstructures pose a unique challenge in the development of accurate models of their response to external stimuli. These difficulties principally arise due to the difficulty in characterizing and modeling the constituents and their interactions. It is usually possible, though non-trivial, to construct an explicit representation of the microstructure (a direct numeric simulation or DNS) but the method by which the complex modes of deformation and other processes can be homogenized to a reduced-order approximation is frequently unclear. Many homogenization approaches are ad-hoc and lack a strong justification beyond ease of computation. Furthermore, the homogenization approach can, in some cases, not utilize the full breadth of information available in the computation of the macro-scale stresses and deformation measures. It is also noteworthy that homogenization, by its very nature, will tend to obfuscate details of processes occurring at the lower length-scale. It is therefore of interest to include as much information as possible in the construction of the reduced-order model so as to be predictive in a variety of loading environments. We here present a length-scale bridging technique based upon the micromorphic continuum mechanics of Eringen which incorporates volume and surface area averages as a part of its construction. This approach enforces the balance equations at the micro-scale and then studies the effect of the spatially varying nature on the macro-scale. This leads, naturally, to further balance equations which are solved at the macro-scale. This work details a homogenization framework which arises naturally from the micromorphic construction of Eringen attempting to introduce no definitions beyond which are justifiable from micro-structural considerations. One of the results of this effort is the so-called “micromorphic filter” which has been developed and applied to several DNS to demonstrate its effectively. In order to determine the macroscopic degrees of freedom we utilize the special case of an overlap coupling technique where the macro-scale is fully constrained to the micro-scale. This enables us to study the resulting material properties as expected but also allows us to further study the boundary conditions on the additional degrees of freedom at the macro-scale.

42 ENGINEERING↗
DOE OSTI2022

Decoding Golden Eagle Movement Behavior from High-Resolution, Variable-Rate Telemetry Data Through Bayesian Filtering

The recent advances in animal tracking technology have enabled the collection of a vast amount of in situ data regarding the movement of wildlife at high spatiotemporal resolution. These data are usually available at variable time resolutions and contains noise (error) originating from GPS fixes. Decoding movement characteristics, particularly of flying animals, from telemetry data while handling these factors is a challenging yet important task for conservation purposes. Typically, this task is broken into two subtasks: resampling, and model calibration. The resampling subtask converts the variable rate positional data into a constant time interval data, while the model calibration subtask uses the resampled data to tune time-invariant parameters of the proposed models. For telemetry data at high temporal resolutions (order of 1 second), it is very challenging to decouple noise from actual movements using interpolation-based resampling techniques. Any errors introduced during resampling can significantly alter the the calibration and prediction attributes of the movement model. We address this problem through a unified Bayesian state-space framework that can handle both the resampling and calibration tasks in a single step. In addition, we use the speed and heading of the bird from telemetry data to regularize the position information of the bird. We use a Kalman filtering approach to include these nonlinearly related motion parameters within the state space framework. We cross-validated to quantify how this inclusion affects the model performance in estimating true bird movements. The relationship between the true state of the bird and environmental and topographical covariates is then represented parametrically. These parameters are then tuned using stochastic sampling strategies like Markov Chain Monte Carlo (MCMC). We use the telemetry data collected from golden eagles in the western USA to demonstrate the applicability of this approach to build a predictive, probabilistic movement model. Our preliminary results show that this approach provides improved predictive performance in terms of capturing higher-order motion parameters such as angular and horizontal accelerations, which may have simpler and more direct relationships with environmental covariates than corresponding speeds. In this talk, we will demonstrate how this state-space approach benefits the prediction capabilities of a movement model in simulating golden eagle paths through a wind power plant in Wyoming given certain atmospheric conditions. The model outcomes are aimed at informing mitigation strategies that can minimize the potential for collisions of golden eagles with wind turbines.

Bayesian methods↗
DOE OSTI2025

MOOSE ProbML: Parallelizable Probabilistic Machine Learning and Uncertainty Quantification Capabilities

The Multiphysics Object Oriented Simulation Environment (MOOSE) is a widely used open- source finite element software for performing multiphysics multiscale simulations in a massively parallel fashion. Recently, the computational team at Idaho National Laboratory (INL) has implemented Probabilistic Machine Learning (ProbML) capabilities in MOOSE—in a parallelized fashion—and enable active learning with large-scale computational models for tasks such as surrogate model development, scale bridging, forward/inverse uncertainty quantification (UQ), Bayesian optimization, etc. This presentation summarizes these developments in MOOSE along with demonstrations on several real applications relevant to nuclear energy. At the fundamental level, samplers like Monte Carlo/Latin Hypercube, variance reduction, parallelized Markov Chain Monte Carlo (MCMC) support uncertainty propagation in both forward and inverse settings. These samplers can be integrated with the Gaussian processes (GP) suite in MOOSE, which offer several variants like scalar GPs, multi-output GPs, and deep GPs, to enable active learning. These GPs can be tuned using gradient-based optimization methods like Adam and its variants or gradient-free methods like the elliptical slice sampler (a variant of MCMC adept under Gaussian settings) for more complex covariance kernels or likelihoods whose gradient computations can be cumbersome. A variety of batch acquisition functions permit parallelized evaluation of the computational model and support different learning objectives with high efficiency like Bayesian inference, global surrogate development, optimization, etc. Furthermore, libtorch integration supports training, evaluation, and re-training of neural networks and other complex machine learning models in active learning settings. The impacts of these developments are shown on several real applications: (1) nuclear fuel inverse UQ and model inadequacy assessment using the Kennedy O’Hagan framework; (2) uncertainty aware surrogate modeling for additive manufacturing to predict field quantities; (3) nuclear reactor rare events analysis; and (4) complex fluid flow prediction using a global surrogate with quantified prediction uncertainty. Finally, the outlook of MOOSE ProbML is discussed for both outer-loop and inner-loop computations in the broad view to accelerate fuels and materials qualification, address gaps in knowledge and data, and assess new reactor/fuel systems.

11 - NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2022

Parameter estimation from spontaneous imbibition into volcanic tuff

Two-phase fluid flow properties underlie quantitative prediction of water and gas movement, but constraining these properties typically requires multiple time-consuming laboratory methods. The estimation of two-phase flow properties (van Genuchten parameters, porosity, and intrinsic permeability) is illustrated in cores of vitric nonwelded volcanic tuff using Bayesian parameter estimation that fits numerical models to observations from spontaneous imbibition experiments. The uniqueness and correlation of the estimated parameters is explored using different modeling assumptions and subsets of the observed data. The resulting estimation process is sensitive to both moisture retention and relative permeability functions, thereby offering a comprehensive method for constraining both functions. The data collected during this relatively simple laboratory experiment, used in conjunction with a numerical model and a global optimizer, result in a viable approach for augmenting more traditional capillary pressure data obtained from hanging water column, membrane plate extractor, or mercury intrusion methods. This method may be useful when imbibition rather than drainage parameters are sought, when larger samples (e.g., including heterogeneity or fractures) need to be tested that cannot be accommodated in more traditional methods, or when in educational laboratory settings.

58 GEOSCIENCES↗
DOE OSTI2021

Large Methane Emissions From the Pantanal During Rising Water‐Levels Revealed by Regularly Measured Lower Troposphere CH 4 Profiles

Abstract The Pantanal region of Brazil is the largest seasonally flooded tropical grassland and, according to local chamber measurements, a substantial CH 4 source. CH 4 emissions from wetlands have recently become of heightened interest because global atmospheric 13 CH 4 data indicate they may contribute to the resumption of atmospheric CH 4 growth since 2007. We have regularly measured vertical atmospheric profiles for 2 years in the center of the Pantanal with the objectives to obtain an estimate of CH 4 emissions using an atmospheric approach, and provide information about flux seasonality and its relation to controlling factors. Boundary layer‐free troposphere differences observed in the Pantanal are large compared to other wetlands. Total emissions based on a planetary boundary layer budgeting technique are 2.0–2.8 TgCH 4 yr −1 (maximum flux ∼0.4 gCH 4 m −2 d −1 ) while those based on a Bayesian inversion using an atmospheric transport model are ∼3.3 TgCH 4 yr −1 . Compared to recent estimates for Amazonia (∼41 ± 3 TgCH 4 yr −1 , maximum flux ∼0.3 gCH 4 m −2 d −1 ) these emissions are not that large. Our Pantanal data suggest a clear flux seasonality with CH 4 being released in large amounts just after water levels begin to rise again after minimum levels have been reached. CH 4 emissions decline substantially once the maximum water level has been reached. While predictions with prognostic wetland CH 4 emission models agree well with the magnitude of the fluxes, they disagree with the phasing. Our approach shows promise for detecting and understanding longer‐term trends in CH 4 emissions and the potential for future wetlands CH 4 emissions climate feedbacks.

Gloor, M.↗
DOE OSTI2023

Effect of surface defects on damage and failure of dynamically driven cylindrical shells

Here, in this work, expanding cylinder experiments are performed using a gas gun on the aluminum 6061 alloy to understand the dynamic deformation and failure behavior of this material in the presence of surface defects in the form of scratches. The experiments are then modeled with the modified Tepla (for tensile plasticity) model, which is equipped with the damage yield function of Gurson [“Continuum theory of ductile rupture by void nucleation and growth: Part I—Yield criteria and flow rules for porous ductile media,” (1977)] and Tvergaard and Needleman [Acta Metall. 32(1), 157–169 (1984)], over-stress viscosity [F. Addessio and J. Johnson, J. Appl. Phys. 74(3), 1640–1648 (1993)], and the underlying viscoplastic model of Preston et al. [J. Appl. Phys. 93(1), 211–220 (2003)] (Preston–Tonks–Wallace model) for the dense material. The Tepla model parameters were calibrated using the Bayesian approach against experimentally measured free-surface velocity data obtained from plate impact experiments on the aluminum 6061 alloy. The evolution of radial expansion and shapes of the deformed cylinder from the simulations on a pristine cylinder wall and a cylinder wall with a longitudinal surface defect shows excellent agreement with the corresponding experimental results. Finally, the role of surface defect size and cylinder wall geometry on the dynamic strength of the cylinder wall was also investigated through a series of simulations.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗