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 955 records · Page 53
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Exploring Data Set Bias and Decision Support with Predictive Uncertainty Through Bayesian Approximations and Convolutional Neural Networks

Individual seismic catalogs can contain multiscale observations from fault level to global scales and associated waveforms from discrete events reflect crustal structure across many different scales and locations. Seismic network aperture, geographic location, and observation distance may not provide informative guidance or intuition on how different catalogs will behave across models trained under different conditions. We rely on uncertainty to provide guardrails for when to trust model decisions, but understanding when our uncertainty is trustworthy is an open challenge. Here, in this work, we explore Bayesian approximation methods for assigning predictive uncertainty in seismic event classification problems. We find that computationally expensive Bayesian approximations do not outperform simple ensemble methods. We also find that when exploiting multiple seismic event catalogs, joint training with data from all the catalogs combined with Bayesian approximations and supervised training for classification can obscure bias and result in less robust uncertainty while also not providing substantial performance benefits compared to training individual models for each catalog.

58 GEOSCIENCES↗
DOE OSTI2021

A comparative study of machine learning models for predicting the state of reactive mixing

Mixing phenomena are important mechanisms controlling flow, species transport, and reaction processes in fluids and porous media. Accurate predictions of reactive mixing are critical for many Earth and environmental science problems such as contaminant fate and remediation, macroalgae growth, and plankton biomass evolution. Here, to investigate the evolution of mixing dynamics under different scenarios (e.g., anisotropy, fluctuating velocity fields), a finite-element-based numerical model was built to solve the fast, irreversible bimolecular reaction-diffusion equations to simulate a range of reactive-mixing scenarios. A total of 2,315 simulations were performed using different sets of model input parameters comprising various spatial scales of vortex structures in the velocity field, time-scales associated with velocity oscillations, the perturbation parameter for the vortex-based velocity, anisotropic dispersion contrast (i.e., ratio of longitudinal-to-transverse dispersion), and molecular diffusion. The outputs comprised concentration profiles of reactants and products. The inputs to and outputs from these simulations were concatenated into feature and label matrices, respectively, to train 20 different machine learning (ML) models intended to emulate system behavior. These 20 ML emulators, based on linear methods, Bayesian methods, ensemble learning methods, and multilayer perceptrons (MLPs), were trained to classify the state of mixing and predict three quantities of interest (QoIs) characterizing species production, decay (i.e., average concentration, square of average concentration), and degree of mixing (i.e., variances of species concentration). Unsurprisingly, linear classifiers and regressors failed to reproduce the QoIs; however, ensemble methods (classifiers and regressors) and the MLP model accurately classified the state of reactive mixing and the QoIs. Among ensemble methods, random forest and decision-tree-based AdaBoost faithfully predicted the QoIs. At run time, trained ML emulators produced results times faster than the finite-element simulations. Due to their low computational expense and high accuracy, ensemble and MLP models are excellent emulators for these numerical simulations and great utilities in uncertainty quantification exercises, which can require 1,000s of forward model runs.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Neural network ensembles and uncertainty estimation for predictions of inelastic mechanical deformation using a finite element method-neural network approach

The finite element method (FEM) is widely used to simulate a variety of physics phenomena. Approaches that integrate FEM with neural networks (NNs) are typically leveraged as an alternative to conducting expensive FEM simulations in order to reduce the computational cost without significantly sacrificing accuracy. However, these methods can produce biased predictions that deviate from those obtained with FEM, since these hybrid FEM-NN approaches rely on approximations trained using physically relevant quantities. In this work, an uncertainty estimation framework is introduced that leverages ensembles of Bayesian neural networks to produce diverse sets of predictions using a hybrid FEM-NN approach that approximates internal forces on a deforming solid body. The uncertainty estimator developed herein reliably infers upper bounds of bias/variance in the predictions for a wide range of interpolation and extrapolation cases using a three-element FEM-NN model of a bar undergoing plastic deformation. This proposed framework offers a powerful tool for assessing the reliability of physics-based surrogate models by establishing uncertainty estimates for predictions spanning a wide range of possible load cases.

42 ENGINEERING↗
DOE OSTI2021

Short-term nodal load forecasting based on machine learning techniques

This paper introduces an advanced Short-term Nodal Load Forecasting (STNLF) method that forecasts nodal load profiles for the next day in power systems, based on the combined use of three machine learning techniques. Least Absolute Shrinkage and Selection Operator (LASSO) is employed to reduce the number of features for a single nodal load forecasting. Principal Component Analysis (PCA) is used to capture the features of historical loads in low-dimensional space compared to the original high-dimensional load space where features are barely possible to depict. Additionally, Bayesian Ridge Regression (BRR) is utilized to decide the parameters of the prediction model from a statistics perspective. Tests based on modified PJM load data demonstrate the effectiveness of the proposed STNLF method compared to the state-of-the-art General Regression Neural Network (GRNN) method. Moreover, the reliability of the day-ahead Unit Commitment (UC) solution is shown to have been improved, based on the forecasted load data using the proposed STNLF method.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2021

Towards robust autonomous impedance spectroscopy analysis: A calibrated hierarchical Bayesian approach for electrochemical impedance spectroscopy (EIS) inversion

Distribution-based analyses, such as the distribution of relaxation times (DRT) and the distribution of diffusion times (DDT), present model-free alternatives to equivalent circuit modeling for analysis of electrochemical impedance spectroscopy (EIS) data. However, reconstructing such distributions from noisy impedance data is an ill-posed problem that must be solved with specialized inversion algorithms, requiring careful control and tuning. Furthermore, most inversion algorithms developed to date can only solve problems of limited complexity. Herein, we present a new hierarchical Bayesian method for EIS inversion, leveraging efficient algorithms for optimization and Hamiltonian Monte Carlo (HMC) sampling to solve models of arbitrary complexity. We overcome the challenge of ad-hoc parameter tuning by encoding intrinsic characteristics of the DRT and DDT into flexible prior distributions and “pre-calibrating” the model to simulated data. This approach is versatile, highly robust to noise, and provides quantitative estimates of both the error structure of the data and the uncertainty in the recovered distributions. The model is validated with simulated data to demonstrate accurate recovery of the DRT and the DDT. The method also shows promise for simultaneous recovery of multiple distributions, raising the intriguing possibility of semi-autonomous EIS analysis and ad-hoc model construction. Finally, the practical utility of the method is illustrated with experimental data. Throughout, we draw comparisons to several recently published EIS inversion methodologies.

36 MATERIALS SCIENCE↗
DOE OSTI2020

On-the-fly active learning of interpretable Bayesian force fields for atomistic rare events

Abstract Machine learned force fields typically require manual construction of training sets consisting of thousands of first principles calculations, which can result in low training efficiency and unpredictable errors when applied to structures not represented in the training set of the model. This severely limits the practical application of these models in systems with dynamics governed by important rare events, such as chemical reactions and diffusion. We present an adaptive Bayesian inference method for automating the training of interpretable, low-dimensional, and multi-element interatomic force fields using structures drawn on the fly from molecular dynamics simulations. Within an active learning framework, the internal uncertainty of a Gaussian process regression model is used to decide whether to accept the model prediction or to perform a first principles calculation to augment the training set of the model. The method is applied to a range of single- and multi-element systems and shown to achieve a favorable balance of accuracy and computational efficiency, while requiring a minimal amount of ab initio training data. We provide a fully open-source implementation of our method, as well as a procedure to map trained models to computationally efficient tabulated force fields.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Decision-making based on Markov decision process in integrated artificial reasoning framework—Part I: Theory

This paper presents a decision-making framework based on an integrated artificial reasoning framework and Markov decision process (MDP). The integrated artificial reasoning framework provides a physics-based approach that converts system information into state transition models, and the analysis result will be represented by the transition probabilities that can be used with an MDP to find a traceable and explainable optimal pathway. A dynamic Bayesian network (DBN) is well suited for representing the structure of an MDP. The causality information among process variables (or among subsystems) is mathematically represented in a DBN by the conditional probabilities of the node’s states provided different probabilities of the parent node’s states. To define node states in a physically understandable manner, we used multilevel flow modeling (MFM). An MFM follows the fundamental energy and mass conservation laws and supports the selection of process variables that represent the system of interest so that causal relations among process variables are properly captured. An MFM-based DBN supports developing state transition models in an MDP to capture the effect of process variables of system having physical relations. The operators of the target system can capture stochastic system dynamics as multiple subsystem state transitions based on their physical relations and uncertainties coming from component degradation or random failures. We analyzed a simplified exemplary system to illustrate an optimal operational policy using the suggested approach.

Markov decision process↗
DOE OSTI2021

Statistically-informed deep learning for gravitational wave parameter estimation

We introduce deep learning models to estimate the masses of the binary components of black hole mergers, $(m_1,m_2)$, and three astrophysical properties of the post-merger compact remnant, namely, the final spin, $a_\mathrm f$, and the frequency and damping time of the ringdown oscillations of the fundamental $\ell = m = 2$ bar mode, $(\omega_\mathrm R, \omega_\mathrm I)$. Our neural networks combine a modified WaveNet architecture with contrastive learning and normalizing flow. We validate these models against a Gaussian conjugate prior family whose posterior distribution is described by a closed analytical expression. Upon confirming that our models produce statistically consistent results, we used them to estimate the astrophysical parameters $(m_1,m_2, a_\mathrm f, \omega_\mathrm R, \omega_\mathrm I)$ of five binary black holes: GW150914, GW170104, GW170814, GW190521 and GW190630. We use PyCBC Inference to directly compare traditional Bayesian methodologies for parameter estimation with our deep learning based posterior distributions. Our results show that our neural network models predict posterior distributions that encode physical correlations, and that our data-driven median results and 90% confidence intervals are similar to those produced with gravitational wave Bayesian analyses. This methodology requires a single V100 NVIDIA GPU to produce median values and posterior distributions within two milliseconds for each event. Furthermore, this neural network, and a tutorial for its use, are available at the Data and Learning Hub for Science.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2026

Active operator learning with predictive uncertainty quantification for partial differential equations

With the increased prevalence of neural operators being used to provide rapid solutions to partial differential equations (PDEs), understanding the accuracy of model predictions and the associated error levels is necessary for deploying reliable surrogate models in scientific applications. Existing uncertainty quantification (UQ) frameworks employ ensembles or Bayesian methods, which can incur substantial computational costs during both training and inference. Here, we propose a lightweight predictive UQ method tailored for Deep operator networks (DeepONets) that also generalizes to other operator networks. Numerical experiments on linear and nonlinear PDEs demonstrate that the framework’s uncertainty estimates are unbiased and provide accurate out-of-distribution uncertainty predictions with a sufficiently large training dataset. Our framework provides fast inference and uncertainty estimates that can efficiently drive outer-loop analyses that would be prohibitively expensive with conventional solvers. We demonstrate how predictive uncertainties can be used in the context of Bayesian optimization and active learning problems to yield improvements in accuracy and data-efficiency for outer-loop optimization procedures. In the active learning setup, we extend the framework to Fourier Neural Operators (FNO) and describe a generalized method for other operator networks. To enable real-time deployment, we introduce an inference strategy based on precomputed trunk outputs and a sparse placement matrix, reducing evaluation time by more than a factor of five. Our method provides a practical route to uncertainty-aware operator learning in time-sensitive settings.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

J-PLUS: Spectral evolution of white dwarfs by PDF analysis

We estimated the spectral evolution of white dwarfs with effective temperature using the Javalambre Photometric Local Universe Survey (J-PLUS) second data release (DR2), which provides 12 photometric optical passbands over 2176 deg 2 . We analyzed 5926 white dwarfs with r ≤ 19.5 mag in common between a white dwarf catalog defined from Gaia EDR3 and J-PLUS DR2. We performed a Bayesian analysis by comparing the observed J-PLUS photometry with theoretical models of hydrogen- and helium-dominated atmospheres. We estimated the probability distribution functions for effective temperature (T eff ), surface gravity, parallax, and composition; and the probability of having a H-dominated atmosphere (p H ) for each source. We applied a prior in parallax, using Gaia EDR3 measurements as a reference, and derived a self-consistent prior for the atmospheric composition as a function of T eff . We described the fraction of white dwarfs with a He-dominated atmosphere (f He ) with a linear function of the effective temperature at 5000 < T eff < 30 000 K. We find f He = 0.24 ± 0.01 at T eff = 10 000 K, a change rate along the cooling sequence of 0.14 ± 0.02 per 10 kK, and a minimum He-dominated fraction of 0.08 ± 0.02 at the high-temperature end. We tested the obtained p H by comparison with spectroscopic classifications, finding that it is reliable. We estimated the mass distribution for the 351 sources with distance d < 100 pc, mass M > 0.45 M ⊙ , and T eff > 6000 K. The result for H-dominated white dwarfs agrees with previous studies, with a dominant M = 0.59 M ⊙ peak and the presence of an excess at M ~ 0.8 M ⊙ . This high-mass excess is absent in the He-dominated distribution, which presents a single peak. The J-PLUS optical data provide a reliable statistical classification of white dwarfs into H- and He-dominated atmospheres. We find a 21 ± 3% increase in the fraction of He-dominated white dwarfs from T eff = 20 000 K to T eff = 5000 K.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2024

A Gaussian process based surrogate approach for the optimization of cylindrical targets

Simulating direct-drive inertial confinement experiments presents significant computational challenges, both due to the complexity of the codes required for such simulations and the substantial computational expense associated with target design studies. Machine learning models, and in particular, surrogate models, offer a solution by replacing simulation results with a simplified approximation. In this study, we apply surrogate modeling and optimization techniques that are well established in the existing literature to one-dimensional simulation data of a new cylindrical target design containing deuterium–tritium fuel. These models predict yields without the need for expensive simulations. We find that Bayesian optimization with Gaussian process surrogates enhances sampling efficiency in low-dimensional design spaces but becomes less efficient as dimensionality increases. Nonetheless, optimization routines within two-dimensional and five-dimensional design spaces can identify designs that maximize yield, while also aligning with established physical intuition. Optimization routines, which ignore constraints on hydrodynamic instability growth, are shown to lead to unstable designs in 2D, resulting in yield loss. However, routines that utilize 1D simulations and impose constraints on the in-flight aspect ratio converge on novel cylindrical target designs that are stable against hydrodynamic instability growth in 2D and achieve high yield.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2022

Prospects for distinguishing supernova models using a future neutrino signal

The next Galactic core-collapse supernova (SN) should yield a large number of observed neutrinos. Here, using Bayesian techniques, we show that with a SN at a known distance up to 25 kpc, the neutrino events in a water Cherenkov detector similar to Super-Kamiokande (SK) could be used to distinguish between seven one-dimensional neutrino emission models assuming no flavor oscillations or the standard Mikheyev-Smirnov-Wolfenstein effect. Some of these models could still be differentiated with a SN at a known distance of 50 kpc. We also consider just the relative distributions of neutrino energy and arrival time predicted by the models and find that a detector like SK meets the requirement to distinguish between these distributions with a SN at an unknown distance up to $\mathrm{\sim 10 kpc.}$

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

Improving Predictions Under Uncertainty of Material Plasma Device Operations

Understanding the properties of materials when exposed to various plasma temperatures and fluxes is essential to the building and operating of fusion reactors. The Material Plasma Exposure eXperiment (MPEX) is an instrument currently being developed by the Department of Energy (DOE) for this purpose. MPEX is expected to come online in stages over the next five years. Proto-MPEX, the predecessor to MPEX, operated from 2014 to 2021, and was designed to understand the generation of plasma temperatures and fluxes at orders of magnitude below what will be obtained by MPEX. This work uses the recently developed stochastic neural network (SNN), a machine learning technique capable of operating under uncertainty to provide a surrogate model for the Proto-MPEX device. We demonstrate that SNN outperforms Bayesian neural network (BNN), a standard in the field of machine learning with uncertainty. The development of a robust surrogate of the Proto-MPEX will aid in the commissioning and operation of the MPEX device.

Archibald, Rick↗
DOE OSTI2023

Measurements of neutrino oscillation parameters from the T2K experiment using $$3.6\times 10^{21}$$ protons on target

Abstract The T2K experiment presents new measurements of neutrino oscillation parameters using $$19.7(16.3)\times 10^{20}$$ 19.7 ( 16.3 ) × 10 20 protons on target (POT) in (anti-)neutrino mode at the far detector (FD). Compared to the previous analysis, an additional $$4.7\times 10^{20}$$ 4.7 × 10 20 POT neutrino data was collected at the FD. Significant improvements were made to the analysis methodology, with the near-detector analysis introducing new selections and using more than double the data. Additionally, this is the first T2K oscillation analysis to use NA61/SHINE data on a replica of the T2K target to tune the neutrino flux model, and the neutrino interaction model was improved to include new nuclear effects and calculations. Frequentist and Bayesian analyses are presented, including results on $$\sin ^2\theta _{13}$$ sin 2 θ 13 and the impact of priors on the $$\delta _{\textrm{CP}}$$ δ CP measurement. Both analyses prefer the normal mass ordering and upper octant of $$\sin ^2\theta _{23}$$ sin 2 θ 23 with a nearly maximally CP-violating phase. Assuming the normal ordering and using the constraint on $$\sin ^2\theta _{13}$$ sin 2 θ 13 from reactors, $$\sin ^2\theta _{23}=0.561^{+0.021}_{-0.032}$$ sin 2 θ 23 = 0 . 561 - 0.032 + 0.021 using Feldman–Cousins corrected intervals, and $$\varDelta {}m^2_{32}=2.494_{-0.058}^{+0.041}\times 10^{-3}~\text {eV}^2$$ Δ m 32 2 = 2 . 494 - 0.058 + 0.041 × 10 - 3 eV 2 using constant $$\varDelta \chi ^{2}$$ Δ χ 2 intervals. The CP-violating phase is constrained to $$\delta _{\textrm{CP}}=-1.97_{-0.70}^{+0.97}$$ δ CP = - 1 . 97 - 0.70 + 0.97 using Feldman–Cousins corrected intervals, and $$\delta _{\textrm{CP}}=0,\pi $$ δ CP = 0 , π is excluded at more than 90% confidence level. A Jarlskog invariant of zero is excluded at more than $$2\sigma $$ 2 σ credible level using a flat prior in $$\delta _{\textrm{CP}},$$ δ CP , and just below $$2\sigma $$ 2 σ using a flat prior in $$\sin \delta _{\textrm{CP}}.$$ sin δ CP . When the external constraint on $$\sin ^2\theta _{13}$$ sin 2 θ 13 is removed, $$\sin ^2\theta _{13}=28.0^{+2.8}_{-6.5}\times 10^{-3},$$ sin 2 θ 13 = 28 . 0 - 6.5 + 2.8 × 10 - 3 , in agreement with measurements from reactor experiments. These results are consistent with previous T2K analyses.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2020

A Bayesian Approach for Statistical–Physical Bulk Parameterization of Rain Microphysics. Part I: Scheme Description

A novel framework is proposed for the bulk parameterization of rain microphysics: the Bayesian Observationally Constrained Statistical–Physical Scheme (BOSS). It is designed to facilitate direct constraint by observations using Bayesian inference. BOSS combines existing process-level microphysical knowledge with flexible process rate formulations and parameters constrained by observations within a Bayesian framework. Furthermore, using a raindrop size distribution (DSD) normalization method that relates DSD moments to one another via generalized power series, generalized multivariate power expressions are derived for the microphysical process rates as functions of a set of prognostic DSD moments. The scheme is flexible and can utilize any number and combination of prognostic moments and any number of terms in the process rate formulations. This means that both uncertainty in parameter values and structural uncertainty associated with the process rate formulations can be investigated systematically, which is not possible using traditional schemes. In this paper, BOSS is compared to two- and three-moment versions of a traditional bulk rain microphysics scheme (denoted as MORR). It is demonstrated that some process formulations in MORR are analytically equivalent to the generalized power expressions in BOSS using one or two terms, while others are not. BOSS is able to replicate the behavior of MORR in idealized one-dimensional rainshaft tests, but with a much more flexible and systematic design. Part II of this study describes the application of BOSS to derive rain microphysical process rates and posterior parameter distributions in Bayesian experiments using Markov chain Monte Carlo sampling constrained by synthetic observations.

58 GEOSCIENCES↗
DOE OSTI2022

Accurate and Rapid Forecasts for Geologic Carbon Storage via Learning-Based Inversion-Free Prediction

Carbon capture and storage (CCS) is one approach being studied by the U.S. Department of Energy to help mitigate global warming. The process involves capturing CO 2 emissions from industrial sources and permanently storing them in deep geologic formations (storage reservoirs). However, CCS projects generally target “green field sites,” where there is often little characterization data and therefore large uncertainty about the petrophysical properties and other geologic attributes of the storage reservoir. Consequently, ensemble-based approaches are often used to forecast multiple realizations prior to CO 2 injection to visualize a range of potential outcomes. In addition, monitoring data during injection operations are used to update the pre-injection forecasts and thereby improve agreement between forecasted and observed behavior. Thus, a system for generating accurate, timely forecasts of pressure buildup and CO 2 movement and distribution within the storage reservoir and for updating those forecasts via monitoring measurements becomes crucial. This study proposes a learning-based prediction method that can accurately and rapidly forecast spatial distribution of CO 2 concentration and pressure with uncertainty quantification without relying on traditional inverse modeling. The machine learning techniques include dimension reduction, multivariate data analysis, and Bayesian learning. The outcome is expected to provide CO 2 storage site operators with an effective tool for timely and informative decision making based on limited simulation and monitoring data.

58 GEOSCIENCES↗