Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “uncertainty Quantification”

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 199 records · Page 11
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Uncertainty quantification for neural network potential foundation models

Abstract For neural network potentials (NNPs) to gain widespread use, researchers must be able to trust model outputs. However, the blackbox nature of neural networks and their inherent stochasticity are often deterrents, especially for foundation models trained over broad swaths of chemical space. Uncertainty information provided at the time of prediction can help reduce aversion to NNPs. In this work, we detail two uncertainty quantification (UQ) methods. Readout ensembling, by finetuning the readout layers of an ensemble of foundation models, provides information about model uncertainty, while quantile regression, by replacing point predictions with distributional predictions, provides information about uncertainty within the underlying training data. We demonstrate our approach with the MACE-MP-0 model, applying UQ to the foundation model and a series of finetuned models. The uncertainties produced by the readout ensemble and quantile methods are demonstrated to be distinct measures by which the quality of the NNP output can be judged.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Improving and Assessing the Quality of Uncertainty Quantification in Deep Learning

Deep learning (DL) models have enjoyed increased attention in recent years because of their powerful predictive capabilities. While many successes have been achieved, standard deep learning methods suffer from a lack of uncertainty quantification (UQ). While the development of methods for producing UQ from DL models is an active area of current research, little attention has been given to the quality of the UQ produced by such methods. In order to deploy DL models to high-consequence applications, high-quality UQ is necessary. This report details the research and development conducted as part of a Laboratory Directed Research and Development (LDRD) project at Sandia National Laboratories. The focus of this project is to develop a framework of methods and metrics for the principled assessment of UQ quality in DL models. This report presents an overview of UQ quality assessment in traditional statistical modeling and describes why this approach is difficult to apply in DL contexts. An assessment on relatively simple simulated data is presented to demonstrate that UQ quality can differ greatly between DL models trained on the same data. A method for simulating image data that can then be used for UQ quality assessment is described. A general method for simulating realistic data for the purpose of assessing a model’s UQ quality is also presented. A Bayesian uncertainty framework for understanding uncertainty and existing metrics is described. Research that came out of collaborations with two university partners are discussed along with a software toolkit that is currently being developed to implement the UQ quality assessment framework as well as serve as a general guide to incorporating UQ into DL applications.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Inferring Structural Parameters of Low-Surface-Brightness-Galaxies with Uncertainty Quantification using Bayesian Neural Networks

Measuring the structural parameters (size, total brightness, light concentration, etc.) of galaxies is a significant first step towards a quantitative description of different galaxy populations. In this work, we demonstrate that a Bayesian Neural Network (BNN) can be used for the inference, with uncertainty quantification, of such morphological parameters from simulated low-surface-brightness galaxy images. Compared to traditional profile-fitting methods, we show that the uncertainties obtained using BNNs are comparable in magnitude, well-calibrated, and the point estimates of the parameters are closer to the true values. Our method is also significantly faster, which is very important with the advent of the era of large galaxy surveys and big data in astrophysics.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2023

Uncertainty quantification for high explosive reactant and product equations of state

Equations of state (EOSs) are typically represented as physics-informed models with tunable parameters that are adjusted to replicate calibration data as closely as possible. Uncertainty quantification (UQ) allows for the development of an ensemble of EOS parameters that are consistent with the calibration data instead of a single EOS. In this work, we perform UQ for the reactant and product EOSs for a variety of high explosives (HEs). In doing so, we demonstrate a strategy for dealing with heterogeneous (both experimental and calculated) data. We also use a statistical distance metric to quantify the differences between the various HEs using the UQ results.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2026

Quantum-Inspired Bayesian Sampling for Uncertainty Quantification and Machine Learning (Final Technical Report)

With increasing simulation and measurement data, machine learning and artificial intelligence have been widely used in computational decision-making of complex engineering systems. The resulting tools, such as uncertainty quantification solvers, reinforcement learning, and physics-informed machine learning, have achieved great success in critical DOE tasks such as material discovery and design, energy system modeling and control, and numerical weather and climate prediction. A core topic in scientific machine learning and artificial intelligence is Bayesian inference: given an observed data set, people want to estimate the posterior distribution of a (possibly large) number of hidden parameters. Due to the flexibility and weak assumptions, Bayesian sampling has been the mainstream Bayesian inference solvers despite the rapid progress of approximate Bayesian inference. Classical Bayesian sampling methods such as Markov-chain Monte Carlo suffer from a low-acceptance rate due to the random walk nature, therefore state-of-the-art techniques use Hamiltonian Monte Carlo and its variants to efficiently draw posterior samples in a high dimension. The key idea of Hamiltonian Monte Carlo and its variants is to simulate the Hamiltonian dynamics of a classical particle with a fixed mass, and their performance significantly degrades when the posterior distribution is highly spiky or has multiple modes. Leveraging the idea of quantum physics, this project has investigated new theory, algorithms and applications of Bayesian inference (especially Bayesian sampling). The main results include: (1) novel quantum-inspired Bayesian sampling methods that can lead to better accuracy for challenging multi-modal or spiky distributions, (2) more scalable machine learning framework leveraging tensor-compressed Bayesian inference, and (3) Bayesian and sampling approaches for verifying the robustness of continuous and binary neural networks.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Uncertainty Quantification and Sensitivity Analysis of Low-Dimensional Manifold via Co-Kurtosis PCA in Combustion Modeling

For multi-scale multi-physics applications e.g., the turbulent combustion code Pele, robust and accurate dimensionality reduction is crucial to solving problems at exascale and beyond. A recently developed technique, Co-Kurtosis based Principal Component Analysis (CoK-PCA) which leverages principal vectors of co-kurtosis, is a promising alternative to traditional PCA for complex chemical systems. To improve the effectiveness of this approach, we employ Artificial Neural Networks for reconstructing thermo-chemical scalars, species production rates, and overall heat release rates corresponding to the full state space. Our focus is on bolstering confidence in this deep learning based non-linear reconstruction through Uncertainty Quantification (UQ) and Sensitivity Analysis (SA). UQ involves quantifying uncertainties in inputs and outputs, while SA identifies influential inputs. One of the noteworthy challenges is the computational expense inherent in both endeavors. To address this, we employ the Monte Carlo methods to effectively quantify and propagate uncertainties in our reduced spaces while managing computational demands. Our research carries profound implications not only for the realm of combustion modeling but also for a broader audience in UQ. By showcasing the reliability and robustness of CoK-PCA in dimensionality reduction and deep learning predictions, we empower researchers and decision-makers to navigate complex combustion systems with greater confidence.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Uncertainty Quantification for a Multi-phase Carbon Equation of State Model

Many physics models have tunable parameters that are calibrated by matching the model output to experimental or calculated data. However, given that calibration data often contain uncertainty and that different model parameter sets might result in a very similar simulated output for a finite calibration data set, it is advantageous to provide an ensemble of parameter sets that are consistent with the calibration data. Uncertainty quantification (UQ) provides a means to generate such an ensemble in a statistically rigorous fashion. In this work, we perform UQ for a multi-phase equation of state (EOS) model for carbon containing the diamond, graphite, and liquid phases. We use a Bayesian framework for the UQ and introduce a novel strategy for including phase diagram information in the calibration. The method is highly general and accurately reproduces the calibration data without any material-specific prior knowledge of the EOS model parameters.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Beyond Point Estimates: Benchmarking Uncertainty Quantification Methods on the AION-1 Astronomical Foundation Model

Foundation models for astronomical surveys offer powerful learned representations that can be transferred to downstream regression tasks such as galaxy property estimation. However, point predictions alone are insufficient for scientific inference; reliable uncertainty quantification (UQ) is essential. We compare seven UQ methods on galaxy property regression using frozen AION-1 foundation-model embeddings, predicting redshift, stellar mass, stellar-population age, gas-phase metallicity, and specific star-formation rate, from Legacy Survey photometry/imaging and DESI spectra, with PROVABGS-derived labels. Distribution-free conformal methods achieve marginal coverage within $\sim$1 pp of the nominal 90% across all properties, while non-conformal baselines (Deep Ensembles, MC~Dropout) fail to calibrate reliably. Among conformal approaches, Conformalized Quantile Regression (CQR) delivers the best coverage in the bin with the poorest model predictions. More importantly, only the Locally Valid and Discriminative (LVD) framework -- particularly when operating on AION-1 embeddings -- also provides finite-sample \emph{local validity}, producing intervals that adapt to each galaxy's local prediction difficulty rather than relying on marginal guarantees alone. These results establish conformal prediction, and LVD in particular, as the preferred UQ framework for uncertainty-aware inference on foundation-model embeddings in astrophysics.

Tame-Narvaez, Karla [Fermilab] (ORCID:000000022249↗
DOE OSTI2025

Evaluating probabilistic deep learning methods for uncertainty quantification of temperature downscaling

Deep learning (DL) has emerged as a promising tool for downscaling coarse-resolution climate data to high-resolution outputs, enabling improved regional climate predictions. A critical aspect of DL-based downscaling is the incorporation of uncertainty quantification (UQ), which enhances the interpretability and reliability of predictions—key factors for climate risk assessment and decision-making. This study develops a DL model to downscale 2 m temperature across the contiguous United States using reanalysis datasets. We systematically evaluate three epistemic UQ methods—deep ensembles (DEns), Monte Carlo dropout (MCD), and Flipout—based on their probabilistic accuracy, downscaling performance, sensitivity to geographical features, and computational efficiency. Results indicate that MCD generally outperforms Flipout and DEns in terms of calibration and downscaling accuracy. However, DEns demonstrate lower calibration errors in coastal regions, indicating its higher confidence within these areas. Flipout, in contrast, is more sensitive to elevation gradients and exhibits higher calibration errors in mountainous regions. Hence, the choice of UQ method for this task depends on the specific requirements of the application. For applications that prioritize overall calibration, downscaling accuracy, and computational efficiency, MCD is a strong candidate. These findings highlight the importance of selecting UQ methods based on application-specific requirements, such as geographical context and computational constraints. By addressing the trade-offs between UQ methods, this study provides actionable insights for improving the reliability, scalability, and utility of DL-based downscaling in climate science.

Environmental sciences↗
DOE OSTI2022

Verification, Validation, and Uncertainty Quantification in Thermal Hydraulics, Freeman Scholar Lecture (2019)

Engineering problems are generally solved by analytical models or computer codes. These models, in addition to conservation equations, also include many empirical relationships and approximate numerical methods. Each of these components contributes to the uncertainty in the prediction. A systematic approach to judge the applicability of the code to the intended application is needed. It starts from verification of implementation of formulation in the code, identification of important phenomena, finding relevant tests with quantified uncertainty for these phenomena, and validation of the code by comparing predictions with the relevant test data. The relevant tests must address phenomena as expected in the intended application. In case of small size or limited condition tests, the scaling analyses are needed to assess the relevancy of the tests. Finally, a statement of uncertainty in the prediction is needed. Systematic approaches are described to aggregate uncertainties from different components of the code for intended application. Here, verification, validation, and uncertainty quantifications (VVUQs) are briefly described.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2024

Quantum surrogate models for uncertainty quantification

Surrogate models are a critical ingredient to computation-based design and validation of many DOE mission-relevant physical systems. When first-principles computation of properties of a physical systems becomes pro hibitive, surrogate models are the only path towards achieving tasks such as uncertainty quantification (UQ), exploration of design space, and validation of design choices. In this project we have developed and demonstrated a new surro gate modeling paradigm for complex models that is data-driven, non-intrusive, and has the potential to be versatile and equipped with performance guaran tees. This combination of features is absent in existing surrogate modeling tools. The framework we have developed in this project exploits a quantum-classical correspondence to establish a quantum system that mimics the dynamics of the classical Hamiltonian system from which data in the form of temporal snapshots is provided. Since quantum dynamics propagates distributions over observables, the framework is naturally suited to propagation of epistemic uncertainties in the form of distributions over initial state and parametric uncertainties. In this project, we take the first step in establishing this novel framework by deriving a quantization and de-quantization procedure, demonstrating the accuracy of the quantum surrogate models these define using two model systems, and defining the next steps in maturing the framework towards a tool applicable to Sandia mission-relevant problems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Uncertainty Quantification in High-Low Dynamic System Coupling Using RAVEN and TRANSFORM

This report demonstrates new functionality and applications stemming from the development of high fidelity to low fidelity (high-low) coupling for system simulations and to further explore the capabilities of RAVEN in the performance of uncertainty quantification in this kind of high-low coupled system models. The work builds from previous work on high-low coupling that utilized CTF, the high fidelity subchannel analysis code, with a low fidelity model built in TRANSFORM, the system analysis code, utilizing the Functional Mock-Up Interface (FMI)

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Uncertainty Quantification in High-Low Dynamic System Coupling using RAVEN and TRANSFORM

This work demonstrates new functionality and applications stemming from the development of high-fidelity to low-fidelity (high-low) coupling for system simulations and to further explore the capabilities of the Risk Analysis Virtual Environment (RAVEN) in the performance of uncertainty quantification in this kind of high-low coupled system models. The work builds from previous work on high-low coupling that utilized COBRA-TF (CTF), the high-fidelity subchannel analysis code, with a low fidelity model built in ORNL’s TRANSFORM, the system analysis code, utilizing the Functional Mock-Up Interface (FMI). Steady-state and transient analysis examples using the high/low coupled models generated from CTF and TRANSFORM/FMI are investigated. The workflows for both steady-state and transient coupled simulations are described. A steady-state parameter sweep and uncertainty analysis of the primary flow rates and reactor power are demonstrated. Likewise, a transient pump trip and power ramp sensitivity studies are also demonstrated. This work elucidates some of the potential benefits and future needs of using RAVEN for high/low system coupling analysis of energy systems. It also shows some of the difficulties that can be encountered in coupling system simulations.

Williams, Wesley↗
DOE OSTI2021

Particle image velocimetry analysis with simultaneous uncertainty quantification using Bayesian neural networks

Particle image velocimetry (PIV) is an effective tool in experimental fluid mechanics for extracting flow fields from images. Recently, convolutional neural networks (CNNs) have been used to perform PIV analysis with accuracy on par with classical methods. Here we extend the use of CNNs to analyze PIV data while providing simultaneous uncertainty quantification on the inferred flow field. The method we apply in this paper is a Bayesian convolutional neural network (BCNN) which learns distributions of the CNN weights through variational Bayes. In order to demonstrate the utility of BCNNs for the PIV task, we compare the performance of three distinct BCNN models with simple architectures. The first network estimates flow velocity from image interrogation regions only. Our second model learns to infer velocity from both the image interrogation regions and interrogation region cross-correlation maps. Finally, our best performing network infers velocities from interrogation region cross-correlation maps only. We find that BCNNs using interrogation region cross-correlation maps as inputs perform better than those using interrogation windows only as inputs and discuss reasons why this may be the case. Additionally, we test the best performing BCNN on a full synthetic test image pair and a real image pair from the 1st International PIV Challenge. We show that ~98% of true particle displacements from the full synthetic image pair can be captured within the BCNN's 95% confidence intervals, and that the BCNN's performance on the real image pair is quantitatively similar to that of algorithms tested in the 1st International PIV Challenge. Finally, we show that BCNNs can be generalized to be used with multi-pass PIV algorithms with a moderate loss in accuracy, which may be overcome by future work on finetuning and training schemes. So to our knowledge, this is the first use of Bayesian neural networks to perform PIV.

47 OTHER INSTRUMENTATION↗
DOE OSTI2023

Simulation of a TRISO MiniFuel irradiation experiment with data-informed uncertainty quantification

An irradiation experiment using tristructural isotropic (TRISO) fuel particles and the miniature fuel (MiniFuel) irradiation vehicle was performed in Oak Ridge National Laboratory’s High Flux Isotope Reactor (HFIR) to support development of the Kairos Power fluoride salt–cooled, high-temperature reactor (KP-FHR). Here, this paper describes modeling predictions of temperatures and fuel burnup for the as-built experiment. An uncertainty quantification (UQ) analysis was performed to determine the effect of TRISO particle volume and position on the temperature predictions at various fuel heat generation rates (HGRs). This UQ study utilized fuel kernel position and volume measurements previously collected using X-ray computed tomography (XCT) techniques and Monte Carlo sampling methods to generate fuel compact cases that were then analyzed using a finite element thermal model. The UQ analysis indicated that uncertainty in calculated temperatures caused by varying TRISO particle arrangement is relatively small, even at high fuel HGR. Final predictions of particle temperatures throughout the irradiation are shown to be relevant to KP-FHR normal and off-normal operating conditions and to previous TRISO irradiation experiments. The combination of XCT with UQ analyses will inform post-irradiation examination (PIE) of the irradiated fuel compacts, and these analyses can be used to develop fuel performance models for coated particle fuel forms. Both PIE of separate-effects irradiation data and enhanced fuel performance modeling support accelerated qualification of TRISO fuels for a broad range of advanced reactor applications. The novel approach demonstrated here of measuring TRISO particle configurations with XCT methods and generating representative fuel compacts for finite element modeling and UQ analysis could be leveraged by the broader particle fuel community in the development of other TRISO fuel experiments in which these variables may have a significant impact on key outcomes.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2020

Multi-fidelity machine-learning with uncertainty quantification and Bayesian optimization for materials design: Application to ternary random alloys

We present a scale-bridging approach based on a multi-fidelity (MF) machine-learning (ML) framework leveraging Gaussian processes (GP) to fuse atomistic computational model predictions across multiple levels of fidelity. Through the posterior variance of the MFGP, our framework naturally enables uncertainty quantification, providing estimates of confidence in the predictions. We used density functional theory as high-fidelity prediction, while a ML interatomic potential is used as low-fidelity prediction. Practical materials’ design efficiency is demonstrated by reproducing the ternary composition dependence of a quantity of interest (bulk modulus) across the full aluminum–niobium–titanium ternary random alloy composition space. The MFGP is then coupled to a Bayesian optimization procedure, and the computational efficiency of this approach is demonstrated by performing an on-the-fly search for the global optimum of bulk modulus in the ternary composition space. The framework presented in this manuscript is the first application of MFGP to atomistic materials simulations fusing predictions between density functional theory and classical interatomic potential calculations.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗