Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “uncertainty quantification (UQ)”

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 181 records · Page 10
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Influence of alloy solidification path on melt pool behavior in additive manufacturing

Numerical models used to study transport phenomena in laser-powder bed fusion processes often rely on assumptions and simplifications to reduce their computational expense. One common simplification is in the description of latent heat evolution during the solid-liquid phase change (i.e., the solidification pathway), justified by the fact that the mushy zone thickness is similar to the numerical grid spacing used for continuum transport models. The lack of resolution of transport phenomena in the mushy zone motivates the use of computationally convenient solidification paths such as linear or sigmoidal relationships over pathways derived from fundamental solidification theory such as equilibrium or Scheil models. In the present work, an uncertainty quantification (UQ) framework is used to analyze the influence of solidification pathway selection on the solidification dynamics and melt pool geometries in laser based additive manufacturing (AM) of IN625. Results show the solidification pathway has a quantifiable influence on the cooling rate at the liquidus isotherm, mushy zone thickness, and solidification time. Due to similarities in the latent heat evolution at the beginning of solidification, the equilibrium and Scheil models predict similar cooling rates near the liquidus isotherm, however the wider freezing range of Scheil leads to a wider mushy zone compared to equilibrium. The non-physical latent heat release profiles of sigmoidal and linear paths lead to significant overpredictions of cooling rates at the liquidus isotherm compared to equilibrium and Scheil. Finally, these results indicate that careful consideration should be given to the choice of solidification pathway to ensure reliable model predictions.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Improvement of the $\mathrm{BISON U_3Si_2}$ modeling capabilities based on multiscale developments to modeling fission gas behavior

Uranium silicide (U 3 Si 2 ) is a concept explored as a potential alternative to UO 2 fuel used in light water reactors (LWRs) since it may improve accident tolerance and economics due to its higher thermal conductivity and increased uranium density. U 3 Si 2 has been previously used in research reactors in the form of dispersion fuel, but operated at lower temperatures than commercial LWRs. The research reactor data illustrated that significant gaseous swelling occurs as the fuel burnup increases. Therefore, it is imperative to understand the fission gas behavior of U 3 Si 2 under higher temperature LWR operating conditions. In this work, molecular dynamics and phase-field modeling techniques are used to reduce the uncertainty in select modeling assumptions made in developing the fission gas behavior model for U 3 Si 2 in the BISON fuel performance code. These lower length scale informed models are then utilized in the validation of BISON U 3 Si 2 modeling capabilities to simulate the ATF-1 experiments irradiated in the Advanced Test Reactor (ATR). Sensitivity analysis (SA) and uncertainty quantification (UQ) are included as part of the validation process to identify where further experiments and lower length scale modeling would be beneficial. Here, the multiscale modeling approach utilized in this work can be applied to new fuel concepts being explored for both LWRs and advanced reactors (e.g., uranium nitride, uranium carbide).

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2022

Physics-informed machine learning assisted uncertainty quantification for the corrosion of dissimilar material joints

Jointing techniques like the Self-Piercing Riveting (SPR), Resistance Spot Welding (RSW) and Rivet-Weld (RW) joints are used for mass production of dissimilar material joints due to their high performance, short cycle time, and adaptability. However, the service life and safety usage of these joints can be largely impacted by the galvanic corrosion due to the difference in equilibrium potentials between the metals with the presence of electrolyte. Here, in this paper, we focus on Al-Fe galvanic corrosion and develop physics-informed machine learning based surrogate model for statistical corrosion analysis, which enables the reliability analysis of dissimilar material joints under corrosion environment. In this study, a physics-based finite element (FE) corrosion model has been developed to simulate the galvanic corrosion between a Fe cathode and an Al anode. Geometric and environmental factors including crevice gap, roughness of anode, conductivity, and the temperature of the electrolyte are investigated. Further, a thorough Uncertainty Quantification (UQ) analysis is conducted for the overall corrosion behavior of the Fe-Al joints. It is found that the electrolyte conductivity has the largest effects on the material loss and needs to be managed closely for better corrosion control. This will help in designing and manufacturing joints with improved corrosion performance.

42 ENGINEERING↗
DOE OSTI2025

Enhancing generative molecular design via uncertainty-guided fine-tuning of variational autoencoders

In recent years, deep generative models have been successfully applied to various molecular design tasks, particularly in the life and materials sciences. One critical challenge for pre-trained generative molecular design (GMD) models is to fine-tune them to be better suited for downstream design tasks that aim at optimizing specific molecular properties. However, redesigning and training an existing effective generative model from scratch for each new design task are impractical. Furthermore, the black-box nature of typical downstream tasks that involve property prediction makes it nontrivial to optimize the generative model in a task-specific manner. In this work, we propose an uncertainty-guided fine-tuning strategy that can effectively enhance a pre-trained variational autoencoder (VAE) for GMD through performance feedback in an active learning setting. The strategy begins by quantifying the model uncertainty of the generative model using an efficient active subspace-based UQ (uncertainty quantification) scheme. Next, the decoder diversity within the characterized model uncertainty class is explored to expand the viable space of molecular generation. The low-dimensionality of the active subspace makes this exploration tractable using a black-box optimization scheme, which in turn enables us to identify and leverage a diverse set of high-performing models to generate enhanced molecules. Empirical results across six target molecular properties using multiple VAE-based generative models demonstrate that our uncertainty-guided fine-tuning strategy consistently leads to improved models that outperform the original pre-trained models.

97 MATHEMATICS AND COMPUTING↗
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 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 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 OSTI2026

Conformalized-KANs: Uncertainty Quantification with Coverage Guarantees for Kolmogorov-Arnold Networks (KANs) in Scientific Machine Learning

This paper explores uncertainty quantification (UQ) methods in the context of Kolmogorov–Arnold Networks (KANs). We apply an ensemble approach to KANs to obtain a heuristic measure of UQ, enhancing interpretability and robustness in modeling complex functions. Building on this, we introduce Conformalized-KANs, which integrate conformal prediction, a distribution-free UQ technique, with KAN ensembles to generate calibrated prediction intervals with guaranteed coverage.} Extensive numerical experiments are conducted to evaluate the effectiveness of these methods, focusing particularly on the robustness and accuracy of the prediction intervals under various hyperparameter settings. We show that the conformal KAN predictions can be applied to recent extensions of KANs, including Finite Basis KANs (FBKANs) and multifideilty KANs (MFKANs). The results demonstrate the potential of our approaches to significantly improve the reliability and applicability of KANs in scientific machine learning.

• Artificial intelligence (AI) / machine learning ↗
DOE OSTI2023

Bayesian, Multifidelity Operator Learning for Complex Engineering Systems–A Position Paper

Abstract Deep learning has significantly improved the state-of-the-art in computer vision and natural language processing, and holds great potential to design effective tools for predicting and simulating complex engineering systems. In particular, scientific machine learning seeks to apply the power of deep learning to scientific and engineering tasks, with operator learning (OL) emerging as a particularly effective tool. OL can approximate nonlinear operators arising in complex engineering systems, making it useful for simulating, designing, and controlling those systems. In this position paper, we provide a comprehensive overview of OL, including its potential applications to complex engineering domains. We cover three variations of OL approaches: deterministic OL for modeling nonautonomous systems, OL with uncertainty quantification (UQ) capabilities, and multifidelity OL. For each variation, we discuss drawbacks and potential applications to engineering, in addition to providing a detailed explanation. We also highlight how multifidelity OL approaches with UQ capabilities can be used to design, optimize, and control engineering systems. Finally, we outline some potential challenges for OL within the engineering domain.

Computer Science↗
DOE OSTI2026

Hierarchical Gaussian Random Field Sampling for Multilevel Markov Chain Monte Carlo: Coupling Stochastic Partial Differential Equation and the Karhunen–Loève Decomposition

This work introduces structure preserving hierarchical decompositions for sampling Gaussian random fields (GRFs) within the context of multilevel Bayesian inference in high-dimensional space. Existing scalable hierarchical sampling methods, such as those based on stochastic partial differential equations (SPDEs), often reduce the dimensionality of the sample space at the cost of accuracy of inference. Other approaches, such that those based on Karhunen-Loève (KL) expansions, offer sample space dimensionality reduction but sacrifice GRF representation accuracy and ergodicity of the Markov chain Monte Carlo (MCMC) sampler and are computationally expensive for high-dimensional problems. The proposed method integrates the dimensionality reduction capabilities of KL expansions with the scalability of SPDE-based sampling, thereby providing a robust, unified framework for high-dimensional uncertainty quantification (UQ) that is scalable and accurate, preserves ergodicity, and offers dimensionality reduction of the sample space. The hierarchy in our multilevel algorithm is derived from the geometric multigrid hierarchy. By constructing a hierarchical decomposition that maintains the covariance structure across the levels in the hierarchy, the approach enables efficient coarse-to-fine sampling while ensuring that all samples are drawn from the desired distribution. The effectiveness of the proposed method is demonstrated on a benchmark subsurface flow problem, demonstrating its effectiveness in improving computational efficiency and statistical accuracy. Furthermore, our proposed technique is more efficient and accurate and displays better convergence properties than existing methods for high-dimensional Bayesian inference problems.

Gaussian random fields↗
DOE OSTI2022

A Bayesian Approach for Quantifying Data Scarcity when Modeling Human Behavior via Inverse Reinforcement Learning

Computational models that formalize complex human behaviors enable study and understanding of such behaviors. However, collecting behavior data required to estimate the parameters of such models is often tedious and resource intensive. Thus, estimating dataset size as part of data collection planning (also known as Sample Size Determination) is important to reduce the time and effort of behavior data collection while maintaining an accurate estimate of model parameters. In this paper, we present a sample size determination method based on Uncertainty Quantification (UQ) for a specific Inverse Reinforcement Learning (IRL) model of human behavior, in two cases: 1) pre-hoc experiment design—conducted in the planning stage before any data is collected, to guide the estimation of how many samples to collect; and 2) post-hoc dataset analysis—performed after data is collected, to decide if the existing dataset has sufficient samples and whether more data is needed. Here, we validate our approach in experiments with a realistic model of behaviors of people with Multiple Sclerosis (MS) and illustrate how to pick a reasonable sample size target. Our work enables model designers to perform a deeper, principled investigation of effects of dataset size on IRL.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

AL-ASMR: Active Learning of Atomistic Surrogate Models for Rare Events

Atomistic simulation with artificial intelligence (AI) is an emerging tool for understanding materials' properties and behaviors and predicting novel materials with optimized/targeted properties. Neural network potentials (NNPs) are outstanding in this field as they have shown a comparable accuracy to ab initio electronic structure calculations for reproducing potential energy surfaces while being several orders of magnitude faster. However, such NNPs can perform poorly outside of their training domain and typically fail catastrophically in the prediction of rare events in molecular dynamics (MD) simulations. For effective AL loops to distinguish the informative data from enhanced sampled configurations, we developed a decision engine by configurational similarity and uncertainty quantification (UQ) with data augmentation.

Jung, Gang Seob↗
DOE OSTI2024

HydraGNN_Predictive_GFM_2024 - Ensemble of predictive graph foundation models for ground state atomistic materials modeling

We provide the ensemble of fifteen pre-trained graph foundation models (GFMs) for atomistic materials modeling applications. Each one of the fifteen GFMs has been trained on five open-source datasets that (once aggregated) amount to over 154 million atomistic structures, which cover over two-thirds of the natural elements of the periodic table and that comprises a broad set of organic and inorganic compounds. This vast set of atomistic structures comprises ground state configurations that are dynamically stable (i.e., equilibrated structures with atomic forces approximately close to zero values) as well as dynamically unstable structures (i.e., non-equilibrium structures with non-negligible non-zero values of atomic forces). The ensemble of datasets aggregated does NOT include excited states. The datasets have been curated to remove atomistic structures with spectral norm of the force tensor above 100 eV/angstrom. Moreover, a linear term of the energy was computed for each dataset using a linear regression model that uses the chemical concentration of each natural element as regressor. The linear term predicted by the linear regression model has been subtracted from each original energy value to perform a re-alignment of the energy values across different electronic structures approximation theories performed to generate the diverse multi-source, multi-fidelity datasets. The folder "ADIOS_files" contains the set of pre-processed datasets in Adaptable I/O System (ADIOS) format (https://www.exascaleproject.org/research-project/adios/) that have been used for the development and training of GFMs in this work. The "ADIOS_files" directory contains 6 sub-directories named as follows: - ANI1x-v3.bp - MPTrj-v3.bp - OC2020-20M-v3.bp - OC2020-v3.bp - OC2022-v3.bp - qm7x-v3.bp Each sub-directory contains the pre-processed datasets converted in Adaptable I/O System (ADIOS) format (https://www.exascaleproject.org/research-project/adios/) that have been used to the development, training, and performance testing of the ensemble go predictive graph foundation models. Each GFM was developed using HydraGNN (https://github.com/ORNL/HydraGNN) as underlying graph neural network (GNN) architecture. The multi-task learning (MTL) capability of HydraGNN was used to simultaneously train the GFMs on labeled values for direct predictions of energy (a total system property of an atomistic structure that measures the chemical stability) and atomic forces (an atomic level property of an atomistic structure that measures the dynamical stability). The hyper parameters of the GFM have been tuned using scalable hyperparameter optimization (HPO) algorithms implemented in the software DeepHyper (https://github.com/deephyper/deephyper). The pre-training of each HPO trial was performed using distributed data parallelism (DDP) to scale the training across 128 compute nodes of the exascale OLCF supercomputer Frontier. Each HPO trial was trained only for 10 epochs and an early stopping was performed to avoid wasting significant computational resources on GNN architectures that were clearly underperforming. For each HPO trial, the 'omnistat' tool developed by (AMD Research - Advanced Micro Device) was used to measure the total energy consumption in kWh. The ensemble of GFMs was obtained by selecting the fifteen best performing HPO trials. Four models have been selected for their clear advantage in accuracy, and these are the GFMs with IDs 229, 156, 147, 260. Additional eleven models have been selected based on judicious balance between accuracy and energy consumption needed for training, and these are the GFMs with IDs 165, 78, 137, 1, 175, 171, 181, 67, 179, 167, 351. Each selected GFM of the ensemble was continued to cumulate a total of at most 30 epochs. In some cases, the total number of epochs actually performed was les than 30 due to two combined factors: (1) the size of the GFM (i.e., the number of model parameters to train) and (2) the total wall-clock time for which the computational resources could be allocated on OLCF-Frontier. The "Ensemble_of_models" directory contains 15 sub-directories named as follows: - gfm_0.229 - gfm_0.156 - gfm_0.147 - gfm_0.260 - gfm_0.165 - gfm_0.78 - gfm_0.137 - gfm_0.1 - gfm_0.175 - gfm_0.171 - gfm_0.181 - gfm_0.67 - gfm_0.179 - gfm_0.167 - gfm_0.351 Each one of these sub-directories refers to one of the fifteen HPO trials that have been selected to continue the pre-training with at most 30 epochs. With each sub-directory associated with a specific HPO trial, the following files can be found: - config.json: file for argument parsing to develop and train an HydraGNN architecture - gfm_0.ID_epoch_N.pk: file with model parameters for HPO ID trial after N epochs of training The ensemble of fifteen GFM architectures was used for (1) ensemble averaging to stabilize the predictions of energy and atomic forces after pre-training for post-processing analysis and (2) ensemble uncertainty quantification (UQ). The code used to develop, pre-train, and load the pre-trained models for post-processing analysis is available on the ORNL-GitHub at the following link: https://github.com/ORNL/HydraGNN/tree/Predictive_GFM_2024

36 MATERIALS SCIENCE↗
DOE OSTI2023

Generalized Bayesian Framework for Evaluation of Integral Benchmark Experiments

A recently published generalized Bayesian optimization framework has provided a way to retract any or all of the three common assumptions underlying the conventional Generalized Linear Least Squares (GLLS) optimization method based on the concepts introduced in Ref. [2]. These assumptions are: 1. Perfection: The model used for data evaluation and the prior probability distribution function (PDF) of generalized data are perfect. 2. Normality: The prior and posterior PDF are normal. 3. Linearity: The model is linear. In this work we outline how the framework in [1] could be directly adopted for improved evaluation of nuclear criticality integral benchmark experiments (IBEs) by: 1. Removing the first assumption alone by utilizing the concept of imperfections introduced in [1] to enable evaluation in the presence of discrepancies between the data and model or of missing covariance information by a GLLS method that will be seen as a generalization of the conventional GLLS method employed by the TSURFER code, and by 2. Removing the remaining two assumptions by implementing a Markov Chain Monte Carlo method for computation of the posterior PDF in the SAMPLER code, where TSURFER and SAMPLER are the uncertainty quantification (UQ) codes for IBEs in the SCALE code system based on the GLLS and the stochastic method, respectively. The graphic in Figure 1 categorizes the methods discussed in terms of the assumptions that they employ to determine posterior PDFs.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2020

In-Situ Inference: Bringing Advanced Data Science Into Exascale Simulations

As simulations generate ever-increasing amounts of data, there are correspondingly richer opportunities for analysis and scientific discovery - discoveries that will be missed if most of the data must be discarded before it is analyzed. Because future exascale architectures will be increasingly storage-limited, it will not be possible to save the vast majority of simulation data for later analysis, requiring analysis to occur “in-situ” within the simulation. However, existing in-situ data analysis frameworks provide little or no support for one of the most sophisticated forms of data science: probabilistic statistical modeling or uncertainty quantification (UQ), and the accompanying challenge of inference - fitting those statistical models to massive simulation output. Our goal is to develop the fundamental statistical algorithms and computer science needed to perform statistical inference in-situ (in HPC simulations) to the full stream of data those simulations generate.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

¬¬Integration of Quantification of Margins and Uncertainties Methodology into Parallel Discrete Event Simulator Framework

Parallel Discrete Events Simulation (PDES) is becoming increasingly important to lab efforts in security and intelligence. It is used to model complex asynchronous systems such as computer networks, satellite systems, vehicular traffic, and human performance. Uncertainty Quantification (UQ) techniques have become a mainstay of Verification and Validation (V&V) efforts on physics simulations. However, PDES models are very different from traditional physics simulations, and research into UQ techniques for PDES is in its infancy. It is not clear which traditional UQ techniques can be applied to PDES, or what new techniques will need to be developed. The goal of this project was to identify existing UQ techniques that can be applied to PDES, and to develop new techniques as necessary. The project implemented or developed techniques to handle issues that do not appear in traditional physics simulations, but are common among PDES, including sampling techniques for high-dimensional homogenous inputs, response surfaces for high-variance heteroskedastic output, and characterization of skewed output distributions. These are foundational UQ techniques that must be used in any complete UQ analysis (Tong 2018).

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Verification and Validation of High Explosive Reactive Burn Models Implemented in LANL's EAP and LAP Code Base

Reactive burn models represent a significant leap in high explosive (HE) modeling capability. The first generation of engineering models of HE detonation are called programmed burn models and they are largely based on the distance between a prescribed detonation point and each zone in a simulation. There have been many advancements to programmed burn models over the years and when the assumptions upon which they are based are met, a properly tuned programmed burn model can be highly accurate but if any of their assumptions is not met, as is the case for corner turning or weakly initiated HE burn, they will give the wrong answer. Reactive burn models represent an entirely new way of modeling HE burn. They use the local conditions of a zone – e.g. temperature, pressure or density – as calculated by a hydrocode to determine if and when the zone is going to detonate and if so, how rapidly. This difference opens up an entirely new set of capabilities for HE modeling. It makes it possible to accurately and predictively model phenomena like the effect of confinement and the formation of dead zones. Reactive burn models have seen sustained development effort at LANL for at least the last decade but several recent developments make it timely to transition reactive burn models from a research topic to a production tool. The main goal of this milestone is to facilitate and accelerate the adoption of reactive burn as a commonly available modeling option, with recommendations on the resolution that will be required and uncertainties associated with their modeling choices. To achieve this, we have performed verification, validation, and uncertainty quantification (UQ) assessments of AWSD and SURF/SURFplus in xRage and FLAG on a variety of different problems.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗