Search NASA⌕ Search

SEARCH · Search NASA

Results for “Computationally efficient surrogate 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 19 records

Uncertainty Quantification of Fatigue Behavior of Rough AM Surfaces and Microstructures to Enable Hydrogen Gas Turbine

Modifying fossil-fueled industrial gas turbines to utilize low or zero-carbon fuels, such as hydrogen or hydrogen-natural gas blends, is a complex endeavor. The successful implementation of this technology hinges on three key design criteria: (1) developing new fuel injectors capable of efficiently burning alternative fuels, (2) ensuring manufacturability to meet cost and time-to-market goals, and (3) achieving component durability in the demanding environment of an operating gas turbine. Additive manufacturing (AM) accelerates product development, yet concerns persist regarding the durability of parts with rough AM surfaces. A fully experimental approach to quantify the fatigue performance of rough AM microstructures is both costly and labor-intensive. To address this, ORNL and Solar Turbines Incorporated (Solar) employed a crystal plasticity finite element (CPFE) model to identify the factors influencing AM surface fatigue behavior. These CPFE findings, combined with targeted experimental data, were used to develop a computationally efficient surrogate model suitable for assessing the lifespan of gas turbine engine components.

08 HYDROGEN↗

Uncertainty Quantification of Fatigue Behavior of Rough AM Surfaces and Microstructures to Enable Hydrogen Gas Turbine Combustion

Modification of fossil-fueled industrial gas turbines to accept no/low carbon fuels (Hydrogen, H2/natural gas blends) is a significant undertaking. Successful deployment of this technology sits at the intersection of three design criteria (1) new functional fuel injectors that can burn these fuels, (2) manufacturability to meet cost and time-to-market targets, and (3) durability in the harsh environment of an operating turbine. Additive manufacturing (AM) provides accelerated product development. However, uncertainty remains around the durability of parts with rough AM surfaces. A fully experimental approach towards quantifying fatigue performance of rough AM microstructures is costly and laborious. Instead, Solar Turbines Incorporated (Solar) proposes the use of a crystal plasticity finite element (CPFE) model to quantify the factors that drive AM surface fatigue behavior. Solar will use the CPFE results, along with targeted experimental data, to train a computationally efficient surrogate model that can be incorporated into existing turbine part lifing methods.

08 HYDROGEN↗

Polynomial Chaos Characterization of Uncertainty in Multiscale Models and Behavior of Carbon Reinforced Composites

Design of non-crimp fabric (NCF) composites entails major challenges pertaining to (1) the complex fine-scale morphology of the constituents, (2) the manufacturing-produced inconsistency of this morphology spatially, and thus (3) the ability to build reliable, robust, and efficient computational surrogate models to account for this complex nature. Traditional approaches to construct computational surrogate models have been to average over the fluctuations of the material properties at different scale lengths. This fails to account for the fine-scale features and fluctuations in morphology, material properties of the constituents, as well as fine-scale phenomena such as damage and cracks. In addition, it fails to accurately predict the scatter in macroscopic properties, which is vital to the design process and behavior prediction. In this work, funded in part by the Department of Energy, we present an approach for addressing these challenges by relying on polynomial chaos representations of both input parameters and material properties at different scales. Moreover, we emphasize the efficiency and robustness of integrating the polynomial chaos expansion with multiscale tools to perform multiscale assimilation, characterization, propagation, and prediction, all of which are necessary to construct the data-driven surrogate models required to design under the uncertainty of composites. These data-driven constructions provide an accurate map from parameters (and their uncertainties) at all scales and the system-level behavior relevant for design. While this perspective is quite general and applicable to all multiscale systems, NCF composites present a particular hierarchy of scales that permits the efficient implementation of these concepts.

42 ENGINEERING↗

Intelligent Surrogate Model Development: Boosting Computational Efficiency for Autonomous Control of Advanced Reactors

Advanced reactors promise enhanced safety, greater efficiency, and waste reductions. To fully realize these benefits, it is crucial to address the need for autonomous or semi-autonomous control systems that require fewer operators. This research primarily supports the MARVEL autonomous control system, which requires real-time operation. However, the current RELAP5 reactor thermal hydraulic transient simulation is excessively time-consuming. Therefore, this study aims to leverage deep learning techniques to develop a surrogate model, providing a more efficient and accurate alternative for real-time performance. The model was trained using a combination of one-timestep prediction and scheduled sampling. It was then used for recursive prediction of the reactor state. This developed surrogate model significantly improves computational efficiency, achieving a 12 times acceleration.

46 - INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AN↗

Probabilistic Calibration of Expensive Models using Efficiently Trained Surrogates

Calibration of computational models in the presence of uncertainty is often cast as a Bayesian inference problem and solved via sampling methods, e.g., Markov chain Monte Carlo. When the computational model is expensive, this task becomes intractable due to the large number of samples required to accurately estimate the posterior distribution of the calibration parameters. A popular solution to this problem is to use machine learning to develop a faster-to-evaluate, lower-fidelity substitute for the original model to serve as a surrogate while solving the inference problem. Although considered an offline cost, generating training data to construct this surrogate model can still be an expensive task in practice. An active learning algorithm is presented that focuses training on improving surrogate accuracy specifically in and around the bulk of the posterior distribution, as this is where the model is exercised during calibration. Candidate samples are drawn from families of distributions related to an approximation of the posterior. The sample maximizing predictive variance is then selected for evaluation by the original computational model, yielding a label for the training point. Iterating this approach increases efficiency relative to space filling designs (e.g., Latin hypercube sampling) by avoiding low probability points. Practical considerations are discussed, including the benefits of using a sequential Monte Carlo sampling approach, convergence heuristics, and the importance of both exploration and exploitation given that the true posterior is unknown a priori.

uncertainty quantification↗

Enabling in-time Prognostics with Surrogate Modeling through Physics-enhanced Dynamic Mode Decomposition Method

Computational models provide essential quantitative tools for assessing and predicting the health and performance of physical systems. However, high-fidelity models are rarely used in real-time operations or large optimization loops, due to their time-intensive nature. A common approach to improving computational efficiency of prognosis is to employ surrogate models. Such models can significantly decrease computation time for some accuracy loss. In this context, use of Dynamic Mode Decomposition (DMD) is proposed to generate surrogate models for lithium-ion (Li-ion) battery discharge. DMD has been suggested and used successfully in the area of fluid dynamics for over a decade, but it has not been applied to the PHM domain, where far-ahead prediction of nonlinear behavior is crucial to propagate faults or predict Remaining Useful Life (RUL). For Li-ion battery health management, the standard application of DMD using only the observable quantities of interest was unable to capture the nonlinear discharge of batteries exhibited in lab testing. The Koopman theory, however, provides a mechanism to tradeoff low dimensional nonlinear models with high-dimensional linear ones in a DMD framework, by augmenting nonlinear state variables into the system representation. In this way, DMD allows for configurable simulation accuracy dependent on the dimensionality of the Koopman operator. For battery health management, we augmented the observable variables with the hidden states of a higher-fidelity physics model to build the DMD surrogate. In comparison to a high-fidelity model, the surrogate improved computational efficiency with only a minimal loss of accuracy, and enabled long-term prognostics horizons. A generalized method for this was implemented in the prog models python package.

prognostics and health management↗

High-resolution hourly surrogate modeling framework for physics-based large-scale building stock modeling

Surrogate modeling can play a key role in reducing high computational burdens for large-scale physics-based modeling and uncertainty quantification. With the rapid development of large-scale building stock energy modeling, surrogate modeling has also begun to be widely applied in this field; however, most existing surrogate models lack hourly time resolution for regional-scale modeling, which is essential for understanding building demand profiles and grid impacts. Further, there is generally a lack of necessary data and feature engineering frameworks specific to building modeling for efficiently managing large datasets and complex computations. Furthermore, this paper proposes a modeling framework for large-scale (city-/region-scale), high-resolution, high-fidelity surrogate building stock energy models. Our developed framework consists of six modules: (1) building stock energy modeling (ComStock TM and ResStock TM ), (2) data engineering for large simulation data, (3) high performance computing workflow, (4) feature engineering, (5) machine learning model development, and (6) model performance evaluation. Two case studies apply the developed framework in both residential and commercial building stock analysis to demonstrate its computational efficiency and surrogate modeling accuracies. Results show that surrogate models, when efficiently trained using the HPC workflow module, reach a high level of modeling accuracy for two case studies.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Multifidelity, Multidisciplinary Design Under Uncertainty with Non-Intrusive Polynomial Chaos

The primary objective of this work is to develop an approach for multifidelity uncertainty quantification and to lay the framework for future design under uncertainty efforts. In this study, multifidelity is used to describe both the fidelity of the modeling of the physical systems, as well as the difference in the uncertainty in each of the models. For computational efficiency, a multifidelity surrogate modeling approach based on non-intrusive polynomial chaos using the point-collocation technique is developed for the treatment of both multifidelity modeling and multifidelity uncertainty modeling. Two stochastic model problems are used to demonstrate the developed methodologies: a transonic airfoil model and multidisciplinary aircraft analysis model. The results of both showed the multifidelity modeling approach was able to predict the output uncertainty predicted by the high-fidelity model as a significant reduction in computational cost.

West, Thomas K., IV↗

L'Ralph's Advanced Thermal Model Correlation Using Veritrek

Thermal model correlation uses data from thermal balance tests to better estimate uncertain input parameter values. During the correlation process, input parameters are modified in an iterative manner which can become computationally expensive since this requires that the high-fidelity thermal model be run for each iteration. Depending on the number of thermal balance test points there can be many sets of correlation parameters that satisfy correlation criteria; and having enough data to ascertain the best set of correlation parameters to use, further increases the computational expense. Reduced-order models (ROMs) provide computationally efficient surrogates of high-fidelity models and are often built to reduce development cycle times and cost. By leveraging the speed of reduced-order models and the Correlation Analysis feature in the Veritrek software, the typical computational expense of a traditional thermal model correlation process can be significantly reduced and having access to hundreds of thousands of iteration results provides an advanced means of intelligently determining the best set of correlation parameters to use. The L’Ralph thermal team at NASA Goddard Space Flight Center explored the use of the Veritrek software for their thermal model correlation efforts. The ROM that was created allowed for the variation of 15 input parameters to match 70 temperature sensor readouts from 3 thermal balance plateus and required 125 runs of the high-fidelity Thermal Desktop® model to generate a ROM that could predict the detailed model’s results to within 0.2 K (RMS). The ROM was then used to find dozens of plausible correlation parameter values based on L’Ralph instrument test data within a few seconds. By providing several plausible correlation parameter combinations, Veritrek allowed the thermal team to explore different uncertain parameter value combinations and provided insight into how deterministic each input parameter was. This allowed for a more confident decision on the best set of correlation parameters to use, compared to traditional model correlation techniques. In this presentation, the L’Ralph thermal team will be presenting their experience with the Veritrek software and how the software was utilized to provide additional insights during the correlation process.

Daniel Bae↗

L'Ralph's Advanced Thermal Model Correlation Using Veritrek

Thermal model correlation uses data from thermal balance tests to better estimate uncertain input parameter values. During the correlation process, input parameters are modified in an iterative manner which can become computationally expensive since this requires that the high-fidelity thermal model be run for each iteration. Depending on the number of thermal balance test points there can be many sets of correlation parameters that satisfy correlation criteria; and having enough data to ascertain the best set of correlation parameters to use, further increases the computational expense. Reduced-order models (ROMs) provide computationally efficient surrogates of high-fidelity models and are often built to reduce development cycle times and cost. By leveraging the speed of reduced-order models and the Correlation Analysis feature in the Veritrek software, the typical computational expense of a traditional thermal model correlation process can be significantly reduced and having access to hundreds of thousands of iteration results provides an advanced means of intelligently determining the best set of correlation parameters to use. The L’Ralph thermal team at NASA Goddard Space Flight Center explored the use of the Veritrek software for their thermal model correlation efforts. The ROM that was created allowed for the variation of 15 input parameters to match 70 temperature sensor readouts from 3 thermal balance plateus and required 125 runs of the high-fidelity Thermal Desktop® model to generate a ROM that could predict the detailed model’s results to within 0.2 K (RMS). The ROM was then used to find dozens of plausible correlation parameter values based on L’Ralph instrument test data within a few seconds. By providing several plausible correlation parameter combinations, Veritrek allowed the thermal team to explore different uncertain parameter value combinations and provided insight into how deterministic each input parameter was. This allowed for a more confident decision on the best set of correlation parameters to use, compared to traditional model correlation techniques. In this presentation, the L’Ralph thermal team will be presenting their experience with the Veritrek software and how the software was utilized to provide additional insights during the correlation process. "

Daniel Bae↗

Examples of Mission-driven Data Science from Jefferson Lab and ACES

This presentation details mission-driven data science initiatives at Jefferson Lab and the Joint Institute for Advanced Computing on Environmental Studies (ACES). JLab, a U.S. Department of Energy Office of Science national laboratory, operates the Continuous Electron Beam Accelerator Facility (CEBAF), and is the lead institute for the new High Performance Data Facility (HPDF) Hub. The Joint Institute for ACES brings together interdisciplinary teams in health informatics, climate modeling, computer science, and physics to address environmental challenges, including flood modeling. The Hampton Roads region, particularly Norfolk and Virginia Beach, faces increasing flood risks, motivating the need for rapid, reliable, and risk-aware decision support. ACES’s flooding work has a focus on uncertainty quantification (UQ) and machine learning (ML) for coastal flood management. The work is motivated by the increasing vulnerability of communities such as Norfolk and Virginia Beach, Virginia, to frequent coastal flooding events, and the need for rapid, reliable decision support. The research develops computationally efficient ML surrogate models to forecast water levels and flooding risk. A central theme is the quantification and calibration of predictive uncertainty, especially for out-of-distribution (OOD) scenarios, using techniques such as Monte Carlo Dropout, Deep Ensembles, Gaussian Processes, and Deep Quantile Regression (DQR). The study demonstrates that distance-aware UQ is critical for reliable scientific AI, particularly in high-dimensional, safety-critical, and real-time applications.

McSpadden, Diana [Thomas Jefferson National Accele↗

Convolutional L2LFlows: generating accurate showers in highly granular calorimeters using convolutional normalizing flows

Abstract In the quest to build generative surrogate models as computationally efficient alternatives to rule-based simulations, the quality of the generated samples remains a crucial frontier. So far, normalizing flows have been among the models with the best fidelity. However, as the latent space in such models is required to have the same dimensionality as the data space, scaling up normalizing flows to high dimensional datasets is not straightforward. The prior L2LFlows approach successfully used a series of separate normalizing flows and sequence of conditioning steps to circumvent this problem. In this work, we extend L2LFlows to simulate showers with a 9-times larger profile in the lateral direction. To achieve this, we introduce convolutional layers and U-Net-type connections, move from masked autoregressive flows to coupling layers, and demonstrate the successful modelling of showers in the ILD Electromagnetic Calorimeter as well as Dataset 3 from the public CaloChallenge dataset.

Instruments & Instrumentation↗

Micromechanical Surrogate Machine Learning Model for Creep Deformation Modeling

Process variability during the manufacture of gas turbine engine hot section components can significantly affect the material’s resulting microstructure. In casting, for instance, geometric variation within a component (thin sections versus thick sections, radial location) influences cooling rates and the resulting grain size. The high temperature creep response is known to be sensitive to grain size owing to a diffusional creep mechanism which occurs more readily along grain boundaries. Microstructural variation correspondingly drives mechanical behavior which propagates into component scale performance uncertainty. These factors are essential when planning inspection, maintenance, and repair strategies within a reliability framework. These benefits provide opportunities to increase overall energy efficiency through refined margins. Critically, there is an opportunity to bolster existing data-driven reliability models using physics-driven process-structure-property relations. Here we present recent work establishing a framework for evaluating the probabilistic creep performance of high-temperature materials. A novel microstructure-sensitive crystal plasticity finite element model is established that captures both grain boundary and crystallographic deformation effects. The computationally expensive physics model is calibrated using a statistical approach and this high-fidelity model is subsequently used to train a computationally efficient machine learning surrogate model. The surrogate model is essential for sampling a large ensemble of simulated structure-property pair results. The ensemble data are then mined to extract salient trends to be incorporated into a microstructure-sensitive reliability model. The proposed approach represents a novel way to capture microstructure-sensitive trends from physics-based models within a modern reliability framework.

Fernandez-Zelaia, Patxi [ORNL]↗

A comparison of surrogate constitutive models for viscoplastic creep simulation of HT-9 steel

Mechanistic microstructure-informed constitutive models for the mechanical response of polycrystals are a cornerstone of computational materials science. However, as these models become increasingly more complex – often involving coupled differential equations describing the effect of specific deformation modes – their associated computational costs can become prohibitive, particularly in optimization or uncertainty quantification tasks that require numerous model evaluations. To address this challenge, surrogate constitutive models that balance accuracy and computational efficiency are highly desirable. Data-driven surrogate models, that learn the constitutive relation directly from data, have emerged as a promising solution. In this work, we develop two local surrogate models for the viscoplastic response of a steel: a piecewise response surface method and a mixture of experts model. These surrogates are designed to adapt to complex material behavior, which may vary with material parameters or operating conditions. The surrogate constitutive models are applied to creep simulations of HT-9 steel, an alloy of considerable interest to the nuclear energy sector due to its high tolerance to radiation damage, using training data generated from viscoplastic self-consistent (VPSC) simulations. In conclusion, we define a set of test metrics to numerically assess the accuracy of our surrogate models for predicting viscoplastic material behavior, and show that the mixture of experts model outperforms the piecewise response surface method in terms of accuracy.

36 MATERIALS SCIENCE↗

A Framework for Deep Learning Emulation of Numerical Models With a Case Study in Satellite Remote Sensing

Numerical models based on physics represent the state of the art in Earth system modeling and comprise our best tools for generating insights and predictions. Despite rapid growth in computational power, the perceived need for higher model resolutions overwhelms the latest generation computers, reducing the ability of modelers to generate simulations for understanding parameter sensitivities and characterizing variability and uncertainty. Thus, surrogate models are often developed to capture the essential attributes of the full-blown numerical models. Recent successes of machine learning methods, especially deep learning (DL), across many disciplines offer the possibility that complex nonlinear connectionist representations may be able to capture the underlying complex structures and nonlinear processes in Earth systems. A difficult test for DL-based emulation, which refers to function approximation of numerical models, is to understand whether they can be comparable to traditional forms of surrogate models in terms of computational efficiency while simultaneously reproducing model results in a credible manner. A DL emulation that passes this test may be expected to perform even better than simple models with respect to capturing complex processes and spatiotemporal dependencies. Here, we examine, with a case study in satellite-based remote sensing, the hypothesis that DL approaches can credibly represent the simulations from a surrogate model with comparable computational efficiency. Our results are encouraging in that the DL emulation reproduces the results with acceptable accuracy and often even faster performance. We discuss the broader implications of our results in light of the pace of improvements in high-performance implementations of DL and the growing desire for higher resolution simulations in the Earth sciences.

Bayesian Deep Learning↗

Closing in on Hydrologic Predictive Accuracy: Combining the Strengths of High-Fidelity and Physics-Agnostic Models

Applications of process-based models (PBM) for predictions are confounded by multiple uncertainties and computational burdens, resulting in appreciable errors. A novel modeling framework combining a high-fidelity PBM with surrogate and machine learning (ML) models is developed to tackle these challenges and applied for streamflow prediction. A surrogate model permits high computational efficiency of a PBM solution at a minimum loss of its accuracy. A novel probabilistic ML model partitions the PBM-surrogate prediction errors into reducible and irreducible types, quantifying their distributions that arise due to both explicitly perceived uncertainties (such as parametric) or those that are entirely hidden to the modeler (not included or unexpected). Using this approach, we demonstrate a substantial improvement of streamflow predictive accuracy for a case study urbanized watershed. Such a framework provides an efficient solution combining the strengths of high-fidelity and physics-agnostic models for a wide range of prediction problems in geosciences.

58 GEOSCIENCES↗