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 163 records · Page 9

Prediction of Stiffness and Fatigue Lives of Polymer Matrix Composite Laminates Using Artificial Neural Networks

Machine learning (ML) models are increasingly being used in many engineering fields due to the advancements in ML algorithms and availability of high-speed computing power. One of the most popular ML class of models is artificial neural networks (ANN). ML is increasingly being used in the design and analysis of composite materials and structures, specifically in the constitutive modeling of composite materials with the focus on greatly accelerating multiscale analyses of composite materials and structures through development of surrogate models. Towards that end, both Python and MATLAB-based neural nets have been developed to predict initial stiffness and fatigue life of an eight-ply symmetric polymer matrix composite laminate. Two types of neural networks, a Multilayer Perceptron (MLP) and a Recurrent Neural Network (RNN), have been developed for both platforms. Results show that the both neural net types can provide an excellent estimate of initial stiffness as well as fatigue life of eight-ply symmetric polymer matrix composite laminate. RNNs are better able to capture the shape of the fatigue curve of a laminate. This tool can be very useful for system level studies to obtain an estimate of desired properties and life of PMC composite laminates. The associated surrogate models could also be used in composite multiscale analyses to replace the actual physics-based calculations at lower scales and thereby significantly increase the computational efficiency of such analyses and thus make multiscale analyses a viable industrial tool for large scale structural problems.

Composite↗

Stiffness and Fatigue Life Estimator for Polymer Composite Laminates Using Machine Learning

Machine learning (ML) models are increasingly being used in many engineering fields due to the advancements in ML algorithms and availability of high-speed computing power. One of the most popular ML class of models is artificial neural networks (ANN). ML is increasingly being used in the design and analysis of composite materials and structures, specifically in the constitutive modeling of composite materials with the focus on greatly accelerating multiscale analyses of composite materials and structures through development of surrogate models. Towards that end, Python-based neural nets have been developed to predict initial stiffness and fatigue life of an eight-ply symmetric polymer matrix composite laminate. Two types of neural networks, a Multilayer Perceptron (MLP) and a Recurrent Neural Network (RNN), have been established. Results show that both neural net type algorithms can provide an excellent estimate of initial laminate stiffness as well as fatigue life of eight-ply symmetric polymer matrix composite laminates (PMCs). RNNs are better able to capture the shape of the fatigue curve of a laminate. The resulting tool and GUI can be very useful for system level studies to obtain an estimate of desired properties and life of PMC composite laminates. Further, the associated surrogate models can also be used in composite multiscale analyses to replace the actual physics-based calculations at lower scales and thereby significantly increase the computational efficiency of such analyses and thus make micromechanics-based multiscale analyses a viable industrial tool for large scale structural problems.

multiscale analysis↗

Stiffness and Fatigue Life Estimator for Polymer Composite Laminates Using Machine Learning

Machine learning (ML) models are increasingly being used in many engineering fields due to the advancements in ML algorithms and availability of high-speed computing power. One of the most popular ML class of models is artificial neural networks (ANN). ML is increasingly being used in the design and analysis of composite materials and structures, specifically in the constitutive modeling of composite materials with the focus on greatly accelerating multiscale analyses of composite materials and structures through development of surrogate models. Towards that end, Python-based neural nets have been developed to predict initial stiffness and fatigue life of an eight-ply symmetric polymer matrix composite laminate. Two types of neural networks, a Multilayer Perceptron (MLP) and a Recurrent Neural Network (RNN), have been established. Results show that both neural net type algorithms can provide an excellent estimate of initial laminate stiffness as well as fatigue life of eight-ply symmetric polymer matrix composite laminates (PMCs). RNNs are better able to capture the shape of the fatigue curve of a laminate. The resulting tool and GUI can be very useful for system level studies to obtain an estimate of desired properties and life of PMC composite laminates. Further, the associated surrogate models can also be used in composite multiscale analyses to replace the actual physics-based calculations at lower scales and thereby significantly increase the computational efficiency of such analyses and thus make micromechanics-based multiscale analyses a viable industrial tool for large scale structural problems.

multiscale analysis↗

Efficient evaluation of small failure probability in high-dimensional groundwater contaminant transport modeling via a two-stage Monte Carlo method

In decision-making for groundwater management and contamination remediation, it is important to accurately evaluate the probability of the occurrence of a failure event. For small failure probability analysis, a large number of model evaluations are needed in the Monte Carlo (MC) simulation, which is impractical for CPU-demanding models. One approach to alleviate the computational cost caused by the model evaluations is to construct a computationally inexpensive surrogate model instead. However, using a surrogate approximation can cause an extra error in the failure probability analysis. Furthermore, constructing accurate surrogates is challenging for high-dimensional models, i.e., models containing many uncertain input parameters. To address these issues, we propose an efficient two-stage MC approach for small failure probability analysis in high-dimensional groundwater contaminant transport modeling. In the first stage, a low-dimensional representation of the original high-dimensional model is sought with Karhunen–Loève expansion and sliced inverse regression jointly, which allows for the easy construction of a surrogate with polynomial chaos expansion. Then a surrogate-based MC simulation is implemented. In the second stage, the small number of samples that are close to the failure boundary are re-evaluated with the original model, which corrects the bias introduced by the surrogate approximation. The proposed approach is tested with a numerical case study and is shown to be 100 times faster than the traditional MC approach in achieving the same level of estimation accuracy.

54 ENVIRONMENTAL SCIENCES↗

Comparisons of Mixing Efficiency for the Strut Fuel Injector Obtained from Large-Eddy and Reynolds-Averaged Simulations, and Experiments

Mixing efficiency is obtained for a strut fuel injector at hypervelocity flow conditions by using large-eddy simulations (LES), Reynolds-averaged simulations (RAS), and experiments. The injector and flow conditions have been previously investigated by using RAS and experiments as a part of the Enhanced Injection and Mixing Project (EIMP) at the NASA Langley Research Center (LaRC). Because the fidelity of LES is a strong function of the grid, the mixing efficiency is obtained on two grids, the coarser of which is a factor of two coarser in each of the three dimensions with respect to the fine grid. The RAS uses the two-equation linear eddy viscosity and diffusivity modeling of Menter. In RAS, the species diffusivity model exhibits a strong dependence on the turbulent Schmidt number, which is often adjusted until some metric of engineering interest, such as the mixing efficiency, matches the experimental data. In the absence of experimental data, scale-resolving simulations, such as LES, have been proposed as surrogates for experiments that could provide the data needed to “calibrate” the turbulent Schmidt number in the RAS models. This approach is followed because LES requires significantly more computational resources (CPU, data storage, and time) than RAS, making it prohibitive for use in many engineering applications and specifically for parameter exploration or optimization. Here we examine the mixing efficiency obtained from several RAS with different values of the turbulent Schmidt number, and compare the results with those obtained from the LES and experiments. In addition, the least squares fitting approach was used to demonstrate how to obtain an estimate for the turbulent Schmidt number from LES analytically. These estimates were then used together with prior knowledge about RAS model sensitivity to select a turbulence model that was expected to best match the LES data.

LES↗

Comparisons of Mixing Efficiency for the Strut Fuel Injector Obtained from Large-Eddy and Reynolds-Averaged Simulations, and Experiments

Mixing efficiency is obtained for a strut fuel injector at hypervelocity flow conditions by using large-eddy simulations (LES), Reynolds-averaged simulations (RAS), and experiments. The injector and flow conditions have been previously investigated by using RAS and experiments as a part of the Enhanced Injection and Mixing Project (EIMP) at the NASA Langley Research Center (LaRC). Because the fidelity of LES is a strong function of the grid, the mixing efficiency is obtained on two grids, the coarser of which is a factor of two coarser in each of the three dimensions with respect to the fine grid. The RAS uses the two-equation linear eddy viscosity and diffusivity modeling of Menter. In RAS, the species diffusivity model exhibits a strong dependence on the turbulent Schmidt number, which is often adjusted until some metric of engineering interest, such as the mixing efficiency, matches the experimental data. In the absence of experimental data, scale-resolving simulations, such as LES, have been proposed as surrogates for experiments that could provide the data needed to “calibrate” the turbulent Schmidt number in the RAS models. This approach is followed because LES requires significantly more computational resources (CPU, data storage, and time) than RAS, making it prohibitive for use in many engineering applications and specifically for parameter exploration or optimization. Here we examine the mixing efficiency obtained from several RAS with different values of the turbulent Schmidt number, and compare the results with those obtained from the LES and experiments. In addition, the least squares fitting approach was used to demonstrate how to obtain an estimate for the turbulent Schmidt number from LES analytically. These estimates were then used together with prior knowledge about RAS model sensitivity to select a turbulence model that was expected to best match the LES data.

LES↗

GenAI4UQ: A software for forward and inverse uncertainty quantification using conditional generative AI

We introduce GenAI4UQ, a software package for forward and inverse uncertainty quantification in model calibration, parameter estimation, and ensemble forecasting. GenAI4UQ leverages a generative AI-based conditional modeling framework to address limitations of traditional inverse modeling techniques, such as Markov Chain Monte Carlo (MCMC) methods. By replacing computationally intensive iterative processes with a direct, learned mapping, GenAI4UQ enables efficient calibration of input parameters and generation of predictions directly from observations. The software supports rapid ensemble forecasting with robust uncertainty quantification while maintaining computational and storage efficiency. Built-in auto-tuning of hyperparameters simplifies model training, ensuring accessibility for users with varying expertise. Its versatile conditional generative framework is applicable across diverse scientific domains. While GenAI4UQ offers significant advantages in flexibility and efficiency, users should interpret its uncertainty estimates with caution in data-sparse scenarios, as the model may overestimate uncertainty—an effect common to all surrogate-based approaches including MCMC with surrogate models. Despite this, GenAI4UQ transforms inverse modeling by providing a fast, reliable, and user-friendly solution. It empowers researchers and practitioners to quickly estimate parameter distributions and generate model predictions for new observations, facilitating efficient decision-making and advancing the state of uncertainty quantification in computational modeling.

97 MATHEMATICS AND COMPUTING↗

Efficient Monte Carlo event generation for neutrino-nucleus exclusive cross sections

Modern neutrino-nucleus cross section computations need to incorporate sophisticated nuclear models to achieve greater predictive precision. However, the computational complexity of these advanced models often limits their practicality for experimental analyses. To address this challenge, we introduce a new Monte Carlo method utilizing normalizing flows to generate surrogate cross sections that closely approximate those of the original model while significantly reducing computational overhead. As a case study, we built a Monte Carlo event generator for the neutrino-nucleus cross section model developed by the Ghent group. This model employs a Hartree-Fock procedure to establish a quantum mechanical framework in which both the bound and scattering nucleon states are solutions to the mean-field nuclear potential. The surrogate cross sections generated by our method demonstrate excellent accuracy with a relative effective sample size of more than 98.4%, providing a computationally efficient alternative to traditional Monte Carlo sampling methods for differential cross sections.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Surrogate Modeling and Optimization of a Combustor with an Interdigitated Flushwall Injector

Design and Analysis of Computer Experiments (DACE) methods are applied and used to perform surrogate modeling and optimization of a simplified combustor flowpath with an interdigitated flushwall injector. The objectives of the optimization are the thrust potential and combustion efficiency, which are evaluated across a range of flight Mach numbers, duct heights, spanwise spacings, and injection angles. The focus of this work is to highlight the application of a sequential learning approach, in order to learn about the responses of the objective functions over the design space and to identify local regions of interest for further analysis. This approach is contrasted to a previous effort where only a single sampling set was used to fit surrogate models and perform optimization. The optimal solutions resulting from the previous and present approaches are different, due to surrogate model-guided local refinement of the design space allowed by the sequential learning method. The values of the global error estimates between the previous and present approaches are comparable, but the sequential method proved more computationally cost-effective. Further refinement in the optimal regions might be needed to improve predictive capability of surrogate models and to obtain the optimal solutions sets.

Rajiv R Shenoy↗

Gradient-based optimization for regression in the functional tensor-train format

Predictive analysis of complex computational models, such as uncertainty quantification (UQ), must often rely on using an existing database of simulation runs. In this paper we consider the task of performing low-multilinear-rank regression on such a database. Specifically we develop and analyze an efficient gradient computation that enables gradient-based optimization procedures, including stochastic gradient descent and quasi-Newton methods, for learning the parameters of a functional tensor-train (FT). We compare our algorithms with 22 other nonparametric and parametric regression methods on 10 real-world data sets and show that for many physical systems, exploiting low-rank structure facilitates efficient construction of surrogate models. Here, we use a number of synthetic functions to build insight into behavior of our algorithms, including the rank adaptation and group-sparsity regularization procedures that we developed to reduce overfitting. Finally we conclude the paper by building a surrogate of a physical model of a propulsion plant on a naval vessel.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Scalable training of graph convolutional neural networks for fast and accurate predictions of HOMO-LUMO gap in molecules

Abstract Graph Convolutional Neural Network (GCNN) is a popular class of deep learning (DL) models in material science to predict material properties from the graph representation of molecular structures. Training an accurate and comprehensive GCNN surrogate for molecular design requires large-scale graph datasets and is usually a time-consuming process. Recent advances in GPUs and distributed computing open a path to reduce the computational cost for GCNN training effectively. However, efficient utilization of high performance computing (HPC) resources for training requires simultaneously optimizing large-scale data management and scalable stochastic batched optimization techniques. In this work, we focus on building GCNN models on HPC systems to predict material properties of millions of molecules. We use HydraGNN, our in-house library for large-scale GCNN training, leveraging distributed data parallelism in PyTorch. We use ADIOS, a high-performance data management framework for efficient storage and reading of large molecular graph data. We perform parallel training on two open-source large-scale graph datasets to build a GCNN predictor for an important quantum property known as the HOMO-LUMO gap. We measure the scalability, accuracy, and convergence of our approach on two DOE supercomputers: the Summit supercomputer at the Oak Ridge Leadership Computing Facility (OLCF) and the Perlmutter system at the National Energy Research Scientific Computing Center (NERSC). We present our experimental results with HydraGNN showing (i) reduction of data loading time up to 4.2 times compared with a conventional method and (ii) linear scaling performance for training up to 1024 GPUs on both Summit and Perlmutter.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Enabling High-Dimensional Hierarchical Uncertainty Quantification by ANOVA and Tensor-Train Decomposition

Hierarchical uncertainty quantification can reduce the computational cost of stochastic circuit simulation by employing spectral methods at different levels. This paper presents an efficient framework to simulate hierarchically some challenging stochastic circuits/systems that include high-dimensional subsystems. Due to the high parameter dimensionality, it is challenging to both extract surrogate models at the low level of the design hierarchy and to handle them in the high-level simulation. In this paper, we develop an efficient analysis of variance-based stochastic circuit/microelectromechanical systems simulator to efficiently extract the surrogate models at the low level. In order to avoid the curse of dimensionality, we employ tensor-train decomposition at the high level to construct the basis functions and Gauss quadrature points. As a demonstration, we verify our algorithm on a stochastic oscillator with four MEMS capacitors and 184 random parameters. This challenging example is efficiently simulated by our simulator at the cost of only 10min in MATLAB on a regular personal computer.

ANOVA↗

Defect Diffusion Graph Neural Networks for Materials Discovery in High-Temperature Energy Applications

Here, the migration of crystallographic defects dictates material properties and performance for a plethora of technological applications. Density functional theory (DFT)-based nudged elastic band (NEB) calculations are a powerful computational technique for predicting defect migration activation energy barriers, yet they become prohibitively expensive for high-throughput screening of defect diffusivities. Without introducing hand-crafted (i.e., chemistry- or structure-specific) descriptors, we propose a generalized deep learning approach to train surrogate models for NEB energies of vacancy migration by hybridizing graph neural networks with transformer encoders and simply using pristine host structures as input. With sufficient training data, computationally efficient and simultaneous inference of vacancy defect thermodynamics and migration activation energies can be obtained to compute temperature-dependent vacancy diffusivities and to down-select candidates for more thorough DFT analysis or experiments. Thus, as we specifically demonstrate for potential water-splitting materials, candidates with desired defect thermodynamics, kinetics, and host stability properties can be more rapidly targeted from open-source databases of experimentally validated or hypothetical materials.

14 SOLAR ENERGY↗

Constructing a Simulation Surrogate with Partially Observed Output

Gaussian process surrogates are a popular alternative to directly using computationally expensive simulation models. When the simulation output consists of many responses, dimension-reduction techniques are often employed to construct these surrogates. However, surrogate methods with dimension reduction generally rely on complete output training data. This article proposes a new Gaussian process surrogate method that permits the use of partially observed output while remaining computationally efficient. The new method involves the imputation of missing values and the adjustment of the covariance matrix used for Gaussian process inference. The resulting surrogate represents the available responses, disregards the missing responses, and provides meaningful uncertainty quantification. In conclusion, the proposed approach is shown to offer sharper inference than alternatives in a simulation study and a case study where an energy density functional model that frequently returns incomplete output is calibrated.

42 ENGINEERING↗

Autonomous x-ray scattering

Autonomous experimentation (AE) is an emerging paradigm that seeks to automate the entire workflow of an experiment, including—crucially—the decision-making step. Beyond mere automation and efficiency, AE aims to liberate scientists to tackle more challenging and complex problems. We describe our recent progress in the application of this concept at synchrotron x-ray scattering beamlines. We automate the measurement instrument, data analysis, and decision-making, and couple them into an autonomous loop. We exploit Gaussian process modeling to compute a surrogate model and associated uncertainty for the experimental problem, and define an objective function exploiting these. We provide example applications of AE to x-ray scattering, including imaging of samples, exploration of physical spaces through combinatorial methods, and coupling to in situ processing platforms These uses demonstrate how autonomous x-ray scattering can enhance efficiency, and discover new materials.

77 NANOSCIENCE AND NANOTECHNOLOGY↗

Accelerating the design of lattice structures using machine learning

Lattices remain an attractive class of structures due to their design versatility; however, rapidly designing lattice structures with tailored or optimal mechanical properties remains a significant challenge. With each added design variable, the design space quickly becomes intractable. To address this challenge, research efforts have sought to combine computational approaches with machine learning (ML)-based approaches to reduce the computational cost of the design process and accelerate mechanical design. While these efforts have made substantial progress, significant challenges remain in (1) building and interpreting the ML-based surrogate models and (2) iteratively and efficiently curating training datasets for optimization tasks. Here, we address the first challenge by combining ML-based surrogate modeling and Shapley additive explanation (SHAP) analysis to interpret the impact of each design variable. We find that our ML-based surrogate models achieve excellent prediction capabilities (R 2 > 0.95) and SHAP values aid in uncovering design variables influencing performance. We address the second challenge by utilizing active learning-based methods, such as Bayesian optimization, to explore the design space and report a 5 × reduction in simulations relative to grid-based search. Collectively, these results underscore the value of building intelligent design systems that leverage ML-based methods for uncovering key design variables and accelerating design.

36 MATERIALS SCIENCE↗

Latent space mapping: Revolutionizing predictive models for divertor plasma detachment control

The inherent complexity of boundary plasma, characterized by multi-scale and multi-physics challenges, has historically restricted high-fidelity simulations to scientific research due to their intensive computational demands. Consequently, routine applications such as discharge control and scenario development have relied on faster but less accurate empirical methods. This work introduces DivControlNN, a novel machine-learning-based surrogate model designed to address these limitations by enabling quasi-real-time predictions (i.e., ~ 0.2 ms) of boundary and divertor plasma behavior. Trained on over 70,000 2D UEDGE simulations from KSTAR tokamak equilibria, DivControlNN employs latent space mapping to efficiently represent complex divertor plasma states, achieving a computational speed-up of over 10 8 compared to traditional simulations while maintaining a relative error below 20% for key plasma property predictions. During the 2024 KSTAR experimental campaign, a prototype detachment control system powered by DivControlNN successfully demonstrated detachment control on its first attempt, even for a new tungsten divertor configuration and without any fine-tuning. These results highlight the transformative potential of DivControlNN in overcoming diagnostic challenges in future fusion reactors by providing fast, robust, and reliable predictions for advanced integrated control systems.

Artificial neural networks↗

Uncertainty quantification for Multiphase-CFD simulations of bubbly flows: a machine learning-based Bayesian approach supported by high-resolution experiments

In this paper, we developed a machine learning-based Bayesian approach to inversely quantify and reduce the uncertainties of multiphase computational fluid dynamics (MCFD) simulations for bubbly flows. The proposed approach is supported by high-resolution two-phase flow measurements, including those by double-sensor conductivity probes, high-speed imaging, and particle image velocimetry. Local distributions of key physical quantities of interest (QoIs), including the void fraction and phasic velocities, are obtained to support the Bayesian inference. In the process, the epistemic uncertainties of the closure relations are inversely quantified while the aleatory uncertainties from stochastic fluctuations of the system are evaluated based on experimental uncertainty analysis. The combined uncertainties are then propagated through the MCFD solver to obtain uncertainties of the QoIs, based on which probability-boxes are constructed for validation. The proposed approach relies on three machine learning methods: feedforward neural networks and principal component analysis for surrogate modeling, and Gaussian processes for model form uncertainty modeling. The whole process is implemented within the framework of an open-source deep learning library PyTorch with graphics processing unit (GPU) acceleration, thus ensuring the efficiency of the computation. The results demonstrate that with the support of high-resolution data, the uncertainties of MCFD simulations can be significantly reduced. The proposed approach has the potential for other applications that involve numerical models with empirical parameters.

42 ENGINEERING↗