Search NASA⌕ Search

SEARCH · Search NASA

Results for “SURROGATE MODEL”

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 1,351 records · Page 75

Unified differentiable digital twin for the IOTA/FAST facility

As the design complexity of modern accelerators grows, there is more interest in using advanced simulations that have fast execution time or produce insights about accelerator state. One notable example of additional information are gradients of physical observables with respect to design parameters produced by differentiable simulations. The IOTA/FAST facility has recently begun a program to implement and experimentally validate a unified start-to-end differentiable digital twin to serve as a virtual accelerator test stand, allowing for rapid prototyping of new software and experiments with minimal beam time costs. In this contribution we will discuss our plans and progress. Specifically, we will cover the selection and benchmarking of both physics and ML codes, the development of generic interfaces between device models and surrogate or physics-based sections, and the export of the parameters through either a deterministic event loop or a fully asynchronous EPICS soft input/output controller. We will also discuss challenges in model calibration and uncertainty quantification, as well as future plans to support larger proton accelerators like PIPII and Booster.

Kuklev, Nikita [Fermilab]↗

Entropy-driven Optimal Sub-sampling of Fluid Dynamics for Developing Machine-learned Surrogates

Optimal sub-sampling of large datasets from fluid dynamics simulations is essential for training reduced-order machine learned models. A method using Shannon entropy was developed to weight flow features according to their level of information content, such that the most informative features can be extracted and used for training a surrogate model. The method is demonstrated in the canonical flow over a cylinder problem simulated with OpenFOAM. Both time-independent predictions and temporal forecasting were investigated as well as two types of prediction targets: local per-grid-point predictions and global per-time-step predictions. When tested on training a surrogate model, results indicate that our entropy-based sampling method typically outperforms random sampling and yields more reproducible results in less iterations. Finally, the method was used to train a surrogate model for modeling turbulence in magnetohydrodynamic flows, which revealed various challenges and opportunities for future research.

Brewer, Wes↗

Modeling and simulation of high dimensional stochastic multiscale PDE systems at the exascale

Predictive Modeling of multiscale and Multiphysics systems requires accurate data driven characterization of the input uncertainties, and understanding of how they propagate across scales and alter the final solution. This project develops a rigorous mathematical framework and scalable uncertainty quantification algorithms to efficiently construct realistic low dimensional input models, and surrogate low complexity systems for the analysis, design, and control of physical systems represented by multiscale stochastic PDEs. The work can be applied to many areas including physical and biological processes, from climate modeling to systems biology.

97 MATHEMATICS AND COMPUTING↗

Practical Multi-Cycle Refueling Simulation of Stable Salt Reactors Based on REBUS Depletion Calculation

A Python software tool ReloadPy has been developed to assistant in formulating online refueling strategies for a family of stable salt reactors. ReloadPy wraps over the legacy fast reactor analysis codes REBUS, DIF3D, and PERSENT. These codes are used to perform single cycle depletion analysis and calculate reactivity worth and power density. ReloadPy determines a refueling assembly position to achieve the user-specified primary objective while satisfying constraints on various performance parameters such as the maximum power density, the maximum reactivity worth of reloaded assembly, and the minimum cycle length. Various capabilities of prescribing refueling sequence or a range of candidate refueling positions and restarting a previous simulation with altered options are implemented to reduce the required user’s efforts to investigate different refueling strategies. This report presents the computational models and methods and also serves as a user guide. Long-term simulation capabilities with different refueling strategies are demonstrated by a series of sample SSR refueling calculations with two-dimensional surrogate core models.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Graph-Based Modeling for the Detection and Tracking of Sarin-Surrogate-Induced Neurotoxicity Using a Human-Relevant, In-Vitro Brain Model

Organophosphorus (OP) nerve agents are a chemical threat to the United States, to the civilian population (e.g., pesticides) and historically weaponized (e.g., sarin) as chemical warfare agents. The unprecedented, accelerated process from “bench-to-bedside” during the SARSCov2 pandemic has made it clear that technology and tools need to be readily available for immediate response. Advances in human organ tissue mimetic systems are a promising technology to evaluate the human-relevant response in vitro for basic and applied research and drug screening. In particular, current brain microphysiological systems (MPS) have the capability to monitor and detect changes in engineered human neural circuit activity. However, current data analytics approaches for these systems lack the granularity to functionally detect and distinguish the different mechanisms that occur in the brain following neurotoxicity, injury, and disease. The goal of this project was to advance the computational analytical capabilities of the brain MPS to detect functional changes in neural circuit structure at different stages of Sarin surrogate-induced neurotoxicity. We developed graph-based models to (1) identify the composition of the neural circuit structure; (2) detect and monitor how this structure changes following sarin-induced neurotoxicity; and (3) evaluate the analytical pipeline using known/promising oxime reactivators. Through experiments on the bMPS where in vitro neuronal cultures were exposed to a sarin surrogate, we demonstrated the capabilities of our computational pipeline to identify different responses in the functional networks of brain cells exposed to low and high concentrations of the nerve agent. We identified a biphasic response of human neural network activity following exposure to a sarin-surrogate that had not been reported in the literature before. The graph-based models and software developed in this project can be used for future studies that leverage the brain MPS technology, such as treatment efficacy assessment.

59 BASIC BIOLOGICAL SCIENCES↗

Creation of an Upper Stage Trajectory Capability Boundary to Enable Booster System Trade Space Exploration

The problem of trajectory optimization is important in all space missions. The solution of this problem enables one to specify the optimum thrust steering program which should be followed to achieve a specified mission objective, simultaneously satisfying the constraints.1 It is well known that whether or not the ascent trajectory is optimal can have a significant impact on propellant usage for a given payload, or on payload weight for the same gross vehicle weight.2 Consequently, ascent guidance commands are usually optimized in some fashion. Multi-stage vehicles add complexity to this analysis process as changes in vehicle properties in one stage propagate to the other stages through gear ratios and changes in the optimal trajectory. These effects can cause an increase in analysis time as more variables are added and convergence of the optimizer to system closure requires more analysis iterations. In this paper, an approach to simplifying this multi-stage problem through the creation of an upper stage capability boundary is presented. This work was completed as part of a larger study focused on trade space exploration for the advanced booster system that will eventually form a part of NASA s new Space Launch System.3 The approach developed leverages Design of Experiments and Surrogate Modeling4 techniques to create a predictive model of the SLS upper stage performance. The design of the SLS core stages is considered fixed for the purposes of this study, which results in trajectory parameters such as staging conditions being the only variables relevant to the upper stage. Through the creation of a surrogate model, which takes staging conditions as inputs and predicts the payload mass delivered by the SLS upper stage to a reference orbit as the response, it is possible to identify a "surface" of staging conditions which all satisfy the SLS requirement of placing 130 metric tons into low-Earth orbit (LEO).3 This identified surface represents the 130 metric ton capability boundary for the upper stage, such that if the combined first stage and boosters can achieve any one staging point on that surface, then the design is identified as feasible. With the surrogate model created, design and analysis of advanced booster concepts is streamlined, as optimization of the upper stage trajectory is no longer required in every design loop.

Walsh, Ptrick↗

Soyuz Landing Reconstructions

Introduction: Recent data show a landing-attributed injury rate among Soyuz crew members to be higher than predicted in original certification analysis. New vehicles being developed for NASA are being certified using analytical tools to quantify injury risk. This assessment will provide data to allow the Agency to evaluate whether these tools are able to capture true injury risk and allow a comparison between Soyuz landings and upcoming vehicles. Methods: A finite element model (FEM) of the Soyuz descent module (DM) and its landing environment were developed to recreate Soyuz landing conditions. Occupant breakout models composed of the Soyuz seat and Sokol helmet were then developed to evaluate occupant response. These models included both anthropomorphic test device (ATD) and human body model (HBM) surrogates in three anthropometric sizes. A generalized distribution analysis of the Soyuz landing environment was performed using landing variable distributions from available literature. Results were used to identify trends in vehicle landing acceleration with landing conditions and to compare landing model injury risk predictions with those estimated in vehicle certification analysis. Next, historic Soyuz landings identified as inducing occupant injury during were reconstructed using the developed landing model and estimated landing conditions. Results and Discussion: This assessment demonstrated the capability of certification metrics, which include a combination of vehicle- and occupant-level injury risk analysis, to identify elevated injury risk landing conditions. However, the developed landing load predictions were limited by available vehicle and landing condition data. Additional data, particularly landing acceleration data specific to historic Soyuz landing conditions, would greatly enhance this assessment’s findings.

Preston Greenhalgh↗

Improved Estimates of Air Pollutant Emissions from Biorefinery

We have attempted to use detailed kinetic modeling approach for improved estimation of combustion air pollutant emissions from biorefinery. We have developed a preliminary detailed reaction mechanism for biomass combustion. Lignin is the only biomass component included in the current mechanism and methane is used as the biogas surrogate. The model is capable of predicting the combustion emissions of greenhouse gases (CO2, N2O, CH4) and criteria air pollutants (NO, NO2, CO). The results are yet to be compared with the experimental data. The current model is still in its early stages of development. Given the acknowledged complexity of biomass oxidation, as well as the components in the feed to the combustor, obviously the modeling approach and the chemistry set discussed here may undergo revision, extension, and further validation in the future.

09 BIOMASS FUELS↗

Machine-Learning-Based Predictive Modeling of Glass Transition Temperatures: A Case of Polyhydroxyalkanoate Homopolymers and Copolymers

Polyhydroxyalkanoate-based polymers—being ecofriendly, biosynthesizable, and economically viable and possessing a broad range of tunable properties—are currently being actively pursued as promising alternatives for petroleum-based plastics. The vast chemical complexity accessible within this class of polymers gives rise to challenges in the rational discovery of novel polymer chemistries for specific applications. Here, the burgeoning field of polymer informatics addresses this challenge via providing tools and strategies for accelerated property prediction and materials design via surrogate machine-learning models built on reliable past data. In this contribution, we use glass transition temperature T g as an example target property to demonstrate promise of the data-enabled route to accelerated learning of accurate structure–property mappings in PHA-based polymers. Our analysis uses a data set of experimentally measured T g values, polymer molecular weights, and a polydispersity index for PHA-based homo- and copolymers that was carefully assembled from the literature. A fingerprinting scheme that captures key properties based on topology, shape, and charge/polarity of specific chemical units or motifs forming the polymer backbone was devised to numerically represent the polymers. A validated statistical learning model is then developed to allow for a mapping of the polymer fingerprints onto the property space in a physically meaningful and reliable manner. Once developed, the model can not only rapidly predict the property of new PHA polymers but also provide uncertainties underlying the predictions. The model is further combined with an evolutionary-algorithm-based search strategy to efficiently identify multicomponent polymer compositions with a prespecified T g . While the present contribution is focused specifically on T g , the surrogate model development approach put forward here is general and can, in principle, be extended to a range of other properties.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Hover and Forward Flight Performance Modeling of the Ingenuity Mars Helicopter

In 2015, NASA’s Jet Propulsion Laboratory partnered with Ames Research Center, Langley Research Center, and AeroVironment to develop Ingenuity, a small coaxial helicopter capable of flying within Mars’ unique atmospheric conditions. Ingenuity was successfully deployed from its protective shroud on the underside of the Mars 2020 Perseverance Rover and has flown 17 flights on Mars as of December 2021. A number of rotorcraft analysis tools were utilized, and a series of experimental tests were performed to ready Ingenuity for its launch with the Perseverance Rover in July 2020. In this paper, RotCFD, a Reynolds-averaged Navier-Stokes flow solver, is used to model Ingenuity in hover and forward flight for the purposes of validating tools to aid in the development of a future generation of Mars rotorcraft. The results from the RotCFD modeling are benchmarked against results from hover performance tests of the Ingenuity prototype in the 25-Foot Space Simulator at the Jet Propulsion Laboratory and are also compared to hover and forward flight predictions made by CAMRAD II, a well-known comprehensive rotorcraft analysis code. Surrogate performance models are trained to obtain a set of trimmed rotor settings for Ingenuity at different forward flight speeds, which are then used as inputs for the RotCFD forward flight simulations. Additionally, a study of the airframe-rotor interaction and a study of the aerodynamics of the individual airframe components of Ingenuity in forward flight are performed. Finally, to better understand performance predictions by RotCFD and CAMRAD II, a study is conducted on how sectional angles of attack in each code vary with radial station and azimuth.

Hover↗

Generalized Bayesian MARS: Tools for Stochastic Computer Model Emulation

The multivariate adaptive regression spline (MARS) approach of Friedman and its Bayesian counterpart are effective approaches for the emulation of computer models. The traditional assumption of Gaussian errors limits the usefulness of MARS, and many popular alternatives, when dealing with stochastic computer models. Here, we propose a generalized Bayesian MARS (GBMARS) framework which admits the broad class of generalized hyperbolic distributions as the induced likelihood function. This allows us to develop tools for the emulation of stochastic simulators which are parsimonious, scalable, and interpretable and require minimal tuning, while providing powerful predictive and uncertainty quantification capabilities. GBMARS is capable of robust regression with t distributions, quantile regression with asymmetric Laplace distributions, and a general form of “Normal-Wald” regression in which the shape of the error distribution and the structure of the mean function are learned simultaneously. We demonstrate the effectiveness of GBMARS on various stochastic computer models, and we show that it compares favorably to several popular alternatives.

97 MATHEMATICS AND COMPUTING↗

Development of advanced machine learning models for analysis of plutonium surrogate optical emission spectra

This work investigates and applies machine learning paradigms seldom seen in analytical spectroscopy for quantification of gallium in cerium matrices via processing of laser-plasma spectra. Ensemble regressions, support vector machine regressions, Gaussian kernel regressions, and artificial neural network techniques are trained and tested on cerium-gallium pellet spectra. A thorough hyperparameter optimization experiment is conducted initially to determine the best design features for each model. The optimized models are evaluated for sensitivity and precision using the limit of detection (LoD) and root mean-squared error of prediction (RMSEP) metrics, respectively. Gaussian kernel regression yields the superlative predictive model with an RMSEP of 0.33% and an LoD of 0.015% for quantification of Ga in a Ce matrix. This study concludes that these machine learning methods could yield robust prediction models for rapid quality control analysis of plutonium alloys.

Rao, Ashwin P. (ORCID:0000000319312568)↗

Tuning a RANS k-e model for jet-in-crossflow simulations.

We develop a novel calibration approach to address the problem of predictive k e RANS simulations of jet-incrossflow. Our approach is based on the hypothesis that predictive k e parameters can be obtained by estimating them from a strongly vortical flow, specifically, flow over a square cylinder. In this study, we estimate three k e parameters, C%CE%BC, Ce2 and Ce1 by fitting 2D RANS simulations to experimental data. We use polynomial surrogates of 2D RANS for this purpose. We conduct an ensemble of 2D RANS runs using samples of (C%CE%BC;Ce2;Ce1) and regress Reynolds stresses to the samples using a simple polynomial. We then use this surrogate of the 2D RANS model to infer a joint distribution for the k e parameters by solving a Bayesian inverse problem, conditioned on the experimental data. The calibrated (C%CE%BC;Ce2;Ce1) distribution is used to seed an ensemble of 3D jet-in-crossflow simulations. We compare the ensemble's predictions of the flowfield, at two planes, to PIV measurements and estimate the predictive skill of the calibrated 3D RANS model. We also compare it against 3D RANS predictions using the nominal (uncalibrated) values of (C%CE%BC;Ce2;Ce1), and find that calibration delivers a significant improvement to the predictive skill of the 3D RANS model. We repeat the calibration using surrogate models based on kriging and find that the calibration, based on these more accurate models, is not much better that those obtained with simple polynomial surrogates. We discuss the reasons for this rather surprising outcome.

Lefantzi, Sophia↗

Microstructure modeling of nuclear structural materials: Recent progress and future directions

Modeling and simulation of microstructures are essential to understand the complex responses and behaviors of nuclear materials in extreme environments. The needs to assess the extended life operation as well as the growing interest in accelerating nuclear materials development and qualification have stimulated the use of high-fidelity multiscale models aided by empirical and ab initio data. This paper reviews the role of various models across different length and time scales in investigating irradiation effects on microstructure evolution and degradation, in particular the embrittlement caused by radiation induced or enhanced formation of nanoscale chemical heterogeneities. The strength and limitations of these models, including classical rate theories, cluster dynamics, phase-field methods, and atomistic models informed by ab initio energies, are discussed with seminal examples. Challenges regarding the lack of thermo-kinetic data and theoretical treatments considering chemical complexities and magnetic excitations, as well as the stabilizing effect by excess point defects in nuclear structural materials are presented, along with potential solutions based on ab initio informed surrogate energy models and statistical sampling by Monte Carlo simulations. Further, the review then highlights the opportunities to leverage the advantages of different methods by establishing hybrid models by shared variables or coupled codes and applications. Finally, the review concludes with forward-looking remarks on how the use of physics-based models can aid the improvement of machine-learning models of property degradation and vice versa.

36 MATERIALS SCIENCE↗

Machine Learned Empirical Numerical Integrator from Simulated Data

Recently, a number of state-of-the-art surrogate machine learning (ML) models have been designed for global weather and climate prediction, which have been trained using reanalysis data products. Reanalysis data products are constructed using numerical model simulations that combine numerical integration of partial differential equations and parameterization schemes. These products are typically only archived and made available using coarsened spatial and temporal resolutions. This study explores the impact of the numerical generation methods used to produce the training datasets and the temporal resolution of those datasets on machine learning surrogate models. Using the nonlinear vector autoregression (NVAR) machine as an explainable ML technique, simple dynamical systems are emulated with ML models trained on data produced by three classical numerical integration schemes. NVAR is validated as a skillful ML method, capable of producing accurate predictions and, more importantly, reconstructing both the underlying dynamics and the numerical integration scheme used to generate the training data. However, the machine fails to generalize predictions on unseen test data generated by different numerical integration schemes, despite the underlying dynamical system being the same. This result provides a word of caution for the growing field of machine learning emulation of weather and climate dynamics. Furthermore, we illustrate using NVAR that training on temporally coarsened data may increase the required complexity of ML models and potentially introduce new numerical challenges. Finally, we discover that empirical integration schemes with arbitrary time-stepping sizes can be constructed directly from the data, which implies a potential for the development of empirical numerical integration schemes.

54 ENVIRONMENTAL SCIENCES↗

Flow Reactor Study and Kinetic Model Development of HEFA-SPK and its Surrogate

In this work, we formulate a two-component surrogate for HEFA-SPK, incorporating aromatic or cycloalkane components, and develop reduced kinetic models for the surrogates to be used in high-performance computing simulations. The HEFA-SPK surrogate was selected and optimized based on the fuel's physical and combustion properties, including ignition delay times and flame speeds. The resulting surrogate consists of 40% n-undecane and 60% 2-methylnonane. The surrogate was confirmed by flow reactor experiments for both the HEFA-SPK fuel and the suggested two-component surrogates, where excellent agreement was observed. To meet aromatic requirements, 1,2,4-trimethylbenzene (8%) was selected, and we determined that incorporating 30% propylcyclohexane into the HEFA-SPK will achieve a volume swell equivalent to 8% aromatics. The properties of the surrogates were measured, and a new reduced kinetic model was developed based on the semi-decoupling methodology, using a reduced CH4 chemistry from NUIG 1.0 as base chemistry. Kinetic models will be employed in combustor simulations to enable a comprehensive understanding of the effect of SAF fuel properties on aviation combustor performance.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

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

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

97 MATHEMATICS AND COMPUTING↗