Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Surrogate Models”

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 1,279 records · Page 71

ZEM: Integrated Framework for Real-Time Data and Model Analyses for Robust Environmental Management Decision Making - 16438

Typically environmental management (EM) problems require analysis of large and complex data sets originating from concurrent data streams with different data collection frequencies and pedigree. These big data sets require on-the-fly analysis, assimilation and integration into a series of models with different complexity for various types of model-based analyses. This is needed to provide fast iterative model analyses based on the latest available data to guide decision-making. Furthermore, the data and model are associated with uncertainties. The uncertainties are probabilistic (e.g. measurement errors) and non-probabilistic (unknowns, e.g. alternative conceptual models characterizing site conditions). To address all of these issues, we have developed an integrated framework for real-time data and model analyses for environmental decision-making called ZEM. The framework allows for seamless and on-the-fly integration of data and modeling results for robust and scientifically-defensible decision-making applying advanced decision analyses tools such as Bayesian-Information-Gap Decision Theory (BIG-DT). The framework also includes advanced methods for optimization that are capable of dealing with a large number of unknown model parameters, and surrogate (reduced order) modeling capabilities based on support vector regression techniques. The framework is predominantly coded in Julia, a state-of-the-art high-performance programing language (http://julialang.org) and incorporates the MADS computational tools (Model Analysis and Decision Support; http://mads.lanl.gov). We demonstrate the application of ZEM for data and model analyses at the LANL Chromium site. The ZEM framework will be released as open-source code and can be applied to any environmental management site. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

A Gaussian process based surrogate approach for the optimization of cylindrical targets

Simulating direct-drive inertial confinement experiments presents significant computational challenges, both due to the complexity of the codes required for such simulations and the substantial computational expense associated with target design studies. Machine learning models, and in particular, surrogate models, offer a solution by replacing simulation results with a simplified approximation. In this study, we apply surrogate modeling and optimization techniques that are well established in the existing literature to one-dimensional simulation data of a new cylindrical target design containing deuterium–tritium fuel. These models predict yields without the need for expensive simulations. We find that Bayesian optimization with Gaussian process surrogates enhances sampling efficiency in low-dimensional design spaces but becomes less efficient as dimensionality increases. Nonetheless, optimization routines within two-dimensional and five-dimensional design spaces can identify designs that maximize yield, while also aligning with established physical intuition. Optimization routines, which ignore constraints on hydrodynamic instability growth, are shown to lead to unstable designs in 2D, resulting in yield loss. However, routines that utilize 1D simulations and impose constraints on the in-flight aspect ratio converge on novel cylindrical target designs that are stable against hydrodynamic instability growth in 2D and achieve high yield.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Machine learning-enhanced model-based scenario optimization for DIII-D

Abstract Scenario development in tokamaks is an open area of investigation that can be approached in a variety of different ways. Experimental trial and error has been the traditional method, but this required a massive amount of experimental time and resources. As high fidelity predictive models have become available, offline development and testing of proposed scenarios has become an option to reduce the required experimental resources. The use of predictive models also offers the possibility of using a numerical optimization process to find the controllable inputs that most closely achieve the desired plasma state. However, this type of optimization can require as many as hundreds or thousands of predictive simulation cases to converge to a solution; many of the commonly used high fidelity models have high computational burdens, so it is only reasonable to run a handful of predictive simulations. In order to make use of numerical optimization approaches, a compromise needs to be found between model fidelity and computational burden. This compromise can be achieved using neural networks surrogates of high fidelity models that retain nearly the same level of accuracy as the models they are trained to replicate while reducing the computation time by orders of magnitude. In this work, a model-based numerical optimization tool for scenario development is described. The predictive model used by the optimizer includes neural network surrogate models integrated into the fast Control-Oriented Transport simulation framework. This optimization scheme is able to converge to the optimal values of the controllable inputs that produce the target plasma scenario by running thousands of predictive simulations in under an hour without sacrificing too much prediction accuracy.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Online Learning of Effective Turbine Wind Speed in Wind Farms

To develop better wind farm controllers that can meet more complex objectives, methods of modeling the wind turbine wakes at low computational expense are needed. Gaussian process (GP) regression offers a computationally inexpensive framework for learning complex functions from noisy measurements with very few datapoints. In this work, an online learning approach is presented to learn the rotor-averaged wind velocity at downstream wind turbines with GPs, using the available datastream of wind field measurements and wind turbine control set-points. This framework can readily be integrated into model-based controls methods because the model a) is updated online at low computational expense, b) assumes a mathematically favorable Gaussian form, and c) explicitly quantifies the stochastic nature of the wake field so that the trade-off between exploration and exploitation, and the uncertainty in the prediction, can be utilized. We show that a GP-learned model can match true values with errors within 0.5% on average, with as few as 5 training data points.

Gaussian process↗

Explainable and Differentiable Reinforcement Learning for Multi-objective Optimization in Particle Accelerators

Operating particle accelerators involves optimizing multiple goals simultaneously, which can be challenging due to trade-offs among objectives. While evolutionary algorithms like the genetic algorithm (GA) have been used for various Multi-Objective Optimization (MOO) tasks, they are not inherently suited for complex control problems. This talk highlights two variations of Reinforcement Learning (RL) for concurrently optimizing heat load and trip rates at the Continuous Electron Beam Accelerator Facility (CEBAF). The problem involves strict constraints on individual states, actions, and overall energy requirements of the beam. First, this talk highlights how differentiability can be harnessed through a Deep Differentiable Reinforcement Learning (DDRL) approach to address MOO issues within particle accelerators. We examine the DDRL method alongside Model Free Reinforcement Learning (MFRL), GA, and Bayesian Optimization (BO). The performance of these methods is assessed by generating a Pareto-front for two objectives. Our findings indicate that DDRL excels in handling high-dimensional problems more effectively than MFRL, BO, and GA. Next, we will show integration of explainable physics-based constraints into RL algorithms to enhance trans- parency and trust in decision-making processes by enabling users to verify that agents adhere to established physical principles. This surrogate function can be modeled using neural networks or sparse dictionary mod- els. By examining the mathematical form of the learned constraint function, we are able to confirm the agent has learned to use the established physics of each environment provided but the surrogate model. In addi- tion, we find that the introduction of a mathematical functional dictionary based surrogate model enables our reinforcement learning algorithms to reliably converge for difficult high-dimensional accelerator controls environments.

Rajput, Kishansingh [Thomas Jefferson National Acc↗

PINNSTRIPES (Physics-Informed Neural Network SurrogaTe for Rapidly Identifying Parameters in Energy Systems) [SWR-22-12]

Energy systems models typically take the form of complex partial differential equations which make multiple forward calculations prohibitively expensive. Fast and data-efficient construction of surrogate models is of utmost importance for applications that require parameter exploration such as design optimization and Bayesian calibration. In presence of a large number of parameters, surrogate models that capture correct dependencies may be difficult to construct with traditional techniques. The issue is addressed here with the formulation of the surrogate model constructed via Physics-Informed Neural Networks (PINN) which capture the dependence with respect to the parameters to estimate, while using a limited amount of data. Since forward evaluations of the surrogate model are cheap, parameter exploration is made inexpensive, even when considering a large number of parameters.

Hassanaly, Malik↗

On the use of air temperature and precipitation as surrogate predictors in soil respiration modelling

Soil respiration (R S ), the soil-to-atmosphere CO 2 flux that is a major component of the global carbon cycle, is strongly influenced by local soil temperature (T soil ) and water content (SWC). Regional to global-scale R S modelling thus requires this information at local scales, but few high-quality, wall-to-wall (global) T soil and SWC data exist. As a result, such modelling efforts commonly use air temperature (T air ) and monthly precipitation (P m ) as surrogate predictors, but their site-scale accuracy and potential bias are unknown. In this report we used monthly data from 880 sites across a wide variety of different environmental conditions (i.e., climate, ecosystem type, elevation, vegetation leaf habit and drainage conditions) to determine the suitability of T air as a surrogate for T soil , and data from 507 sites to examine the suitability of P m as a surrogate for SWC. Site-specific linear and second-order exponential non-linear models were compared using model evaluation metrics (i.e., slope, p-value of slope, root mean square error [RMSE], index of agreement and model efficiency). We found that T soil and T air are highly correlated and explain similar R S variability. In contrast, P m is not a good surrogate for SWC, even though P m explains a similar amount of R S variability to SWC. The wide variability in the site-specific relationships between R S and SWC means that no single relationship can be used for large-scale modelling. The results from this study support the use of T air in continental-to-global scale R S models, and highlight the urgent need for continental-to-global scale SWC datasets for the modelling and evaluation of future soil carbon dynamics under global climate change.

54 ENVIRONMENTAL SCIENCES↗

HCCI experiments with toluene reference fuels modeled by a semidetailed chemical kinetic model

A semidetailed mechanism (137 species and 633 reactions) and new experiments in a homogeneous charge compression ignition (HCCI) engine on the autoignition of toluene reference fuels are presented. Skeletal mechanisms for isooctane and n-heptane were added to a detailed toluene submechanism. The model shows generally good agreement with ignition delay times measured in a shock tube and a rapid compression machine and is sensitive to changes in temperature, pressure, and mixture strength. The addition of reactions involving the formation and destruction of benzylperoxide radical was crucial to modeling toluene shock tube data. Laminar burning velocities for benzene and toluene were well predicted by the model after some revision of the high-temperature chemistry. Moreover, laminar burning velocities of a real gasoline at 353 and 500 K could be predicted by the model using a toluene reference fuel as a surrogate. The model also captures the experimentally observed differences in combustion phasing of toluene/n-heptane mixtures, compared to a primary reference fuel of the same research octane number, in HCCI engines as the intake pressure and temperature are changed. For high intake pressures and low intake temperatures, a sensitivity analysis at the moment of maximum heat release rate shows that the consumption of phenoxy radicals is rate-limiting when a toluene/n-heptane fuel is used, which makes this fuel more resistant to autoignition than the primary reference fuel. Typical CPU times encountered in zero-dimensional calculations were on the order of seconds and minutes in laminar flame speed calculations. Cross reactions between benzylperoxy radicals and n-heptane improved the model predictions of shock tube experiments for {phi}=1.0 and temperatures lower than 800 K for an n-heptane/toluene fuel mixture, but cross reactions had no influence on HCCI simulations. (author)

33 ADVANCED PROPULSION SYSTEMS↗

Structure and Bonding Investigation of Plutonium Peroxocarbonate Complexes Using Cerium Surrogates and Electronic Structure Modeling

Herein, we report the synthesis and structural characterization of K8[(CO3)3Pu]2(µ-η2-η2-O2)2•12H2O. This is the second plutonium-containing addition to the previously studied alkali metal peroxo-carbonate series M8[(CO3)3A]2(µ-η2-η2-O2)2•xH2O (M = alkali metal; A = Ce or Pu; x = 8, 10, 12 or 18), for which only the M = Na analog has been previously reported when A = Pu. The previously reported crystal structure for Na8[(CO3)3Pu]2(µ-η2-η2-O2)2•12H2O is not isomorphous with its known Ce analogue. However, a new synthetic route to these M8[(CO3)3A]2(µ-η2-η2-O2)2•12H2O complexes, described below, has produced crystals of Na8[(CO3)3Ce]2(µ-η2-η2-O2)2•12H2O that are isomorphous with the previously reported Pu analogue. Via this synthetic method, the M = Na, K, Rb, and Cs salts of M8[(CO3)3Ce]2(µ-η2-η2-O2)2•xH2O have also been synthesized for systematic structural comparison with each other and the available Pu analogues using single-crystal X-ray diffraction, Raman spectroscopy and density functional theory (DFT) calculations. The cerium salts in particular demonstrate subtle differences in the peroxide bond lengths which correlate to Raman shifts for the peroxide Op–Op stretch (Op = the oxygen atoms of the peroxide bridges) with each of the cations studied: Na+ (1.492(3) Å /847 cm-1), Rb+ (1.471(1) Å /854 cm-1), Cs+ (1.474(1) Å /859 cm-1), and K+ (1.468(6) Å, 870 cm-1). The trends observed in the M–Op and Op–Op bond distances appear to relate to supermolecular interactions between the neighboring cations.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Online learning of quadratic manifolds from streaming data for nonlinear dimensionality reduction and nonlinear model reduction

Here, this work introduces an online greedy method for constructing quadratic manifolds from streaming data, designed to enable in situ analysis of numerical simulation data on the Petabyte scale. Unlike traditional batch methods, which require all data to be available upfront and take multiple passes over the data, the proposed online greedy method incrementally updates quadratic manifolds in one pass as data points are received, eliminating the need for expensive disk input/output operations as well as storing and loading data points once they have been processed. A range of numerical examples demonstrate that the online greedy method learns accurate quadratic manifold embeddings while being capable of processing data that far exceed common disk input/output capabilities and volumes as well as main-memory sizes.

97 MATHEMATICS AND COMPUTING↗