Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “inverse prediction methods”

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 73 records · Page 4
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Optimizing shift selection in multilevel Monte Carlo for disconnected diagrams in lattice QCD

The calculation of disconnected diagram contributions to physical signals is a computationally expensive task in Lattice QCD. To extract the physical signal, the trace of the inverse Lattice Dirac operator, a large sparse matrix, must be stochastically estimated. Because the variance of the stochastic estimator is typically large, variance reduction techniques must be employed. Multilevel Monte Carlo (MLMC) methods reduce the variance of the trace estimator by utilizing a telescoping sequence of estimators. Frequency Splitting is one such method that uses a sequence of inverses of shifted operators to estimate the trace of the inverse lattice Dirac operator, however there is no a priori way to select the shifts that minimize the cost of the multilevel trace estimation. Here we present a sampling and interpolation scheme that is able to predict the variances associated with Frequency Splitting under displacements of the underlying space time lattice. The interpolation scheme is able to predict the variances to high accuracy and therefore chooses shifts that correspond to an approximate minimum of the cost for the trace estimation. We show that Frequency Splitting with the chosen shifts displays significant speedups over multigrid deflation, and that these shifts can be used for multiple configurations within the same ensemble with no penalty to performance.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

ML-based Dimension Reduction Strategies

Deep learning (DL)--based surrogate models have achieved success in various applications in carbon capture and storage (CCS). However, the model training on high-dimensional spaces is computationally expensive and impractical for large-scale and complex geological models, because the models usually contain hundreds of thousands to millions of grid cells, each with a set of parameters. Furthermore, the high cost of generating training data with sufficient variation is another limitation of model training on high-dimensional spaces, which may result in overfitting and reduce the model efficiency and prediction performance. We proposed the workflow incorporating dimension reduction methods and deep learning models, which aim to extract the latent variables of input parameters and output state variables, and then build the mapping function at the latent spaces. The proposed workflow can significantly reduce the computational complexity in solving both forward and inverse problems compared to models trained on high-dimensional spaces. Dimensionality reduction models showed great potential in workflows for fast reservoir simulation, history matching, prior model generation, visualization, and more, ultimately enhancing DL model performance in related SMART Work Packages.

Hosseini, Seyyed↗
DOE OSTI2022

Interpolation as a means of shift selection for multilevel Monte Carlo with lattice displacements

The calculation of disconnected diagram contributions to physical signals is a computationally expensive task in Lattice QCD. To extract the physical signal, the trace of the inverse Lattice Dirac operator, a large sparse matrix, must be stochastically estimated. Because the variance of the stochastic estimator is typically large, variance reduction techniques must be employed. Multilevel Monte Carlo (MLMC) methods reduce the variance of the trace estimator by utilizing a telescoping sequence of estimators. Frequency Splitting is one such method that uses a sequence of inverses of shifted operators to estimate the trace of the inverse of the lattice Dirac operator, however there is no a priori way to select the shifts that minimize the cost of the multilevel trace estimation. We present a sampling and interpolation scheme that is able to predict the variances associated with Frequency Splitting under displacements of the underlying space time lattice. The interpolation scheme is able to predict the variances to high accuracy and therefore choose shifts that correspond to an approximate minimum of the cost for the trace estimation. We show that Frequency Splitting with the chosen shifts displays significant speedups over multigrid deflation

Whyte, Travis↗
DOE OSTI2025

Machine Learning-Driven Conservative-to-Primitive Conversion in Hybrid Piecewise Polytropic and Tabulated Equations of State

We present a novel machine learning (ML)-based method to accelerate conservative-to-primitive inversion, focusing on hybrid piecewise polytropic and tabulated equations of state. Traditional root-finding techniques are computationally expensive, particularly for large-scale relativistic hydrodynamics simulations. To address this, we employ feedforward neural networks (NNC2PS and NNC2PL), trained in PyTorch (2.0+) and optimized for GPU inference using NVIDIA TensorRT (8.4.1), achieving significant speedups with minimal accuracy loss. The NNC2PS model achieves 𝐿 1 and 𝐿 ∞ errors of 4.54 × 10 −7 and 3.44 × 10−6, respectively, while the NNC2PL model exhibits even lower error values. TensorRT optimization with mixed-precision deployment substantially accelerates performance compared to traditional root-finding methods. Specifically, the mixed-precision TensorRT engine for NNC2PS achieves inference speeds approximately 400 times faster than a traditional single-threaded CPU implementation for a dataset size of 1,000,000 points. Ideal parallelization across an entire compute node in the Delta supercomputer (dual AMD 64-core 2.45 GHz Milan processors and 8 NVIDIA A100 GPUs with 40 GB HBM2 RAM and NVLink) predicts a 25-fold speedup for TensorRT over an optimally parallelized numerical method when processing 8 million data points. Moreover, the ML method exhibits sub-linear scaling with increasing dataset sizes. We release the scientific software developed, enabling further validation and extension of our findings. By exploiting the underlying symmetries within the equation of state, these findings highlight the potential of ML, combined with GPU optimization and model quantization, to accelerate conservative-to-primitive inversion in relativistic hydrodynamics simulations.

conservative-to-primitive conversion↗
DOE OSTI2025

Resummation for lattice QCD calculation of generalized parton distributions at nonzero skewness

Large-momentum effective theory (LaMET) provides an approach to directly calculate the x-dependence of generalized parton distributions (GPDs) on a Euclidean lattice through power expansion and a perturbative matching. When a parton’s momentum becomes soft, the corresponding logarithms in the matching kernel become non-negligible at higher orders of perturbation theory, which requires a resummation. But the resummation for the off-forward matrix elements at nonzero skewness ξ is difficult due to their multi-scale nature. In this work, we demonstrate that these logarithms are important only in the threshold limit, and derive the threshold factorization formula for the quasi-GPDs in LaMET. We then propose an approach to resum all the large logarithms based on the threshold factorization, which is implemented on a GPD model. We demonstrate that the LaMET prediction is reliable for [−1 + x 0 , −ξ − x 0 ] ∪ [−ξ + x 0 , ξ − x 0 ] ∪ [ξ + x 0 , 1 − x 0 ], where x 0 is a cutoff depending on hard parton momenta. Through our numerical tests with the GPD model, we demonstrate that our method is self-consistent and that the inverse matching does not spread the nonperturbative effects or power corrections to the perturbatively calculable regions.

hadronic spectroscopy↗
DOE OSTI2024

Reactor antineutrino flux and anomaly

Reactor antineutrinos have played a significant role in establishing the standard model of particle physics and the theory of neutrino oscillations. In this article, we review the reactor antineutrino flux and in particular the reactor antineutrino anomaly (RAA) coined over a decade ago. RAA refers to a deficit of the measured antineutrino inverse beta decay rates at very short-baseline reactor experiments compared to the theoretically improved predictions (i.e. the Huber–Mueller model). Since the resolution of several previous experimental anomalies have led to the discovery of non-zero neutrino mass and mixing, many efforts have been invested to study the origin of RAA both experimentally and theoretically. The progress includes the observation of discrepancies in antineutrino energy spectrum between data and the Huber–Mueller model, the re-evaluation of the Huber–Mueller model uncertainties, the potential isotope-dependent rate deficits, and the better agreement between data and new model predictions using the improved summation method. Importantly, these developments disfavor the hypothesis of a light sterile neutrino as the explanation of RAA and supports the deficiencies of Huber–Mueller model as the origin. Looking forward, more effort from both the theoretical and experimental sides is needed to fully understand the root of RAA and to make accurate predictions of reactor antineutrino flux and energy spectrum for future discoveries.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Artificial Intelligence for Conjugated Polymers

Conjugated polymers have garnered significant attention due to their diverse applications in electronics, photonics, and energy storage. However, realizing their full potential poses a formidable challenge, as their design has historically relied on iterative adjustments and continuous inspiration from researchers. Traditional methods often struggle to efficiently navigate their vast chemical landscape. In this work, the application of artificial intelligence (AI), specifically machine learning (ML), needs to be discussed in the realm of conjugated polymers. Our paper emphasizes the importance of understanding the structure–property relationships of these polymers and how ML can facilitate property prediction and inverse-design. We delve into various chemical fingerprints, structural descriptors, and ML algorithms, showcasing their utility across a spectrum of applications, including simulations, glass transition temperature determination, photovoltaics, reorganization energy for charge transport, photocatalysts, and sensors. Finally, we give some outlooks in this filed and propose unexplored areas within the field that hold the potential to benefit from ML techniques.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Predicting Dynamic-to-Static Correction Factor from Petrophysical Data and Chemostratigraphy using Unsupervised Machine Learning

Estimating static mechanical properties of stratigraphic layers is critical for optimizing subsurface engineering applications. To estimate dynamic-to-static correction factor F ds (static-to-dynamic Young’s modulus ratio) across the Caney shale interval in Oklahoma, USA, we integrated triaxial test measurements and petrophysical data, including well logs and X-ray fluorescence (XRF) using unsupervised machine learning (ML). We used a novel workflow that includes principal component analysis (PCA) to reduce data set dimensionality of well logs and XRF data sets—both separately and combined—creating three scenarios, and later applied inverse distance weighting (IDW) to derive F ds profiles for these scenarios. Furthermore, we applied K-means clustering on each scenario to predict depositional facies, and built a stiffness zonation profile through chemostratigraphic analysis of the terrigenous elements to validate the predicted F ds . The predicted F ds profile from each scenario using the PCA-IDW method was compared with the constant F ds approach from our previous study by calculating the root mean square error (RMSE). The combined data sets scenario yielded the lowest RMSE value of 0.113, while the RMSE values for the well logs and XRF scenarios were 0.131 and 0.129, respectively. In addition, the predicted F ds from the XRF scenario well-matched the stiffness zonation from the chemostratigraphic analysis that was built using the optimized K-means clustering of nine clusters for that scenario. These methods and findings offer a valuable tool for refining lithological classification and improving the F ds profile, potentially enhancing drilling and stimulation strategies for subsurface energy engineering applications.

clastic rock↗
DOE OSTI2023

Integration of seismic-pressure-petrophysics inversion of continuous active-seismic monitoring data for monitoring and quantifying CO 2 plume (Final Report)

The overall objective of this project is to develop and validate an integrated package of joint seismic-pressure-petrophysics inversion (jSPPI) of continuous active-source seismic monitoring dataset capable of providing real-time monitoring of CO 2 plume during geologic carbon sequestration (GCS). The three specific developments include: (a) the methodologies for fast seismic full waveform inversion of continuous active source seismic monitoring, (CASSM) datasets for simultaneously estimating velocity and attenuation, and with data assimilation; (b) joint Bayesian petrophysical inversion of seismic models and pressure data for providing and updating CO 2 saturation models; (c) the methods using multiple datasets including (Crainfield and Frio-II borehole) synthetic, laboratory, and field CASSM datasets. The outcomes of jSPPI include (a) a workflow for processing CASSM data, (b) Bayesian inversion algorithms using CASSM data and pressure response data, and (c) integration with data assimilation algorithms for continuously updating site-specific models used for prediction and reservoir management. The validation of joint FWI will be conducted using synthetic models based on the Cranfield and Frio experiments as well as field CASSM datasets collected as part of the Frio-II pilot injection. To quantify and map the mass and distribution of CO 2 (saturation), we will jointly invert velocity and attenuation measurements from the FWI with a Bayesian approach using a rock physics model for attenuation (e.g., White’s attenuation model with two selected patch sizes (White, 1976; Dutta and Seriff, 1979)). The Bayesian inversion will be applied to each time step in the CASSM survey in an updating scheme, which integrates with an ensemble of reservoir simulations at each step. A more complete experimental validation dataset will be collected as part of a mesoscale (2-3 m) gas-CO 2 injection experiment utilizing a higher frequency version of the CASSM system developed for laboratory studies; the integrated inversion will be demonstrated using this dataset which will provide both a dense geometry as well as more precise secondary confirmation measurements (e.g. saturation) typically not available in the field. The resulting real-time map of CO 2 saturation is able to provide a deeper scientific understanding of the complex, time-varying dynamics of subsurface fluid flow migration path as well as the rapid detection of CO 2 leakage hazards.

25 ENERGY STORAGE↗
DOE OSTI2022

A combined experimental and numerical approach that eliminates the non-uniqueness associated with the Johnson-Cook parameters obtained using inverse methods

Abstract Johnson-Cook constitutive model is a commonly used material model for machining simulations. The model includes five parameters that capture the initial yield stress, strain-hardening, strain-rate hardening, and thermal softening behavior of the material. These parameters are difficult to determine using experiments since the conditions observed during machining (such as high strain-rates of the order of $$10^5$$ 10 5 /sec - $$10^6$$ 10 6 /sec) are challenging to recreate in the laboratory. To address this problem, several researchers have recently proposed inverse approaches where a combination of experiments and analytical models are used to predict the Johnson-Cook parameters. The errors between the measured cutting forces, chip thicknesses and temperatures and those predicted by analytical models are minimized and the parameters are determined. In this work, it is shown that only two of the five Johnson-Cook parameters can be determined uniquely using inverse approaches. Two different algorithms, namely, Adaptive Memory Programming for Global Optimization (AMPGO) and Particle Swarm Optimization (PSO), are used for this purpose. The extended Oxley’s model is used as the analytical tool for optimization. For determining a parameter’s value, a large range for each parameter is provided as an input to the algorithms. The algorithms converge to several different sets of values for the five Johnson-Cook parameters when all the five parameters are considered as unknown in the optimization algorithm. All of these sets, however, yield the same chip shape and cutting forces in FEM simulations. Further analyses show that only the strain-rate and thermal softening parameters can be determined uniquely and the three parameters present in the strain-hardening term of the Johnson-Cook model cannot be determined uniquely using the inverse method. A combined experimental and numerical approach is proposed to eliminate this determine all parameters uniquely.

42 ENGINEERING↗
DOE OSTI2022

Scaled Vecchia Approximation for Fast Computer-Model Emulation

Many scientific phenomena are studied using computer experiments consisting of multiple runs of a computer model while varying the input settings. Gaussian processes (GPs) are a popular tool for the analysis of computer experiments, enabling interpolation between input settings, but direct GP inference is computationally infeasible for large datasets. We adapt and extend a powerful class of GP methods from spatial statistics to enable the scalable analysis and emulation of large computer experiments. Specifically, we apply Vecchia’s ordered conditional approximation in a transformed input space, with each input scaled according to how strongly it relates to the computer-model response. The scaling is learned from the data by estimating parameters in the GP covariance function using Fisher scoring. Our methods are highly scalable, enabling estimation, joint prediction, and simulation in near-linear time in the number of model runs. In several numerical examples, our approach substantially outperformed existing methods.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Modeling hydrogen markets: Energy system model development status and decarbonization scenario results

Hydrogen can be used as an energy carrier and chemical feedstock to reduce greenhouse gas emissions, especially in difficult-to-decarbonize markets such as medium- and heavy-duty vehicles, aviation and maritime, iron and steel, and the production of fuels and chemicals. Significant literature has been accumulated on engineering-based assessments of various hydrogen technologies, and real-world projects are validating technology performance at larger scales and for low-carbon supply chains. While energy system models continue to be updated to track this progress, many are currently limited in their representation of hydrogen, and as a group they tend to generate highly variable results under decarbonization constraints. Here, the present work provides insights into the development status and decarbonization scenario results of 15 energy system models participating in study 37 of the Stanford Energy Modeling Forum (EMF37), focusing on the U.S. energy system. The models and scenario results vary widely in multiple respects: hydrogen technology representation, scope and type of hydrogen end-use markets, relative optimism of hydrogen technology input assumptions, and market uptake results reported for 2050 under various decarbonization assumptions. Most models report hydrogen market uptake increasing with decarbonization constraints, though some models report high carbon prices being required to achieve these increases and some find hydrogen does not compete well when assuming optimistic assumptions for all advanced decarbonization technologies. Across various scenarios, hydrogen market success tends to have an inverse relationship to success with direct air capture (DAC) and carbon capture and storage (CCS) technologies. While most model-scenario combinations predict modest hydrogen uptake by 2050 – <10 million metric tons (MMT) – aggregating the top 10 % of market uptake results across sectors suggests an upper range demand potential of 42–223 MMT. The high degree of variability across both modeling methods and market uptake results suggests that increased harmonization of both input assumptions and subsector competition scope would lead to more consistent results across energy system models. The wide variability in results indicates strongly divergent conclusions on the role of hydrogen in a decarbonized energy future.

08 HYDROGEN↗
DOE OSTI2022

Inferring topological transitions in pattern-forming processes with self-supervised learning

Abstract The identification of transitions in pattern-forming processes are critical to understand and fabricate microstructurally precise materials in many application domains. While supervised methods can be useful to identify transition regimes, they need labels, which require prior knowledge of order parameters or relevant microstructures describing these transitions. Instead, we develop a self-supervised, neural-network-based approach that does not require predefined labels about microstructure classes to predict process parameters from observed microstructures. We show that assessing the difficulty of solving this inverse problem can be used to uncover microstructural transitions. We demonstrate our approach by automatically discovering microstructural transitions in two distinct pattern-forming processes: the spinodal decomposition of a two-phase mixture and the formation of binary-alloy microstructures during physical vapor deposition of thin films. This approach opens a path forward for discovering unseen or hard-to-discern transitions and ultimately controlling complex pattern-forming processes.

Abram, Marcin↗
DOE OSTI2026

Multi-Modal Bayesian Neural Network Surrogates with Conjugate Last-Layer Estimation

As data collection and simulation capabilities advance, multi-modal learning, the task of learning from multiple modalities and sources of data, is becoming an increasingly important area of research. Surrogate models that learn from data of multiple auxiliary modalities to support the modeling of a highly expensive quantity of interest have the potential to aid outer loop applications such as optimization, inverse problems, or sensitivity analyses when multi-modal data are available. We develop two multi-modal Bayesian neural network surrogate models and leverage conditionally conjugate distributions in the last layer to estimate model parameters using stochastic variational inference (SVI). We provide a method to perform this conjugate SVI estimation in the presence of partially missing observations. Here, we demonstrate improved prediction accuracy and uncertainty quantification compared to unimodal surrogate models for both scalar and time series data.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Modeling the viscoplastic behavior of a semicrystalline polymer

In this study, a complex constitutive relation is identified using inverse modeling with the nominal mechanical response as sole experimental input. The methodology is illustrated for a semicrystalline thermoplastic in the presence of strain localization at finite deformations. The experimental database includes cylindrical tensile bars, compression pins and round notched bars loaded at strain rates spanning up to five decades and temperatures below and above T g . The data is organized into a calibration set and a validation set. The response of tensile specimens is determined using finite element analyses and a two-phase constitutive relation for semicrystalline polymers that accounts for temperature- and rate-sensitive plastic flow, pressure-sensitivity, small-strain softening and large-strain orientational hardening of the amorphous phase, along with the evolution of crystallinity. The large number of constitutive parameters is identified using an optimization tool coupled with the finite element solver and the calibration set from experiments. The methodology is shown to be successful in predicting the response of round notched bars and replicating the effects of temperature and strain rate on the severity of necking in tensile bars. The proposed model identification strategy is both simple and effective in comparison with other elaborate methods that attempt to access intrinsic behavior directly from high-fidelity experimental measurements.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Preconditioned least‐squares Petrov–Galerkin reduced order models

Abstract In this article, we introduce a methodology for improving the accuracy and efficiency of reduced order models (ROMs) constructed using the least‐squares Petrov–Galerkin (LSPG) projection method through the introduction of preconditioning. Unlike prior related work, which focuses on preconditioning the linear systems arising within the ROM numerical solution procedure to improve linear solver performance, our approach leverages a preconditioning matrix directly within the minimization problem underlying the LSPG formulation. Applying preconditioning in this way has the potential to improve ROM accuracy for several reasons. First, preconditioning the LSPG formulation changes the norm defining the residual minimization, which can improve the residual‐based stability constant bounding the ROM solution's error. The incorporation of a preconditioner into the LSPG formulation can have the additional effect of scaling the components of the residual being minimized to make them roughly of the same magnitude, which can be beneficial when applying the LSPG method to problems with disparate scales (e.g., dimensional equations, multi‐physics problems). Importantly, we demonstrate that an “ideal preconditioned” LSPG ROM (a ROM in which the preconditioner is the inverse of the Jacobian of its corresponding full order model) emulates projection of the full order model solution increment onto the reduced basis. This quantity defines a lower bound on the error of a ROM solution for a given reduced basis. By designing preconditioners that approximate the Jacobian inverse—as is common in designing preconditioners for solving linear systems—it is possible to obtain a ROM whose error approaches this lower bound. The proposed approach is evaluated on several mechanical and thermo‐mechanical problems implemented within the Albany HPC code and run in the predictive regime, with prediction across material parameter space. We demonstrate numerically that the introduction of simple Jacobi, Gauss‐Seidel, and ILU preconditioners into the proper orthogonal decomposition/LSPG formulation reduces significantly the ROM solution error, the reduced Jacobian condition number, the number of nonlinear iterations required to reach convergence, and the wall time (thereby improving efficiency). Moreover, our numerical results reveal that the introduction of preconditioning can deliver a robust and accurate solution for test cases in which the unpreconditioned LSPG method fails to converge.

Lindsay, Payton↗
DOE OSTI2022

Design-Space Exploration for Inverse-Design of Wind Turbine Blades Using Data-Driven Methods

The state-of-the-practice aerodynamic design methods for wind turbine blades is typically based on Blade-Element Momentum (BEM) theory using a pre-designed frozen family of airfoils. The airfoils are themselves typically designed using panel methods. The design of the next-generation of large flexible rotors will need to capture the non-linear aerodynamics and three-dimensional flow to reduce the levelized cost of wind energy. Data-driven methods for aerodynamic design using data generated by computational fluid dynamics offer an attractive alternative to BEM-based methods that captures the non-linear aerodynamics of the component airfoils as well as the root and tip sections. In this work, we develop and demonstrate a framework to "smartly" explore the relevant design space in combination with an appropriate automated CFD pipeline to evaluate the aerodynamics of each design. The design-space exploration framework uses appropriate perturbations to the airfoil shape and induction profile from a baseline shape in combination with the inverse-design using BEM. The resulting designs are evaluated using an automated CFD pipeline using the in-house CFD solver framework "Mercury". We perform verification and validation to establish the capability of the Mercury framework to predict the aerodynamic performance of wind turbines. The CFD simulation of the perturbed blade shapes are optimized to restart from the converged baseline simulation to reduce the computational time. Finally, we demonstrate the design-space exploration technique for the design of the outboard section and the full rotor using perturbations to the shape and operating conditions of the NREL 5-MW turbine.

aerodynamic design methods↗
DOE OSTI2023

Fourier-DeepONet: Fourier-enhanced deep operator networks for full waveform inversion with improved accuracy, generalizability, and robustness

In this article, full waveform inversion (FWI) infers the subsurface structure information from seismic waveform data by solving a non-convex optimization problem. Data-driven FWI has been increasingly studied with various neural network architectures to improve accuracy and computational efficiency. Nevertheless, the applicability of pre-trained neural networks is severely restricted by potential discrepancies between the source function used in the field survey and the one utilized during training. Here, we develop a Fourier-enhanced deep operator network (Fourier-DeepONet) for FWI with the generalization of seismic sources, including the frequencies and locations of sources. Specifically, we employ the Fourier neural operator as the decoder of DeepONet, and we utilize source parameters as one input of Fourier-DeepONet, facilitating the resolution of FWI with variable sources. To test Fourier-DeepONet, we develop three new and realistic FWI benchmark datasets (FWI-F, FWI-L, and FWI-FL) with varying source frequencies, locations, or both. Our experiments demonstrate that compared with existing data-driven FWI methods, Fourier-DeepONet obtains more accurate predictions of subsurface structures in a wide range of source parameters. Moreover, the proposed Fourier-DeepONet exhibits superior robustness when handling data with Gaussian noise or missing traces and sources with Gaussian noise, paving the way for more reliable and accurate subsurface imaging across diverse real conditions.

42 ENGINEERING↗