Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Prediction Accuracy”

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 811 records · Page 45
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

PopGNN: Graph Neural Network-Based Flexible Future Population Forecasting Model

Accurate population forecasts is important to plan critical infrastructure and services, from housing and education to healthcare and transport. However, traditional population prediction studies have only employed traditional machine learning models limited to capture complex spatial interdependencies and patterns. Althogh recently computer vision-based framework was introduced with with promising accuracy, it has critical limitations for real-world planning applications: it function only at fixed spatial resolutions, restricting their use in diverse boundaries such as census tracts, neighborhoods, or administrative zones. Therefore, this study suggests a Graph Neural Network (GNN)-based population prediction framework, called PopGNN. This model recorded remarkable performance compared with state-of-the-art models and traditional baseline models in the grid and administrative boundaries. Furthermore, our framework achieved comparable predictive accuracy to a computer vision-based model in both the South Korea and Tennessee case studies. Consequently, this study is valuable in that a single model can provide accurate population forecasts that address diverse planning demands, ranging from granular grid-level estimates for precise service allocation and facility location planning to aggregate administrative-level forecasts for macro-scale regional policy and resource distribution.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Energy and Emission Prediction for Mixed-Vehicle Transit Fleets Using Multi-task and Inductive Transfer Learning

Public transit agencies are focused on making their fixed-line bus systems more energy efficient by introducing electric (EV) and hybrid (HV) vehicles to their fleets. However, because of the high upfront cost of these vehicles, most agencies are tasked with managing a mixed-fleet of internal combustion vehicles (ICEVs), EVs, and HVs. In managing mixed-fleets, agencies require accurate predictions of energy use for optimizing the assignment of vehicles to transit routes, scheduling charging, and ensuring that emission standards are met. The current state-of-the-art is to develop separate neural network models to predict energy consumption for each vehicle class. Although different vehicle classes’ energy consumption depends on a varied set of covariates, we hypothesize that there are broader generalizable patterns that govern energy consumption and emissions. In this paper, we seek to extract these patterns to aid learning to address two problems faced by transit agencies. First, in the case of a transit agency which operates many ICEVs, HVs, and EVs, we use multi-task learning (MTL) to improve accuracy of forecasting energy consumption. Second, in the case where there is a significant variation in vehicles in each category, we use inductive transfer learning (ITL) to improve predictive accuracy for vehicle class models with insufficient data. As this work is to be deployed by our partner agency, we also provide an online pipeline for joining the various sensor streams for fixed-line transit energy prediction. Here, we find that our approach outperforms vehicle-specific baselines in both the MTL and ITL settings.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

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↗
DOE OSTI2023

Development of a High-Pressure Fuel Injection System for Use with Propane-DME

Paper details the design approach and performance of a high-pressure common rail fuel injection system used with Propane-DME mixtures targeting high injection pressures on a light duty 2.2L inline-4 compression ignition engine. The study estimates the bulk modulus of elasticity based on the hardware geometry and operating pressures to assess the compressibility of Propane and DME across a range of pressures typical of the LD engine application. The compressibility factor ranges from 500 to 3000 bar, significantly lower than the theoretical values for the conditions tested. The high-pressure pump performance is optimized via the implementation of an inlet metering valve operated on a crank-angle open/close sequence to control pressure at the common rail. The application of a model-based controller and the use of high-speed sampling of rail pressure indicate that pressure at the rail can be attained with the pump metering valve, and without use of the pressure relieve valve present in the rail. Results show a significant reduction on pumping work parasitics and of fuel heating, on the order of 40°C, at typical working conditions with the proposed approach. Injector rates of injection with Propane-DME are very similar to those of Diesel. Paper compares bench data of rates of injection versus simulation predictions across operating pressures of 200 to 1000bar and from injection commands spanning 0.20 to 2.0ms. Furthermore, the accuracy of the model predictions are attributed in part by to the updated fuel compressibility modulus descriptions attained during the testing.

42 ENGINEERING↗
DOE OSTI2020

EVALUATION OF PRESSURE DROP CORRELATIONS FOR THE WIRE-WRAPPED ROD BUNDLES

The accurate prediction of pressure drop in the fuel rod bundle is of importance for the design and thermal-hydraulic analysis of nuclear reactor system. Due to very complex geometry of wire-wrapped fuel rod bundle geometry for the Sodium Fast Reactor (SFR), a simple method using hydraulic (equivalent) diameter is not sufficient to predict the pressure drop of rod bundle accurately. For several decades, many experimental works have been performed to develop an accurate correlation for wire-wrapped fuel bundle friction factor. In these works, the friction factor correlation of wire-wrapped fuel bundle has been developed as a function of Reynolds number of the flow and the design parameters such as fuel pin diameter, wire diameter, rod pitch, and wire lead length. The Cheng and Todreas correlations are well-known and used in many subchannel analysis code, such as CADET, TRIO-U, MATRA-LMW, SE2-ANL, etc. Novendstern model, Rehme model, Baxi and Dalle Donne model are also well-known and widely referred. Computational Fluid Dynamics is another typical approach to predict the pressure drop of wire-wrapped fuel rod bundle, but it requires the model validation because the accuracy of pressure drop prediction by the CFD simulation depends on what turbulence model is employed. The present work aims at evaluating the existing pressure drop correlations for the wire-wrapped fuel rod bundle and evaluating the pressure drop of 217-pin rod bundle by the CFD analysis.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2021

A Deep Learning Modeling Framework to Capture Mixing Patterns in Reactive-Transport Systems

Prediction and control of chemical mixing are vital for many scientific areas such as subsurface reactive transport, climate modeling, combustion, epidemiology, and pharmacology. Due to the complex nature of mixing in heterogeneous and anisotropic media, the mathematical models related to this phenomenon are not analytically tractable. Numerical simulations often provide a viable route to predict chemical mixing accurately. However, contemporary modeling approaches for mixing cannot utilize available spatial-temporal data to improve the accuracy of the future prediction and can be compute-intensive, especially when the spatial domain is large and for long-term temporal predictions. To address this knowledge gap, in this work we will present in this paper a deep learning (DL) modeling framework applied to predict the progress of chemical mixing under fast bimolecular reactions. This framework uses convolutional neural networks (CNN) for capturing spatial patterns and long short-term memory (LSTM) networks for forecasting temporal variations in mixing. By careful design of the framework—placement of non-negative constraint on the weights of the CNN and the selection of activation function, the framework ensures non-negativity of the chemical species at all spatial points and for all times. Our DL-based framework is fast, accurate, and requires minimal data for training. The time needed to obtain a forecast using the model is a fraction (≈ O(-6)) of the time needed to obtain the result using a high-fidelity simulation. To achieve an error of 10% (measured using the infinity norm) for capturing local-scale mixing features such as interfacial mixing, only 24% to 32% of the sequence data for model training is required. To achieve the same level of accuracy for capturing global-scale mixing features, the sequence data required for model training is 64% to 70% of the total spatial-temporal data. Hence, the proposed approach—a fast and accurate way to forecast long-time spatial-temporal mixing patterns in heterogeneous and anisotropic media—will be a valuable tool for modeling reactive-transport in a wide range of applications.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2024

Simultaneously improving accuracy and computational cost under parametric constraints in materials property prediction tasks

Abstract Modern data mining techniques using machine learning (ML) and deep learning (DL) algorithms have been shown to excel in the regression-based task of materials property prediction using various materials representations. In an attempt to improve the predictive performance of the deep neural network model, researchers have tried to add more layers as well as develop new architectural components to create sophisticated and deep neural network models that can aid in the training process and improve the predictive ability of the final model. However, usually, these modifications require a lot of computational resources, thereby further increasing the already large model training time, which is often not feasible, thereby limiting usage for most researchers. In this paper, we study and propose a deep neural network framework for regression-based problems comprising of fully connected layers that can work with any numerical vector-based materials representations as model input. We present a novel deep regression neural network, iBRNet, with branched skip connections and multiple schedulers, which can reduce the number of parameters used to construct the model, improve the accuracy, and decrease the training time of the predictive model. We perform the model training using composition-based numerical vectors representing the elemental fractions of the respective materials and compare their performance against other traditional ML and several known DL architectures. Using multiple datasets with varying data sizes for training and testing, We show that the proposed iBRNet models outperform the state-of-the-art ML and DL models for all data sizes. We also show that the branched structure and usage of multiple schedulers lead to fewer parameters and faster model training time with better convergence than other neural networks. Scientific contribution: The combination of multiple callback functions in deep neural networks minimizes training time and maximizes accuracy in a controlled computational environment with parametric constraints for the task of materials property prediction.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Proteome-scale Deployment of Protein Structure Prediction Workflows on the Summit Supercomputer

Deep learning has contributed to major advances in the prediction of protein structure from sequence, a fundamental problem in structural bioinformatics. With predictions now approaching the accuracy of crystallographic experiments, and with accelerators like GPUs and TPUs making inference using large models rapid, genome-level structure prediction becomes an obvious aim. Leadership-class computing resources can be used to perform genome-scale protein structure prediction using state-of-the-art deep learning models, providing a wealth of new data for systems biology applications. Here we describe our efforts to efficiently deploy the AlphaFold v.2 program, for full-proteome structure prediction, at scale on the Oak Ridge Leadership Computing Facility's resources, including the Summit supercomputer. We performed inference to produce the predicted structures for 40,526 protein sequences, corresponding to four prokaryotic proteomes and one plant proteome, using under 4,400 total Summit node hours, equivalent to using the majority of the supercomputer for a little over one hour. We also designed an optimized structure refinement that reduced the time for the relaxation stage of the AlphaFold pipeline by over 10X for longer sequences. We demonstrate the types of analyses that can be performed on proteome-scale collections of sequences, including a search for novel quaternary structures and implications for functional annotation.

Gao, Mu↗
DOE OSTI2024

Data-Efficient Dimensionality Reduction and Surrogate Modeling of High-Dimensional Stress Fields

Tensor datatypes representing field variables like stress, displacement, velocity, etc., have increasingly become a common occurrence in data-driven modeling and analysis of simulations. Numerous methods [such as convolutional neural networks (CNNs)] exist to address the meta-modeling of field data from simulations. As the complexity of the simulation increases, so does the cost of acquisition, leading to limited data scenarios. Modeling of tensor datatypes under limited data scenarios remains a hindrance for engineering applications. Here, in this article, we introduce a direct image-to-image modeling framework of convolutional autoencoders enhanced by information bottleneck loss function to tackle the tensor data types with limited data. The information bottleneck method penalizes the nuisance information in the latent space while maximizing relevant information making it robust for limited data scenarios. The entire neural network framework is further combined with robust hyperparameter optimization. We perform numerical studies to compare the predictive performance of the proposed method with a dimensionality reduction-based surrogate modeling framework on a representative linear elastic ellipsoidal void problem with uniaxial loading. The data structure focuses on the low-data regime (fewer than 100 data points) and includes the parameterized geometry of the ellipsoidal void as the input and the predicted stress field as the output. The results of the numerical studies show that the information bottleneck approach yields improved overall accuracy and more precise prediction of the extremes of the stress field. Additionally, an in-depth analysis is carried out to elucidate the information compression behavior of the proposed framework.

artificial intelligence↗
DOE OSTI2021

Interpreting Write Performance of Supercomputer I/O Systems with Regression Models

This work seeks to advance the state of the art in HPC I/O performance analysis and interpretation. In particular, we demonstrate effective techniques to: (1) model output performance in the presence of I/O interference from production loads; (2) build features from write patterns and key parameters of the system architecture and configurations; (3) employ suitable machine learning algorithms to improve model accuracy. We train models with five popular regression algorithms and conduct experiments on two distinct production HPC platforms. We find that the lasso and random forest models predict output performance with high accuracy on both of the target systems. We also explore use of the models to guide adaptation in I/O middleware systems, and show potential for improvements of at least 15% from model-guided adaptation on 70% of samples, and improvements up to 10× on some samples for both of the target systems.

Xie, Bing↗
DOE OSTI2021

Classification and regression models of audio and vibration signals for machine state monitoring in precision machining systems

Here we present a data-driven method for monitoring machine status in manufacturing processes. Audio and vibration data from precision machining are used for inference in two operating scenarios: (a) variable machine health states (anomaly detection); and (b) settings of machine operation (state estimation). Audio and vibration signals are first processed through Fast Fourier Transform and Principal Component Analysis to extract transformed and informative features. These features are then used in the training of classification and regression models for machine state monitoring. Specifically, three classifiers (K-nearest neighbors, convolutional neural networks and support vector machines) and two regressors (support vector regression and neural network regression) were explored, in terms of their accuracy in machine state prediction. It is shown that the audio and vibration signals are sufficiently rich in information about the machine that 100% state classification accuracy could be accomplished. Data fusion was also explored, showing overall superior accuracy of data-driven regression models.

42 ENGINEERING↗
DOE OSTI2022

Prognostic importance of the preoperative New‐Naples prognostic score for patients with gastric cancer

Abstract Background The wide applicability of the Naples prognostic score (NPS) is still worthy of further study in gastric cancer (GC). This study aimed to construct a New‐NPS based on the differences in immunity and nutrition in patients with upper and lower gastrointestinal tumors to help obtain an individualized prediction of prognosis. Methods This study retrospectively analyzed patients who underwent radical gastrectomy from April 2014 to September 2016. The cutoff values of the preoperative neutrophil‐to‐lymphocyte ratio (NLR), lymphocyte‐to‐monocyte ratio (LMR), serum albumin (Alb), and total cholesterol (TC) were calculated by ROC curve analysis. ROC and t‐ROC were used to evaluate the accuracy of the prognostic markers. The Kaplan–Meier method and log‐rank test were used to analyze the overall survival probability. Univariate and multivariate analyses based on Cox risk regression were used to show the independent predictors. The nomogram was made by R studio. The predictive accuracy of nomogram was assessed using a calibration plot, concordance index (C‐index), and decision curve. Results A total of 737 patients were included in training cohort, 411 patients were included in validation cohort. ROC showed that the New‐NPS was more suitable for predicting the prognosis of GC patients. NPS = 2 indicated a poor prognosis. Multivariate analysis showed that CEA ( P = 0.026), Borrmann type ( P = 0.001), pTNM ( P < 0.001), New‐NPS ( P < 0.001), and nerve infiltration ( P = 0.035) were independent risk factors for prognosis. Conclusion The New‐NPS based on the cutoff values of NLR, LMR, Alb, and TC is not only suitable for predicting prognosis but can also be combined with clinicopathological characteristics to construct a nomogram model for GC patients.

Wang, Hao↗
DOE OSTI2021

Exploring the impacts of conformer selection methods on ion mobility collision cross section predictions

The prediction of structure dependent molecular properties, such as collision cross sections as measured using ion mobility spectrometry, are crucially dependent on the selection of the correct population of molecular conformers. Here, we report an in-depth evaluation of multiple conformation selection techniques, including simple averaging, Boltzmann weighting, lowest energy selection, low energy threshold reductions, and similarity reduction. Generating 50,000 conformers each for 18 molecules, we used the In Silico Chemical Library Engine (ISiCLE) to calculate the collision cross sections for the entire dataset. First, we employed Monte Carlo simulations to understand the variability between conformer structures as generated using simulated annealing. Then we employed Monte Carlo simulations to the aforementioned conformer selection techniques applied on the simulated molecular property—the ion mobility collision cross section. Based on our analyses, we found Boltzmann weighting to be a good tradeoff between precision and theoretical accuracy. Combining multiple techniques revealed that energy thresholds and root-mean-squared deviation-based similarity reductions can save considerable computational expense while maintaining property prediction accuracy. Molecular dynamic conformer generation tools like AMBER can continue to generate new lowest energy conformers even after tens of thousands of generations, decreasing precision between runs. This reduced precision can be ameliorated and theoretical accuracy increased by running density functional theory geometry optimization on carefully selected conformers.

Nielson, Felicity F.↗
DOE OSTI2020

An a priori evaluation of a principal component and artificial neural network based combustion model in diesel engine conditions

A principal component analysis (PCA) and artificial neural network (ANN) based chemistry tabulation approach is presented. ANNs are used to map the thermochemical state onto a low-dimensional manifold consisting of five control variables that have been identified using PCA. Three canonical configurations are considered to train the PCA-ANN model: a series of homogeneous reactors, a nonpremixed flamelet, and a two-dimensional lifted flame. The performance of the model in predicting the thermochemical manifold of a spatially-developing turbulent jet flame in diesel engine thermochemical conditions is a priori evaluated using direct numerical simulation (DNS) data. The PCA-ANN approach is compared with a conventional tabulation approach (tabulation using ad hoc defined control variables and linear interpolation). The PCA-ANN model provides higher accuracy and requires several orders of magnitude less memory. Here, these observations indicate that the PCA-ANN model is superior for chemistry tabulation, especially for modelling complex chemistries that present multiple combustion modes as observed in diesel combustion. The performance of the PCA-ANN model is then compared to the optimal estimator, i.e. the conditional mean from the DNS. The results indicate that the PCA-ANN model gives high prediction accuracy, comparable to the optimal estimator, especially for major species and the thermophysical properties. Higher errors are observed for the minor species and reaction rate predictions when compared to the optimal estimator. It is shown that the prediction of minor species and reaction rates can be improved by using training data that exhibits a variation of parameters as observed in the turbulent flame. The output of the ANN is analysed to assess mass conservation. It is observed that the ANN incurs a mean absolute error of 0.05% in mass conservation. Furthermore, it is demonstrated that this error can be reduced by modifying the cost function of the ANN to penalise for deviation from mass conservation.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2021

Bayesian Estimation of the D(p,γ) 3 He Thermonuclear Reaction Rate

Big bang nucleosynthesis (BBN) is the standard model theory for the production of the light nuclides during the early stages of the universe, taking place for a period of about 20 minutes after the big bang. Deuterium production, in particular, is highly sensitive to the primordial baryon density and the number of neutrino species, and its abundance serves as a sensitive test for the conditions in the early universe. The comparison of observed deuterium abundances with predicted ones requires reliable knowledge of the relevant thermonuclear reaction rates, and their corresponding uncertainties. Recent observations reported the primordial deuterium abundance with percent accuracy, but some theoretical predictions based on BBN are at tension with the measured values because of uncertainties in the cross section of the deuterium-burning reactions. In this work, we analyze the S-factor of the D(p,γ) 3 He reaction using a hierarchical Bayesian model. We take into account the results of eleven experiments, spanning the period of 1955--2021; more than any other study. We also present results for two different fitting functions, a two-parameter function based on microscopic nuclear theory and a four-parameter polynomial. Furthermore, our recommended reaction rates have a 2.2\% uncertainty at 0.8~GK, which is the temperature most important for deuterium BBN. Differences between our rates and previous results are discussed.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

Machine Learning for Prediction of Thermodynamic Descriptors

Our objective is to apply machine learning (ML) algorithms for the prediction of molecular catalysis descriptors from geometric properties derived from experimental crystallographic databases. Catalysis is often considered a “low-data” discipline that is poorly suited for ML methods. An exception is the extensive structural information that is available for molecular catalysts through the Cambridge Structural Database (CSD), which contains atomically precise molecular structures from X-ray diffraction analysis for >600K metal complexes. As a proof-of-principle, we targeted the prediction of hydricity, a thermodynamic property that provides understanding and control of catalytic hydride transfer. We built a training set composed of ~100 molecular complexes with a known hydricity and structural information from the CSD. This data set was converted into a machine-readable format using the smooth overlap of atomic positions (SOAP) representation and further labeled with simple electronic descriptors for the metal centers. Multiple different neural networks were trained on this data set, and the accuracy of the hydricity predictions ranged from < 2 kcal/mol to 20 kcal/mol. The accuracy of each model was highly sensitive to which compounds were in the train versus test set, underscoring the challenges associated with small and chemically diverse data sets. Finally, to further augment the data set, we attempted to experimentally measure several new hydricity values, however these experiments were unsuccessful due to undesired chemical reactivity of the selected complexes.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Quadrature Based Neural Network Learning of Stochastic Hamiltonian Systems

Hamiltonian Neural Networks (HNNs) provide structure-preserving learning of Hamiltonian systems. In this paper, we extend HNNs to structure-preserving inversion of stochastic Hamiltonian systems (SHSs) from observational data. We propose the quadrature-based models according to the integral form of the SHSs’ solutions, where we denoise the loss-by-moment calculations of the solutions. The integral pattern of the models transforms the source of the essential learning error from the discrepancy between the modified Hamiltonian and the true Hamiltonian in the classical HNN models into that between the integrals and their quadrature approximations. This transforms the challenging task of deriving the relation between the modified and the true Hamiltonians from the (stochastic) Hamilton–Jacobi PDEs, into the one that only requires invoking results from the numerical quadrature theory. Meanwhile, denoising via moments calculations gives a simpler data fitting method than, e.g., via probability density fitting, which may imply better generalization ability in certain circumstances. Numerical experiments validate the proposed learning strategy on several concrete Hamiltonian systems. The experimental results show that both the learned Hamiltonian function and the predicted solution of our quadrature-based model are more accurate than that of the corrected symplectic HNN method on a harmonic oscillator, and the three-point Gaussian quadrature-based model produces higher accuracy in long-time prediction than the Kramers–Moyal method and the numerics-informed likelihood method on the stochastic Kubo oscillator as well as other two stochastic systems with non-polynomial Hamiltonian functions. Moreover, the Hamiltonian learning error εH arising from the Gaussian quadrature-based model is lower than that from Simpson’s quadrature-based model. These demonstrate the superiority of our approach in learning accuracy and long-time prediction ability compared to certain existing methods and exhibit its potential to improve learning accuracy via applying precise quadrature formulae.

Mathematics↗
DOE OSTI2021

Expert elicitation survey predicts 37% to 49% declines in wind energy costs by 2050

Wind energy has experienced accelerated cost reduction over the past five years—far greater than predicted in a 2015 expert elicitation. Here we report results from a new survey on wind costs, compare those with previous results and discuss the accuracy of the earlier predictions. In this work, we show that experts in 2020 expect future onshore and offshore wind costs to decline 37–49% by 2050, resulting in costs 50% lower than predicted in 2015. This is due to cost reductions witnessed over the past five years and expected continued advancements. If realized, these costs might allow wind to play a larger role in energy supply than previously anticipated. Considering both surveys, we also conclude that there is considerable uncertainty about future costs. Our results illustrate the importance of considering cost uncertainty, highlight the value and limits of using experts to reveal those uncertainties, and yield possible lessons for energy modellers and expert elicitation.

17 WIND ENERGY↗