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 595 records · Page 33
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Flexible AI Models for Grid Resilience

The rapid growth in size and complexity of artificial intelligence (AI) and machine learning (ML) models has led to increased energy demands, posing a threat to the reliability of the existing power grid. This project addresses the challenge of highly intermittent and energy-intensive inference workloads by (1) developing fidelity-adaptive neural networks capable of dynamic response to grid conditions and (2) integrating these networks with power flow simulations to assess their impact on power grid reliability. We will explore both top-down and bottom-up approaches to create hierarchies of submodels that provide a controlled trade-off between power draw and prediction accuracy. The top-down method utilizes NN pruning to reduce a flagship model into progressively smaller, energy-efficient variants. The bottom-up approach employs geometrically principled weight setting strategies to construct depth-efficient models from the ground up. A real-time hardware-in-the-loop (HIL) platform will be developed to simulate a scaled AC power grid, integrating live AI workload power draw and enabling dynamic model switching in response to grid feedback. This work will provide a novel framework for evaluating the impact of flexible AI/ML workloads on grid performance and establish new methodologies for energy-aware computing in data centers. The outcomes will demonstrate that adaptive AI/ML can play a critical role in improving grid stability while advancing NREL's leadership in energy-efficient computing research.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Physics-Informed Neural Network (PINN) Prediction of Mixed Mass-Heat-Crystallization Limited Methane Hydrate Formation and Dissociation in Micro-Confinement

The creation and use of Physics-Informed Neural Networks (PINNs) for simulating the dynamics of methane hydrate formation and dissociation will be presented. The PINN framework's main benefit is its capacity to impose physical consistency with only a partial comprehension of the governing equations. This makes the algorithm especially useful for systems with little experimental evidence or a lack of theoretical knowledge. A strong basis for forecasting methane hydrate behavior over the verified operating ranges of 30.0-80.9 bar pressure and 1.0-4.0 K sub-cooling conditions is provided by the combination of conductive heat transfer equations and mixed mass-transfer–crystallization kinetics. PINNs were more accurate at predicting the mixed mass-heat-crystallization limited kinetics than conventional Artificial Neural Networks (ANNs), demonstrating remarkable predictive accuracy for methane hydrate production over the ANN model. The efficiency of incorporating physical limitations from first principles into machine learning frameworks for methane hydrate crystallizations is reinforced by these findings. For hydrate-related applications in energy generation, carbon sequestration, and climate modelling, our study establishes PINNs as a computational tool that is both scalable and efficient. The proven capacity to close the gap between conventional physics-based simulations and solely data-driven models creates new opportunities for expedited hydrate research and practical applications.

Hartman, Ryan L [NYU Tandon School of Engineering]↗
DOE OSTI2023

Waste Glass Property Database and Data Qualification Plan

The U.S. Department of Energy vitrification facilities currently employ glass property-composition models to ensure processability of waste streams and acceptability of the final glass products. The efficiency (e.g., process flexibility, reduced down time, and reduced cost) of waste vitrification is directly tied to the size of the waste processing envelope. To increase the size of the processing envelope, a larger database was developed. The database will improve the prediction accuracy of glass properties, leading to higher waste loadings, higher waste throughput, broader process flexibility, and reduced mission life. Some of the data in this expanded database has insufficient quality assurance (QA) rigor for use in nuclear facility operation and glass qualification. A plan was developed to qualify high-value data under the appropriate QA rigor for use at the Hanford Waste Treatment and Immobilization Plant’s High-Level Waste (HLW) Facility. This qualification plan first compares the data coverage over the composition region of interest to Hanford HLW by property. Those studies that significantly improve the data coverage in the Hanford HLW glass composition region were prioritized for qualification activities. Qualification methods including QA equivalence, peer review, data corroboration, and confirmatory testing have been assigned to each high-priority study.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2026

AI-driven Neutrino Beam Diagnostics for Next-Generation Neutrino Experiments

The accelerator-driven beam uncertainty limits oscillation measurements in long-baseline neutrino experiments. Spill-resolved beam diagnostics and real-time inference are necessary to address these neutrino flux systematics. As such, we present a machine-learning-based beam monitoring framework developed and validated using data from the T2K experiment. Our approach uses downstream, spill-by-spill muon monitor observables to predict upstream parameters such as proton beam position and width. We achieve high predictive accuracy on nominal runs, demonstrating robust baseline performance whether the model is trained on stable runs or systematically varied conditions. The framework is designed to be robust against domain shifts, allowing the neural network architectures and inference strategies developed with T2K data to be retrained and validated using LBNF simulations, with the goal of eventual deployment under real LBNF/DUNE operating conditions. This scalable approach to real-time beam inference offers a pathway toward reducing flux systematics for next-generation neutrino experiments such as DUNE.

Aney, Noah [Fermilab; U. Chicago (main)]↗
DOE OSTI2022

Neural Ordinary Differential Equations for Nonlinear System Identification

Neural ordinary differential equations (NODE) have been recently proposed as a promising approach for nonlinear system identification tasks. In this work, we systematically compare their predictive performance with current state-of-the-art nonlinear and classical linear methods. In particular, we present a quantitative study comparing NODE's performance against neural state-space models and classical linear system identification methods and evaluate their inference speed and prediction performance on open-loop errors across eight different dynamical systems. The experiments show that NODEs can consistently improve the prediction accuracy by order of magnitude compared to benchmark methods. Besides improved accuracy, we also observed that NODEs are less sensitive to hyperparameters compared to neural state-space models by paying the cost of increased computation at the inference time.

machine leaning, system identification, physics in↗
DOE OSTI2023

Data to Accompany: PM2.5 is insufficient to explain personal PAH exposure

Fine particulate matter (PM2.5) air quality index (AQI) data from outdoor stationary monitors and Hazard Mapping System (HMS) smoke density data from satellites are often used as proxies for personal chemical exposure. Silicone wristbands can quantify more individualized exposure data than stationary air monitors or smoke satellites. However, it is not understood how these proxy measurements compare to chemical data measured from wristbands. We hypothesized that predictive models for personal chemical exposure would be significantly improved by expanding beyond stationary PM2.5 AQI data or satellite HMS data to also include environmental and behavioral information. In Eugene, Oregon, participants wore daily wristbands, carried a phone that recorded locations, and answered daily questionnaires for a seven-day period in multiple seasons. We gathered publicly available daily PM2.5 AQI data and HMS data. We analyzed wristbands for 94 organic chemicals, including 53 polycyclic aromatic hydrocarbons (PAHs). Wristband chemical detections and concentrations, behavioral variables (e.g., time spent indoors), and environmental conditions (e.g., PM2.5 AQI) significantly differed between seasons. Machine learning models were fit to predict personal chemical exposure using PM2.5 AQI only, HMS only, and a multivariate feature set including PM2.5 AQI, HMS, and other environmental and behavioral information. On average, the multivariate models increased predictive accuracy by approximately 70% compared to either the AQI model or the HMS model for all chemicals modeled. This study provides evidence that PM2.5 AQI data alone or HMS data alone is insufficient to explain personal chemical exposures. Our results identify additional key predictors of personal chemical exposure.

Bramer, Lisa M↗
DOE OSTI2025

Role of Computational Parameters on Predicting Self-Consistent Residual Stress and Distortion during Wire Arc Additive Manufacturing

Production of three-dimensional metallic parts through integration of an articulated robot and gas metal arc welding, also known as wire arc additive manufacturing (WAAM), can produce large-scale components with moderate geometrical complexity. This technology is particularly appealing due to its high deposition rates, scalability, and cost-effective feedstock compared to other AM processes. Despite its advantages, WAAM adoption is hindered by challenges in ensuring geometric conformity without extensive distortion, defect-free structures, and consistent mechanical properties. Finite element analysis (FEA) is often used to address the challenge of geometrical conformity. As the size of parts increases, the best practices for mesh size and temporal resolution known in the literature become computationally unviable. This research examined the effects of mesh and time-step resolutions during transient FEA of a large-scale (248 layers) metallic part. The impact of computational parameters on the thermal history, displacement, and residual stress distributions were evaluated. The results showed that predicted distortion was consistent across resolutions, while time-step length significantly affected predicted thermal history, and mesh size influenced residual stress distributions. To investigate this relationship further, directionally biased meshes were considered and analyzed. The results indicated that increasing mesh resolution perpendicular to the welding path yielded stress predictions that aligned closely with higher-resolution models while offering substantial computational savings. In conclusion, the significances of this research are related to verification and validation of WAAM models for widespread industrial adoption and pragmatic guidelines for optimizing computation parameters for balancing computational efficiency and predictive accuracy of residual stress and distortion.

Solsbee, Brandon [Univ. of Tennessee, Knoxville, T↗
DOE OSTI2020

Development of a Genome-Scale Metabolic Model of Clostridium thermocellum and Its Applications for Integration of Multi-Omics Datasets and Computational Strain Design

Solving environmental and social challenges such as climate change requires a shift from our current non-renewable manufacturing model to a sustainable bioeconomy. To lower carbon emissions in the production of fuels and chemicals, plant biomass feedstocks can replace petroleum using microorganisms as biocatalysts. The anaerobic thermophile Clostridium thermocellum is a promising bacterium for bioconversion due to its capability to efficiently degrade lignocellulosic biomass. However, the complex metabolism of C. thermocellum is not fully understood, hindering metabolic engineering to achieve high titers, rates, and yields of targeted molecules. In this study, we developed an updated genome-scale metabolic model of C. thermocellum that accounts for recent metabolic findings, has improved prediction accuracy, and is standard-conformant to ensure easy reproducibility. We illustrated two applications of the developed model. We first formulated a multi-omics integration protocol and used it to understand redox metabolism and potential bottlenecks in biofuel (e.g., ethanol) production in C. thermocellum. Second, we used the metabolic model to design modular cells for efficient production of alcohols and esters with broad applications as flavors, fragrances, solvents, and fuels. The proposed designs not only feature intuitive push-and-pull metabolic engineering strategies, but also present novel manipulations around important central metabolic branch-points. We anticipate the developed genome-scale metabolic model will provide a useful tool for system analysis of C. thermocellum metabolism to fundamentally understand its physiology and guide metabolic engineering strategies to rapidly generate modular production strains for effective biosynthesis of biofuels and biochemicals from lignocellulosic biomass.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Genomic selection in algae with biphasic lifecycles: A Saccharina latissima (sugar kelp) case study

Introduction Sugar kelp ( Saccharina latissima ) has a biphasic life cycle, allowing selection on both thediploid sporophytes (SPs) and haploid gametophytes (GPs). Methods We trained a genomic selection (GS) model from farm-tested SP phenotypic data and used a mixed-ploidy additive relationship matrix to predict GP breeding values. Topranked GPs were used to make crosses for further farm evaluation. The relationship matrix included 866 individuals: a) founder SPs sampled from the wild; b) progeny GPs from founders; c) Farm-tested SPs crossed from b); and d) progeny GPs from farm-tested SPs. The complete pedigree-based relationship matrix was estimated for all individuals. A subset of founder SPs ( n = 58) and GPs ( n = 276) were genotyped with Diversity Array Technology and whole genome sequencing, respectively. We evaluated GS prediction accuracy via cross validation for SPs tested on farm in 2019 and 2020 using a basic GBLUP model. We also estimated the general combining ability (GCA) and specific combining ability (SCA) variances of parental GPs. A total of 11 yield-related and morphology traits were evaluated. Results The cross validation accuracies for dry weight per meter ( r ranged from 0.16 to 0.35) and wet weight per meter ( r ranged 0.19 to 0.35) were comparable to GS accuracy for yield traits in terrestrial crops. For morphology traits, cross validation accuracy exceeded 0.18 in all scenarios except for blade thickness in the second year. Accuracy in a third validation year (2021) was 0.31 for dry weight per meter over a confirmation set of 87 individuals. Discussion Our findings indicate that progress can be made in sugar kelp breeding by using genomic selection.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Application of Machine Learning Techniques to an Agent-Based Model of Pantoea

Agent-based modeling (ABM) is a powerful simulation technique which describes a complex dynamic system based on its interacting constituent entities. While the flexibility of ABM enables broad application, the complexity of real-world models demands intensive computing resources and computational time; however, a metamodel may be constructed to gain insight at less computational expense. Here, we developed a model in NetLogo to describe the growth of a microbial population consisting of Pantoea . We applied 13 parameters that defined the model and actively changed seven of the parameters to modulate the evolution of the population curve in response to these changes. We efficiently performed more than 3,000 simulations using a Python wrapper, NL4Py . Upon evaluation of the correlation between the active parameters and outputs by random forest regression, we found that the parameters which define the depth of medium and glucose concentration affect the population curves significantly. Subsequently, we constructed a metamodel, a dense neural network, to predict the simulation outputs from the active parameters and found that it achieves high prediction accuracy, reaching an R 2 coefficient of determination value up to 0.92. Our approach of using a combination of ABM with random forest regression and neural network reduces the number of required ABM simulations. The simplified and refined metamodels may provide insights into the complex dynamic system before their transition to more sophisticated models that run on high-performance computing systems. The ultimate goal is to build a bridge between simulation and experiment, allowing model validation by comparing the simulated data to experimental data in microbiology.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Hyperspectral Reflectance-Based High Throughput Phenotyping to Assess Water-Use Efficiency in Cotton

Cotton is a pivotal global commodity underscored by its economic value and widespread use. In the face of climate change, breeding resilient cultivars for variable environmental conditions becomes increasingly essential. However, the process of phenotyping, crucial to breeding programs, is often viewed as a bottleneck due to the inefficiency of traditional, low-throughput methods. To address this limitation, this study utilizes hyperspectral remote sensing, a promising tool for assessing crucial crop traits across forty cotton varieties. The results from this study demonstrated the effectiveness of four vegetation indices (VIs) in evaluating these varieties for water-use efficiency (WUE). The prediction accuracy for WUE through VIs such as the simple ratio water index (SRWI) and normalized difference water index (NDWI) was higher (up to R2 = 0.66), enabling better detection of phenotypic variations (p < 0.05) among the varieties compared to physiological-related traits (from R2 = 0.21 to R2 = 0.42), with high repeatability and a low RMSE. These VIs also showed high Pearson correlations with WUE (up to r = 0.81) and yield-related traits (up to r = 0.63). We also selected high-performing varieties based on the VIs, WUE, and fiber quality traits. This study demonstrated that the hyperspectral-based proximal sensing approach helps rapidly assess the in-season performance of varieties for imperative traits and aids in precise breeding decisions.

Agriculture↗
DOE OSTI2025

Experimental and Computational Characterization of a Modified Sioutas Cascade Impactor for Respirable Radioactive Aerosols

Oak Ridge National Laboratory is collecting and characterizing aerosols released when spent nuclear fuel (SNF) rods are fractured in bending. An aerosol collection system was designed and tested to collect respirable sized (<10 μm aerodynamic diameter [AED]) particulates inside a hot cell facility. The setup is a modified version of the commercially available Sioutas cascade impactor, to which additional stages were added to expand the aerosol collection range from 2.5 to ~15 μm AED. To accommodate the additional stages and specific test conditions, the operating flow rate for aerosol collection was reduced, and testing was conducted by using pressure drop measurements, surrogate dust collection, and particle size characterization. The fluid flow distribution within the cascade and its stages was simulated in STAR-CCM+, and the stage-wise pressure drops obtained using the computational fluid dynamics model were then compared to experimental data. Lagrangian particle simulations were also performed, and stage-wise collection statistics were obtained from the simulation for comparison with the experimental data obtained using SNF-surrogate dust particles. The results provide valuable insights into the stage-wise particle collection characteristics of the modified cascade impactor and can also be used to improve the prediction accuracy of the manufacturer-determined analytical correlations.

aerosol modeling↗
DOE OSTI2024

Assessment of Envelope- and Machine Learning-Based Electrical Fault Type Detection Algorithms for Electrical Distribution Grids

This study introduces envelope- and machine learning (ML)-based electrical fault type detection algorithms for electrical distribution grids, advancing beyond traditional logic-based methods. The proposed detection model involves three stages: anomaly area detection, ML-based fault presence detection, and ML-based fault type detection. Initially, an envelope-based detector identifying the anomaly region was improved to handle noisier power grid signals from meters. The second stage acts as a switch, detecting the presence of a fault among four classes: normal, motor, switching, and fault. Finally, if a fault is detected, the third stage identifies specific fault types. This study explored various feature extraction methods and evaluated different ML algorithms to maximize prediction accuracy. The performance of the proposed algorithms is tested in an emulated software–hardware electrical grid testbed using different sample rate meters/relays, such as SEL735, SEL421, SEL734, SEL700GT, and SEL351S near and far from an inverter-based photovoltaic array farm. The performance outcomes demonstrate the proposed model’s robustness and accuracy under realistic conditions.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

Transforming Agricultural Productivity with AI-Driven Forecasting: Innovations in Food Security and Supply Chain Optimization

Global food security is under significant threat from climate change, population growth, and resource scarcity. This review examines how advanced AI-driven forecasting models, including machine learning (ML), deep learning (DL), and time-series forecasting models like SARIMA/ARIMA, are transforming regional agricultural practices and food supply chains. Through the integration of Internet of Things (IoT), remote sensing, and blockchain technologies, these models facilitate the real-time monitoring of crop growth, resource allocation, and market dynamics, enhancing decision making and sustainability. The study adopts a mixed-methods approach, including systematic literature analysis and regional case studies. Highlights include AI-driven yield forecasting in European hydroponic systems and resource optimization in southeast Asian aquaponics, showcasing localized efficiency gains. Furthermore, AI applications in food processing, such as plasma, ozone and Pulsed Electric Field (PEF) treatments, are shown to improve food preservation and reduce spoilage. Key challenges—such as data quality, model scalability, and prediction accuracy—are discussed, particularly in the context of data-poor environments, limiting broader model applicability. The paper concludes by outlining future directions, emphasizing context-specific AI implementations, the need for public–private collaboration, and policy interventions to enhance scalability and adoption in food security contexts.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2024

Active Learning for Rapid Targeted Synthesis of Compositionally Complex Alloys

The next generation of advanced materials is tending toward increasingly complex compositions. Synthesizing precise composition is time-consuming and becomes exponentially demanding with increasing compositional complexity. An experienced human operator does significantly better than a novice but still struggles to consistently achieve precision when synthesis parameters are coupled. The time to optimize synthesis becomes a barrier to exploring scientifically and technologically exciting compositionally complex materials. This investigation demonstrates an active learning (AL) approach for optimizing physical vapor deposition synthesis of thin-film alloys with up to five principal elements. We compared AL-based on Gaussian process (GP) and random forest (RF) models. The best performing models were able to discover synthesis parameters for a target quinary alloy in 14 iterations. We also demonstrate the capability of these models to be used in transfer learning tasks. RF and GP models trained on lower dimensional systems (i.e., ternary, quarternary) show an immediate improvement in prediction accuracy compared to models trained only on quinary samples. Furthermore, samples that only share a few elements in common with the target composition can be used for model pre-training. We believe that such AL approaches can be widely adapted to significantly accelerate the exploration of compositionally complex materials.

Chemistry↗
DOE OSTI2021

Improving Prediction of Peroxide Value of Edible Oils Using Regularized Regression Models

We present four unique prediction techniques, combined with multiple data pre-processing methods, utilizing a wide range of both oil types and oil peroxide values (PV) as well as incorporating natural aging for peroxide creation. Samples were PV assayed using a standard starch titration method, AOCS Method Cd 8-53, and used as a verified reference method for PV determination. Near-infrared (NIR) spectra were collected from each sample in two unique optical pathlengths (OPLs), 2 and 24 mm, then fused into a third distinct set. All three sets were used in partial least squares (PLS) regression, ridge regression, LASSO regression, and elastic net regression model calculation. While no individual regression model was established as the best, global models for each regression type and pre-processing method show good agreement between all regression types when performed in their optimal scenarios. Furthermore, small spectral window size boxcar averaging shows prediction accuracy improvements for edible oil PVs. Best-performing models for each regression type are: PLS regression, 25 point boxcar window fused OPL spectral information RMSEP = 2.50; ridge regression, 5 point boxcar window, 24 mm OPL, RMSEP = 2.20; LASSO raw spectral information, 24 mm OPL, RMSEP = 1.80; and elastic net, 10 point boxcar window, 24 mm OPL, RMSEP = 1.91. The results show promising advancements in the development of a full global model for PV determination of edible oils.

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

Simulation Study of High-Precision Characterization of MeV Electron Interactions for Advanced Nano-Imaging of Thick Biological Samples and Microchips

The resolution of a mega-electron-volt scanning transmission electron microscope (MeV-STEM) is primarily governed by the properties of the incident electron beam and angular broadening effects that occur within thick biological samples and microchips. A precise understanding and mitigation of these constraints require detailed knowledge of beam emittance, aberrations in the STEM column optics, and energy-dependent elastic and inelastic critical angles of the materials being examined. This simulation study proposes a standardized experimental framework for comprehensively assessing beam intensity, divergence, and size at the sample exit. This framework aims to characterize electron-sample interactions, reconcile discrepancies among analytical models, and validate Monte Carlo (MC) simulations for enhanced predictive accuracy. Our numerical findings demonstrate that precise measurements of these parameters, especially angular broadening, are not only feasible but also essential for optimizing imaging resolution in thick biological samples and microchips. By utilizing an electron source with minimal emittance and tailored beam characteristics, along with amorphous ice and silicon samples as biological proxies and microchip materials, this research seeks to optimize electron beam energy by focusing on parameters to improve the resolution in MeV-STEM/TEM. This optimization is particularly crucial for in situ imaging of thick biological samples and for examining microchip defects with nanometer resolutions. Our ultimate goal is to develop a comprehensive mapping of the minimum electron energy required to achieve a nanoscale resolution, taking into account variations in sample thickness, composition, and imaging mode.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Multi-objective optimization of peel and shear strengths in ultrasonic metal welding using machine learning-based response surface methodology

Ultrasonic metal welding (UMW) is a solid-state joining technique with varied industrial applications. Despite of its numerous advantages, UMW has a relative narrow operating window and is sensitive to variations in process conditions. As such, it is imperative to quantitatively characterize the influence of welding parameters on the resulting joint quality. The quantification model can be subsequently used to optimize the parameters. Conventional response surface methodology (RSM) usually employs linear or polynomial models, which may not be able to capture the intricate, nonlinear input-output relationships in UMW. Furthermore, some UMW applications call for simultaneous optimization of multiple quality indices such as peel strength, shear strength, electrical conductivity, and thermal conductivity. To address these challenges, this paper develops a machine learning (ML)-based RSM to model the input-output relationships in UMW and jointly optimize two quality indices, namely, peel and shear strengths. The performance of various ML methods including spline regression, Gaussian process regression (GPR), support vector regression (SVR), and conventional polynomial regression models with different orders is compared. A case study using experimental data shows that GPR with radial basis function (RBF) kernel and SVR with RBF kernel achieve the best prediction accuracy. The obtained response surface models are then used to optimize a compound joint strength indicator that is defined as the average of normalized shear and peel strengths. In addition, the case study reveals different patterns in the response surfaces of shear and peel strengths, which has not been systematically studied in the literature. While developed for the UMW application, the method can be extended to other manufacturing processes.

42 ENGINEERING↗