Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “data base for model validation”

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 739 records · Page 41
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Popnet : computer vision based deep learning model for forecasting gridded population

Here, this study introduces Popnet, a deep learning model for forecasting 1 km-gridded populations, integrating U-Net, ConvLSTM, a Spatial Autocorrelation module and deep ensemble methods. Using spatial variables and population data from 2000 to 2020, Popnet predicts South Korea’s population trends by age groups (under 14, 15-64 and over 65) up to 2040. In validation, it outperforms traditional machine learning and state-of-the-art computer vision models. The output of this model discovered significant polarisation: population growth in urban areas, especially the capital region, and severe depopulation in rural areas. Popnet is a robust tool for offering significant insights to policymakers and related stakeholders about the detailed future population, which allows them to establish detailed, localised planning and resource allocations.

computer vision↗
DOE OSTI2022

Uncertainty Quantification Framework for Predicting Material Response with Large Number of Parameters: Application to Creep Prediction in Ferritic-Martensitic Steels Using Combined Crystal Plasticity and Grain Boundary Models

This paper presents an uncertainty quantification (UQ) framework for the physics-based model prediction of material response with a large number of parameters. The application problem presented in this work is that of predicting creep in Grade 91 steel at 600°C. The material response is defined with a physically based microstructural model with constitutive equations emulating several observed phenomena in Grade 91 and embodied into an explicit geometry mesoscale finite element model for prior austenite grains and grain boundaries. Creep within the grains and in grain boundaries are represented by crystal plasticity for dislocation motion and a physics-based model for cavity growth and nucleation, respectively. The creep behavior of this material is influenced by several parameters, some of which have a wide range of variation based on experimental data. UQ combined with microstructural modeling can discover the core microstructural causes of experimental variability, leading to improved materials with lower variability in critical long-term material properties. In this study, we investigate the model's uncertainty to identify material properties that may be modified during production to increase creep life and analyze different components of the crystal plasticity model for improvements. For this purpose, a quantity of interest is defined as time to minimum creep rate, which correlates well to the creep failure of the material. A deep neural network model was trained and validated to be used as a surrogate for the finite element model. Then, a variance-based sensitivity analysis is performed on the surrogate model to find the Sobol indices of the input parameters in respect to the output quantity of interest. The Sobol indices are used to reduce the dimensionality of the model. Generalized polynomial chaos expansion is used on the reduced basis models to propagate the uncertainty from the input parameters to the quantity of interest using the deep neural network surrogate model. These results are benchmarked against uncertainty propagation using Monte Carlo simulations. In conclusion, the UQ performed through the reduced basis model captures almost all the uncertainty in the model with significantly fewer simulations, making it possible to perform the UQ directly via simulations with the finite element model rather than surrogate machine-learned models.

36 MATERIALS SCIENCE↗
DOE OSTI2021

A semiparametric latent factor model for large scale temporal data with heteroscedasticity

Large scale temporal data have flourished in a vast array of applications, and their sophisticated structures, especially the heteroscedasticity among subjects with inter- and intra-temporal dependence, have fueled a great demand for new statistical models. In this paper, with covariate information, we consider a flexible model for large scale temporal data with subject-specific heteroscedasticity. Formally, the model employs latent semiparametric factors to simultaneously account for the subject-specific heteroscedasticity and the contemporaneous and/or serial correlations. The subject-specific heteroscedasticity is modeled as the product of the unobserved factor process and subject’s covariate effect, which is further characterized via additive models. For estimation, we propose a two-step procedure. First, the latent factor process and nonparametric loading are recovered through projection-based methods, and following, we estimate the regression components by approaches motivated from the generalized least squares. By scrupulously examining the non-asymptotic rates for recovering the factor process and its loading, we show the consistency and efficiency of estimated regression coefficients in the absence of prior knowledge of latent factor process and subject’s covariate effect. Here, the statistical guarantees remain valid even for finite time points that makes our method particularly appealing when the subjects significantly outnumber the observation time points. Using comprehensive simulations, we demonstrate the finite sample performance of our method, which corroborates the theoretical findings. Finally, we apply our method to a data set of air quality and energy consumption collected at 129 monitoring sites in the United States in 2015.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Synthetic Scientific Image Generation with VAE, GAN, and Diffusion Model Architectures

Generative AI (genAI) has emerged as a powerful tool for synthesizing diverse and complex image data, offering new possibilities for scientific imaging applications. This review presents a comprehensive comparative analysis of leading generative architectures, ranging from Variational Autoencoders (VAEs) to Generative Adversarial Networks (GANs) on through to Diffusion Models, in the context of scientific image synthesis. We examine each model's foundational principles, recent architectural advancements, and practical trade-offs. Our evaluation, conducted on domain-specific datasets including microCT scans of rocks and composite fibers, as well as high-resolution images of plant roots, integrates both quantitative metrics (SSIM, LPIPS, FID, CLIPScore) and expert-driven qualitative assessments. Results show that GANs, particularly StyleGAN, produce images with high perceptual quality and structural coherence. Diffusion-based models for inpainting and image variation, such as DALL-E 2, delivered high realism and semantic alignment but generally struggled in balancing visual fidelity with scientific accuracy. Importantly, our findings reveal limitations of standard quantitative metrics in capturing scientific relevance, underscoring the need for domain-expert validation. We conclude by discussing key challenges such as model interpretability, computational cost, and verification protocols, and discuss future directions where generative AI can drive innovation in data augmentation, simulation, and hypothesis generation in scientific research.

Generative Adversarial Networks↗
DOE OSTI2026

ResStock Measure Documentation: Residential Variable-Speed Geothermal Heat Pump (4.4 COP, 30.9 EER)

The goal of this work is to develop energy efficiency, demand flexibility, and other retrofit end-use load shapes (electricity, gas, propane, or fuel oil) that cover a majority of the high-impact, market-ready (or nearly market-ready) measures. "Measures" refers to retrofits that can be applied to buildings during modeling. An "end-use savings shape" is the difference in energy consumption between a baseline building and a building with an energy efficiency, demand flexibility, or other retrofit measure applied. It results in a time-series profile that is broken down by end use and fuel (electricity or on-site gas, propane, or fuel oil use) at each time step. ResStock (TM) is a highly granular, physics-based, bottom-up model that uses multiple data sources, statistical sampling methods, and advanced building energy simulations to estimate the annual subhourly energy consumption of the residential building stock across the United States. The baseline model intends to represent the U.S. residential building stock as it existed in 2018. Technical documentation for the inputs and assumptions in the baseline building stock model is available in Reyna et al. (2025). Calibration and validation of the baseline model results are available in the final technical report of the End-Use Load Profiles project (Wilson et al. 2022). This documentation focuses on a single end-use savings shape measure: Residential Variable-Speed Geothermal Heat Pump (GHP). This document provides the relevant new modeling information for variable-speed systems not previously covered in either the single-stage or two-stage documents. Variable-speed GHPs represent the most efficient option available for this technology: They provide the most savings, with up to 46% for the applicable portion of the housing stock, compared to 31% for less efficient single-stage GHPs. Additional results shown here detail how the savings change for sections of the housing stock with different base heating fuels and in different climate zones, and they show the savings potential by state for both heating and cooling. Utility bills and electric panel impacts are also shown and discussed.

15 GEOTHERMAL ENERGY↗
DOE OSTI2025

Explainable machine learning to quantify the value of proximal remote sensing in latent energy flux estimation

Proximal remote sensing has the potential to provide critical information on vegetation biophysical factors that can predict land-atmosphere exchange of water and energy. Latent energy (LE) flux is traditionally estimated using process-based models which rely on vegetation parameters that change during the growing season. Data-driven models have the potential to address these issues by offering flexible predictor selection and more efficient utilization of the information in predictor sets. These models require careful choice of predictors to avoid redundancy and allow robust cross-validation. In this study we present a systematic and comprehensive evaluation of machine learning (ML) models to assess the capability of meteorological and proximal sensing data for predicting LE at a half-hourly temporal resolution across multiple growing seasons for an agricultural system. The results presented here demonstrate that a model using four environmental predictors in combination with two proximal sensing variables can capture 88 % of the variability in LE. ML models using only three predictors (one meteorological and two proximal remote sensing) captured 81 % of LE variability, offering the best trade-off between performance and complexity. An ML model utilizing only two predictors, one proximal remote sensing variable and downwelling radiation, captured 77 % of LE variability. These results demonstrate the power of proximal remote sensing and meteorological observations to estimate land-atmosphere water vapor exchange, providing a solution where more direct methods such as eddy covariance are not available and for evaluations of agronomic management and genotypic variations.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2021

Evolution of elastic and thermal properties of cementitious composites containing micro-size lightweight fillers after exposure to elevated temperature

This work studies the evolution of elastic and thermal properties of cementitious composites containing micro-size lightweight fillers after exposure to elevated temperatures (up to 800 °C). A multiscale investigation is carried out to study the thermal degradation of cementitious composite materials at multiple scale levels: at cement past level, the dehydration kinetics of cement hydrates (i.e., C–S–H, CH and aluminate hydrates) and development of microcracks are studied as functions of exposure temperatures. The damage mechanism of the inclusion phases and damages within the interfacial transition zone (ITZ) under elevated temperature are also investigated. In addition, the change of mechanical (i.e., elastic moduli, compressive strengths) and thermal (thermal conductivities) properties are measured as functions of the exposure temperature. Based on the experimental studies, a multiscale thermal degradation model is developed where the thermal degradations of cement paste (including water composition, porosity, and solid phase changes), inclusion phases, and the interfaces are captured through a multiscale sub-stepping homogenization scheme. The thermal degradation model is validated through multiple sets of experimental data. Finally, the influence of key parameters including the particle size distribution of the inclusions, the chemical composition, as well as the effects of ITZ damage are studied.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Geometric learning for computational mechanics Part II: Graph embedding for interpretable multiscale plasticity

The history-dependent behaviors of classical plasticity models are often driven by internal variables evolved according to phenomenological laws. The difficulty to interpret how these internal variables represent a history of deformation, the lack of direct measurement of these internal variables for calibration and validation, and the weak physical underpinning of those phenomenological laws have long been criticized as barriers to creating realistic models. In this work, geometric machine learning on graph data (e.g. finite element solutions) is used as a means to establish a connection between nonlinear dimensional reduction techniques and plasticity models. Geometric learning-based encoding on graphs allows the embedding of rich time-history data onto a low-dimensional Euclidean space such that the evolution of plastic deformation can be predicted in the embedded feature space. Finally, a corresponding decoder can then convert these low-dimensional internal variables back into a weighted graph such that the dominating topological features of plastic deformation can be observed and analyzed.

42 ENGINEERING↗
DOE OSTI2023

Optimal adjustment sets for causal query estimation in partially observed biomolecular networks

Abstract Causal query estimation in biomolecular networks commonly selects a ‘valid adjustment set’, i.e. a subset of network variables that eliminates the bias of the estimator. A same query may have multiple valid adjustment sets, each with a different variance. When networks are partially observed, current methods use graph-based criteria to find an adjustment set that minimizes asymptotic variance. Unfortunately, many models that share the same graph topology, and therefore same functional dependencies, may differ in the processes that generate the observational data. In these cases, the topology-based criteria fail to distinguish the variances of the adjustment sets. This deficiency can lead to sub-optimal adjustment sets, and to miss-characterization of the effect of the intervention. We propose an approach for deriving ‘optimal adjustment sets’ that takes into account the nature of the data, bias and finite-sample variance of the estimator, and cost. It empirically learns the data generating processes from historical experimental data, and characterizes the properties of the estimators by simulation. We demonstrate the utility of the proposed approach in four biomolecular Case studies with different topologies and different data generation processes. The implementation and reproducible Case studies are at https://github.com/srtaheri/OptimalAdjustmentSet.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Circuit Analysis of Ionizing Surface Potential Measurements of Electrolyte Solutions

Surface potential measurement values of the gas-liquid interface can be ambiguous despite the numerous electrochemical approaches used for quantification of the reported values. Calibration and normalization methods are not standardized, which often undermines the robustness of the reported values. Surface potential instrumentation and data interpretation also varies significantly across literature. Here, we propose a circuit model for an ionizing surface potential method based on the alpha decay of a radioactive americium-241 electrode. We evaluate the robustness of the circuit model for quantifying the surface potential at the air-aqueous interface. We then show successful validation of our circuit model through determination of the surface tension of the air-electrolyte interface with comparison to respective surface tension literature values. This validation reveals the reliability of surface potential measurements using the americium-241 ionizing method. We also report the surface potential difference of the air/water interface to be –0.49 V ± 0.01 V consistent with hydrogens of water pointing toward the air phase.

47 OTHER INSTRUMENTATION↗
DOE OSTI2024

Validation Framework for Post-Combustion Carbon Capture CFD Simulations

First-principles based computational fluid dynamics (CFD) simulations are proposed as a fundamental tool for investigating solvent-based CO2 absorption in packed columns, due to the ability to accurately represent the underlying non-linear multiscale dynamics. In this work, we employ such models to investigate hydrodynamics of columns with structured by assessing the key hydrodynamic metrics, such as pressure drop and liquid holdup. Our models are validated with experimental data from a specifically designed column for this line of work. The test cases of gas and liquid flowrates and operating conditions were selected through a comprehensive sequential design of experiments approach offered by the CCSI2 toolset.

Panagakos, Grigorios↗
DOE OSTI2025

A Preferences Corpus and Annotation Scheme for Human-Guided Alignment of Time-Series GPTs

The process of time-series forecasting such as predicting trajectories of silicon content in blast furnaces is a difficult task. Most time-series approaches today focus on scalar-type MSE loss optimization. This optimization approach, while widely common, could benefit from the use of human expert or process-level preferences. In this paper, we introduce a novel alignment and fine-tuning approach that involves learning from a corpus of preferred and dis-preferred time-series prediction trajectories. Our contributions include (1) a preference annotation pipeline for time-series forecasts, (2) the application of Score-based Preference Optimization (SPO) to train decoder-only transformers from preferences, and (3) results showing improvements in forecast quality. The approach is validated on both proprietary blast furnace data and the UCI Appliances Energy dataset. The proposed preference corpus and training strategy offer a new option for fine-tuning sequence models in industrial settings.

DPO↗
DOE OSTI2025

Surrogate Modeling of Landau Damping with Deep Operator Networks

Kinetic simulations excel at capturing microscale plasma physics phenomena with high accuracy, but their computational demands make them impractical for modeling large-scale space and astrophysical systems. In this context, we build a surrogate model, using Deep Operator Networks (DeepONets), based upon the Vlasov–Poisson simulation data to model the dynamical evolution of plasmas, focusing on the Landau damping process—a fundamental kinetic phenomenon in space and astrophysical plasmas. The trained DeepONets are able to capture the evolution of electric field energy in both linear and nonlinear regimes under various conditions. Extensive validation highlights DeepONets’ robust performance in reproducing complex plasma behaviors with high accuracy, paving the way for large-scale modeling of space and astrophysical plasmas.

plasma astrophysics↗
DOE OSTI2022

Evaluation and Validation of the n+ 63,65 Cu Cross Sections [Slides]

This presentation discusses the objective of the research which is to update n+ 63,65 Cu cross section evaluations with recently measured data to resolve discrepancies in benchmark performance. It also discusses the models used which are the R -matrix analysis and the analysis of angular distribution coefficients. Additionally, the validation methods that were used are discussed, including the Rez shielding benchmark and the ICSBEP criticality benchmarks. In conclusion, he n+ 63,65 Cu cross sections have been updated via R-matrix analysis up to 100 keV. An increased average capture cross section and the adoption of experimentally based Legendre coefficients lead to improved performance in reactivity benchmarks. In the fast region, the adoption of the JENDL-4.0 cross sections above 4.0 MeV improves the performance in shielding benchmarks. Ultimately, the n 63,65 Cu ENDF files will be submitted to ENDF/B-VIII.1.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2024

Predictive model using artificial neural network to design phase change material-based ocean thermal energy harvesting systems for powering uncrewed underwater vehicles

Uncrewed Underwater Vehicles (UUVs) are a major beneficiary of the phase change material (PCM)-based ocean thermal energy harvesting technology for their mission needs. However, this technology relies on different parameters and energy conversion steps that could be critical to the general energy generation efficiency. Sea trials showed that the design performed lower than their laboratory design specifications. This underperformance results from different factors, mainly the UUV’s trajectory, travel time, underwater ocean currents, temperature fluctuations, and biofouling on the heat exchanger due to long term underwater operations. Therefore, there exists a need to continuously monitor the ambient energy harvesting system and predict system performance, for mission planning purposes. Two major parameters influencing the energy harvesting system include the final pressure inside the hydraulic energy storage vessel or accumulator, and the electrical load value. Here, this work focuses on the hydraulic to electric energy conversion system. Therefore, a combination of numerical model and experimental testing is used to develop a predictive model using artificial neural network using MATLAB. After validation with experimental testing, 1000 data samples obtained from the numerical model are used to train the ANN. Compared to the experimental results, the developed ANN model can predict in less than a second the designed benchtop system’s total efficiency with less than 15 percent maximum error range. This predictive model development represents a cost-effective way for optimization and a computational energy efficient mode aboard UUVs for mission planning for deployed UUVs using PCM-based ocean thermal energy harvesting technology.

30 DIRECT ENERGY CONVERSION↗
DOE OSTI2026

Additional Data Focused on Phase 1 Geared Toward Computational Fluid Dynamics (CFD) validation

A new validation campaign was developed within the Offshore Code Comparison Collaboration, Continued, with Correlation and unCertainty (OC6) to better understand the complex interactions between components of a floating wind system (e.g., columns, pontoons, etc.) in a more generic sense, and to validate modeling approaches for a variety of floating designs. A set of cylinders based on the Offshore Code Comparison Collaboration Continuation (OC4)-DeepCwind semidesign were tested under wave loading, both individually and in different combinations (including the attachment of heave plates of different sizes). The cylinders were held rigid, and pressure sensors were used to measure the distributed loading on the structures, while load cells measured the total integrated hydrodynamic loads.

17 WIND ENERGY↗
DOE OSTI2023

A machine learning approach for identifying variables associated with risk of developing neutralizing antidrug antibodies to factor VIII

A key unmet need in the management of hemophilia A (HA) is the lack of clinically validated markers that are associated with the development of neutralizing antibodies to Factor VIII (FVIII) (commonly referred to as inhibitors). This study aimed to identify relevant biomarkers for FVIII inhibition using Machine Learning (ML) and Explainable AI (XAI) using the My Life Our Future (MLOF) research repository. The dataset includes biologically relevant variables such as age, race, sex, ethnicity, and the variants in the F8 gene. In addition, we previously carried out Human Leukocyte Antigen Class II (HLA-II) typing on samples obtained from the MLOF repository. Using this information, we derived other patient-specific biologically and genetically important variables. These included identifying the number of foreign FVIII derived peptides, based on the alignment of the endogenous FVIII and infused drug sequences, and the foreign-peptide HLA-II molecule binding affinity calculated using NetMHCIIpan. The data were processed and trained with multiple ML classification models to identify the top performing models. The top performing model was then chosen to apply XAI via SHAP, (SHapley Additive exPlanations) to identify the variables critical for the prediction of FVIII inhibitor development in a hemophilia A patient. Using XAI we provide a robust and ranked identification of variables that could be predictive for developing inhibitors to FVIII drugs in hemophilia A patients. These variables could be validated as biomarkers and used in making clinical decisions and during drug development. The top five variables for predicting inhibitor development based on SHAP values are: (i) the baseline activity of the FVIII protein, (ii) mean affinity of all foreign peptides for HLA DRB 3, 4, & 5 alleles, (iii) mean affinity of all foreign peptides for HLA DRB1 alleles), (iv) the minimum affinity among all foreign peptides for HLA DRB1 alleles, and (v) F8 mutation type.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2020

Wave and Offshore Wind Resource in the U.S. Pacific Ocean Minor Outlying Islands

Coastal environments such as islands have unique opportunities for renewable energy resources. This work explores the wave and offshore wind energy potential for the U.S. Pacific Ocean Minor Outlying Islands, including Baker Island, Howland Island, Jarvis Island, Johnston Atoll, Kingman Reef, Palmyra Atoll, and Wake Island. A numerical wave model based on WAVEWATCH III and SWAN (both are NWS / NOAA models) was developed, validated, and executed to generate a 32-year hindcast dataset suitable for resource characterization for each island. A complementary offshore wind resource characterization is provided for the same time period based on the European Centre for Medium-Range Weather Forecasts (ECMWF) Reanalysis v5 (ERA5). Each island has five netcdf files: 1. wave_[island]_annual_J_map.nc: the data used to generate the map of annual averaged omnidirectional wave power (J [kW/m]) 2. wave_[island]_100m_IEC: six IEC parameters at 100m isobath from 1979/01/01 to 2020/12/31, output hourly 3. wave_[island]_5km_IEC: six IEC parameters at 5km from the shoreline 1979/01/01 to 2020/12/31, output hourly 4. wind_island_100mASL_windspeed_timeseries.nc: wind speed timeseries from ERA5 at 100 m above sea level within a 60 km radius of the island (m/s) 1979/01/01 to 2010/12/31, output hourly 5. wind_island_100mASL_winddirection_timeseries.nc: wind direction timeseries from ERA5 at 100 m above sea level within a 60 km radius of the island (degrees) 1979/01/01 to 2010/12/31, output hourly

16 TIDAL AND WAVE POWER↗