Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “model weights”

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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Magnon damping and mode softening in quantum double-exchange ferromagnets

We present a comprehensive analysis of the magnetic excitations and electronic properties of fully quantum double-exchange ferromagnets, i.e. systems where ferromagnetic (FM) ordering emerges from the competition between spin, charge, and orbital degrees of freedom, but without the canonical approximation of using classical localized spins. Specifically, we investigate spin excitations within the Kondo lattice-like model, as well as a two-orbital Hubbard Hamiltonian in proximity to the orbital-selective Mott phase. Computational analysis of the magnon dispersion, damping, and spectral weight within these models reveals unexpected phenomena, such as magnon mode softening and the anomalous decoherence of magnetic excitations as observed in earlier experimental efforts, but explained here without the use of the phononic degrees of freedom. We show that these effects are intrinsically linked to incoherent spectral features near the Fermi level, which arise due to the quantum nature of the local (on-site) triplets. This incoherent spectrum leads to a Stoner-like continuum on which spin excitations scatter, governing magnon lifetime and strongly influencing the dynamical spin structure factor. Our study explores the transition from coherent to incoherent magnon spectra by varying the electron density. Furthermore, we demonstrate that the magnitude of the localized spin mitigates decoherence by suppressing the incoherent spectral contributions near the Fermi level. We also discuss the effective J 1 –J 2 spin Hamiltonian, which can accurately describe the large doping region characterized by the magnon-mode softening. Finally, we show that this behavior is also present in multiorbital models with partially filled orbitals, namely, in systems without localized spin moments, provided that the model is in a strong coupling regime. Our results potentially have far-reaching implications for understanding FM ordering in various multi-band systems. These findings establish a previously unknown direct connection between the electronic correlations of those materials and spin excitations.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2024

An Analysis of the Spatial Variations in the Relationship Between Built Environment and Severe Crashes

Traffic crashes significantly contribute to global fatalities, particularly in urban areas, highlighting the need to evaluate the relationship between urban environments and traffic safety. This study extends former spatial modeling frameworks by drawing paths between global models, including spatial lag (SLM), and spatial error (SEM), and local models, including geographically weighted regression (GWR), multi-scale geographically weighted regression (MGWR), and multi-scale geographically weighted regression with spatially lagged dependent variable (MGWRL). Utilizing the proposed framework, this study analyzes severe traffic crashes in relation to urban built environments using various spatial regression models within Leon County, Florida. According to the results, SLM outperforms OLS, SEM, and GWR models. Local models with lagged dependent variables outperform both the global and generic versions of the local models in all performance measures, whereas MGWR and MGWRL outperform GWR and GWRL. Local models performed better than global models, showing spatial non-stationarity; so, the relationship between the dependent and independent variables varies over space. The better performance of models with lagged dependent variables signifies that the spatial distribution of severe crashes is correlated. Finally, the better performance of multi-scale local models than classical local models indicates varying influences of independent variables with different bandwidths. According to the MGWRL model, census block groups close to the urban area with higher population, higher education level, and lower car ownership rates have lower crash rates. On the contrary, motor vehicle percentage for commuting is found to have a negative association with severe crash rate, which suggests the locality of the mentioned associations.

Alisan, Onur (ORCID:0000000193113984)↗
DOE OSTI2025

Hourly Electricity Demand Profiles for Each County in the Contiguous United States

This dataset provides estimated hourly electricity demand for each county in the contiguous United States from 2016-2023. The demand profiles represent the sum of two components: (1) Weighted averages of reported hourly demand profiles for North American Electric Reliability Corporation balancing authority (BA) regions and subregions, scaled to match annual estimates of county-level retail sales and direct use of electricity and weighted by the estimated percentage of county load served by each BA region or subregion. (2) Weighted averages of modeled hourly, county- and sector-level distributed photovoltaic (DPV) capacity factor profiles, scaled to match annual estimates of on-site consumption of DPV-generated electricity for each county and weighted by the percentage of consumption attributable to each sector Annual county-level retail sales are estimated by aggregating utility-reported sales to the state level and allocating the results to counties according to each county's share of state population. Annual county-level direct use is calculated by aggregating power plant-reported direct use values. Annual county-level on-site consumption of DPV-generated electricity is estimated by aggregating utility-reported net metering data to determine the amount of DPV-generated electricity sold back to the grid for each state, subtracting those values from modeled state-level DPV generation estimates, and allocating the results to counties according to each county's share of statewide modeled DPV generation. The open-source Python code used to develop this dataset is available at "Historical Load Data Repository" link below.

14 SOLAR ENERGY↗
DOE OSTI2026

Estimated Hourly Electricity Demand Profiles for Each County in the Contiguous United States

In this data descriptor, we present hourly electricity demand estimates for each county in the contiguous United States from 2016 to 2023. The demand profiles represent the sum of two components for each county. The first is the weighted average of reported hourly demand profiles for North American Electric Reliability Corporation balancing authority (BA) regions and subregions, scaled to match annual estimates of county-level retail sales and direct use of electricity and weighted by the estimated percentage of county load served by each BA region or subregion. The second is the weighted average of modeled hourly, county- and sector-level distributed photovoltaic (DPV) capacity factor profiles, scaled to match annual estimates of on-site consumption of DPV-generated electricity for each county and weighted by the percentage of consumption attributable to each sector.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

A comparative study of calibration techniques for finite strain elastoplasticity: Numerically-exact sensitivities for FEMU and VFM

Accurate identification of material parameters is crucial for predictive modeling in computational mechanics. Here, the two primary approaches in the experimental mechanics community for calibration from full-field digital image correlation data are known as finite element model updating (FEMU) and the virtual fields method (VFM). In VFM, the objective function is a squared mismatch between internal and external virtual work or power. In FEMU, the objective function quantifies the weighted mismatch between model predictions and corresponding experimentally measured quantities of interest. It is minimized by iteratively updating the parameters of an FE model. While FEMU is seen as more flexible, VFM is commonly used instead of FEMU due to its considerably greater computational expense. However, comparisons between the two methods usually involve approximations of gradients or sensitivities with finite difference schemes, thereby making direct assessments difficult. Hence, in this study, we compare VFM and FEMU in the context of numerically-exact sensitivities obtained through local sensitivity analyses and the application of automatic differentiation software. To this end, we conduct a series of test cases to assess both methods under practical challenges using a finite strain elastoplasticity model.

Automatic differentiation↗
DOE OSTI2024

Surrogate construction via weight parameterization of residual neural networks

Surrogate model development is a critical step for uncertainty quantification or other sample-intensive tasks for complex computational models. Here, in this work, we develop a multi-output surrogate form using a class of neural networks (NNs) that employ shortcut connections, namely Residual NNs (ResNets). ResNets are known to regularize the surrogate learning problem and improve the efficiency and accuracy of the resulting surrogate. Inspired by the continuous, Neural ODE analogy, we augment ResNets with weight parameterization strategy with respect to ResNet depth. Weight-parameterized ResNets regularize the NN surrogate learning problem and allow better generalization with a drastically reduced number of learnable parameters. We demonstrate that weight-parameterized ResNets are more accurate and efficient than conventional feed-forward multi-layer perceptron networks. We also compare various options for parameterization of the weights as functions of ResNet depth. We demonstrate the results on both synthetic examples and a large scale earth system model of interest.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Verifying infectious disease scenario planning for geographically diverse populations

In the face of the COVID-19 pandemic, the literature saw a spike in publications for epidemic models, and a renewed interest in capturing contact networks and geographic movement of populations. There remains a general lack of consensus in the modeling community around best practices for spatiotemporal epi-modeling, specifically as it pertains to the infection rate formulation and the underlying contact or mixing model. We mathematically verify several common modeling assumptions in the literature, to prove when certain choices can provide consistent results across different geographic resolutions, population densities and patterns, and mixing assumptions. The most common infection rate formulation, a computationally low cost per capita infection rate assumption, fails the consistency tests for heterogeneous populations and gravity-weighting assumptions. Future modeling efforts in spatiotemporal disease modeling should be wary of this limitation, particularly when working with more heterogeneous or sparse populations. Our results provide guidance for testing that a model preserves desirable properties even when model inputs mask potential problems due to symmetry or homogeneity. We also provide a recipe for performing this type of verification, strengthening decision support tools.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Toward particle accelerator machine state embeddings as a modality for large language models

Understanding and diagnosing the state of a particle accelerator requires navigating high-dimensional control system data, often involving hundreds of interdependent parameters. We propose a novel multimodal embedding framework that jointly learns representations of machine states from both numerical control system readouts and natural language descriptions. This enables the translation of complex machine conditions into human-readable summaries while maintaining fidelity to the underlying physical system. The obtained embeddings are subsequently adapted to an open-weights large language model via cross-attention conditioning. We demonstrate a first implementation trained on European XFEL machine state data. This work covers the embedding model architecture, training methodology, and presents initial examples demonstrating the model's capabilities in action. Due to the general concept of machine state, the model can be easily adapted to other facilities and control system environments.

Accelerator Physics↗
DOE OSTI2026

Enhanced accuracy through ensembling of randomly initialized auto-regressive models for dynamical systems

Computational mechanics simulations using traditional finite element methods (FEM) require prohibitively expensive computational resources for real-time engineering applications, design optimization, and digital twin implementations. While machine learning (ML) surrogate models offer significant computational speedups, autoregressive ML models for time-dependent mechanical systems suffer from error accumulation that compromises long-term prediction reliability - a critical concern for engineering applications where accuracy over extended time horizons is essential for safety and performance assessments. Here, we propose a deep ensemble framework specifically designed to address this challenge in computational mechanics applications, where multiple ML surrogate models with random weight initializations are trained in parallel and their predictions aggregated during inference. This approach leverages statistical diversity to maximize information gain from a fixed set of training data and to mitigate error propagation, while maintaining the computational efficiency that makes ML surrogates attractive for engineering practice. We validate the framework on three representative problems spanning critical areas of computational mechanics: stress field evolution in heterogeneous microstructures under complex loading (relevant to advanced materials design and composite analysis), planetary-scale shallow water dynamics (applicable to environmental and geotechnical engineering), and Gray-Scott reaction-diffusion systems (relevant to mass transport and chemical process engineering). Across all test cases, the ensemble approach demonstrates consistent error reduction of 15-33% compared to individual models. The codes for this work are available on GitHub (https://github.com/Graham-Brady-Research-Group/AutoregressiveEnsemble_SpatioTemporal_Evolution).

autoregressive prediction↗
DOE OSTI2026

Dynamic Evolution of Mass and Physical Properties of Atmospheric Organic Aerosol under Solar Irradiance

Organic aerosol (OA) particles constitute a substantial fraction of sub-micron particulate mass in the atmosphere and play a critical role in climate system. OA undergoes dynamic aging processes in the atmosphere, with photolytic aging induced by ultraviolet solar irradiance being an important yet poorly characterized mechanism. Knowledge gaps persist regarding the role of volatility transformations during photolytic aging on the OA mass decay kinetics and the evolution of climate-relevant properties, such as hygroscopicity, hindering the model evaluation of OA spatiotemporal distributions and atmospheric budgets. In this study, we conduct isothermal photolytic aging experiments on both laboratory-generated secondary organic aerosols and ambient-collected particles from urban Atlanta, utilizing a high-sensitivity Quartz Crystal Microbalance. Our results reveal that photolytic aging reduces 40–66% of the low-volatility OA mass with lifetimes ranging from 8 to 200 hours under solar irradiance, and 44–92% of the photolytic mass loss is through slow evaporation of semi- or intermediate-volatile products, kinetically limited by their volatility. We observe up to ±50% changes in OA hygroscopicity with the transformation of fresh OA to photo-recalcitrant low-volatility products, associated with changes in oxygen-to-carbon ratio and molecular weight. A kinetic model incorporating photolytic volatility transformation provides a cohesive explanation for the observed photolysis-induced changes in mass, volatility, and hygroscopicity. Our results can help constrain model representation of the dynamic evolutions of mass and climate-relevant properties during photolytic aging processes of the ambient OA, improving our understanding of OA atmospheric behavior and climate impact.

Bai, Bin↗
DOE OSTI2025

Optimization-Based Dynamic Voltage Support of Microgrids Using Energy Storage Systems

A microgrid network is characterized by a high R/X ratio, making the voltage more sensitive to active power changes compared to bulk power systems, where the voltage is regulated primarily by reactive power. Due to its sensitivity, voltage control approaches for microgrids should also consider the active power input coupling, making it very different from conventional power systems. Additionally, as the energy costs associated with active and reactive powers are different and the operational conditions of microgrids connected to active distribution systems vary over time, the ideal controller to provide voltage support must be flexible enough to handle these technical and operational constraints. This paper proposes a model predictive control approach to provide dynamic voltage support using energy storage systems. This approach uses a simplified predictive model of the system to solve the model predictive control problem. By proper selection of model predictive control weighting parameters, the quality of service provided can be adjusted to achieve the desired performance. A simulation study in MATLAB/Simulink validates the proposed approach for the Cordova, Alaska microgrid. Results show that the performance of the voltage support can be adjusted depending on the choice of weight and constraints of the controller.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

IoT-based retrofit information diffusion in future smart communities

Community-scale building retrofits are not merely scaled-up versions of single-building retrofits. They involve complex challenges, such as reconciling individual interests with collective goals and managing the dynamic interplay between buildings through mechanisms like power grids and social connections. Internet of Things (IoT) connectivity holds the potential to leverage these interplays to balance individual and collective interests effectively in smart communities. One critical aspect of this interplay is information diffusion, which shapes how retrofit decisions spread among neighbors, influencing individual choices and ultimately impacting community-level retrofit outcomes. In other words, IoT-based smart devices automatically push tailored retrofit notifications to homeowners, which completely changes the format of information diffusion in the future. To investigate this influence by such information diffusion, the study used CityBES to simulate energy performance for different retrofits and applied an information diffusion model to analyze how decisions spread in a networked community of 192 buildings. The diffusion process was modeled on a weighted, directed network, capturing the dynamics of information flow and decision-making across 16 scenarios. Individual retrofit benefits were evaluated through payback years, while community-level retrofit outcomes were assessed using greenhouse gas (GHG) emission reductions. The results demonstrate that easier information diffusion among neighbors encourages households to prioritize retrofit measures that align with the majority’s optimal choices, even at the expense of individual financial benefits. In this case, such collective prioritization enhanced community-level retrofit performance, increasing GHG emission reductions by up to 29.4 %. However, this improvement came with trade-offs, as the average payback period for households extended by approximately 1.74 years. These findings highlight the potential of IoT-based information diffusion in future smart communities to coordinate individual interests with collective goals, ultimately accelerating community-level building retrofits.

Shu, Lei↗
DOE OSTI2024

Investigating explainable transfer learning for battery lifetime prediction under state transitions

Battery lifetime prediction at early cycles is crucial for researchers and manufacturers to examine product quality and promote technology development. Machine learning has been widely utilized to construct data-driven solutions for high-accuracy predictions. However, the internal mechanisms of batteries are sensitive to many factors, such as charging/discharging protocols, manufacturing/storage conditions, and usage patterns. These factors will induce state transitions, thereby decreasing the prediction accuracy of data-driven approaches. Transfer learning is a promising technique that overcomes this difficulty and achieves accurate predictions by jointly utilizing information from various sources. Hence, we develop two transfer learning methods, Bayesian Model Fusion and Weighted Orthogonal Matching Pursuit, to strategically combine prior knowledge with limited information from the target dataset to achieve superior prediction performance. From our results, our transfer learning methods reduce root-mean-squared error by 41% through adapting to the target domain. Furthermore, the transfer learning strategies identify the variations of impactful features across different sets of batteries and therefore disentangle the battery degradation mechanisms and the root cause of state transitions from the perspective of data mining. These findings suggest that the transfer learning strategies proposed in our work are capable of acquiring knowledge across multiple data sources for solving specialized issues.

25 ENERGY STORAGE↗
DOE OSTI2025

network-pruner (Neural network pruning analysis) [SWR-25-113]

This repository implements an iterative magnitude pruning algorithm for pruning neural networks in PyTorch. The pruning method involves gradually removing less significant weights from the model to achieve a specified sparsity, followed by fine-tuning the pruned model to recover performance.

Griffin, Kevin [National Renewable Energy Laborato↗
DOE OSTI2026

Chemical Recommender System: Replacement Suggestions for Small Molecules

The Chemical Recommender System (CRS) is an open-source, high-performance toolkit that enables real-time similarity searches across the complete PubChem database (over 50 million molecules) using commodity hardware. The CRS addresses critical limitations in existing chemical informatics platforms through a novel vector database infrastructure, extensible model integration capabilities, and complete algorithmic transparency. The system implements a vector database deployment with partitioned indexing that achieves a ~60x speedup over traditional approaches. A containerized model integration framework allows researchers to seamlessly incorporate custom predictive models into the full-scale search and scoring pipeline, while complete configurability of search parameters, filtering logic, and scoring functions provides capabilities not available in existing black-box solutions. Beyond structural similarity, the CRS integrates OPERA QSAR models for thermophysical and toxicity predictions, RDKit synthetic accessibility scoring, and user-defined models to compute weighted final replacement scores. The complete system is accessible through an interactive web application supporting real-time progress monitoring, post-processing score re-weighting, automated PDF reporting, and batch processing capabilities.

Nair, Parthiv Anand [Sandia National Laboratories ↗
DOE OSTI2025

Conformal Hierarchical Simulation-Based Inference with Local Validity

Trustworthy and interpretable uncertainty quantification is a long-standing challenge in artificial intelligence. Simulation-based inference (SBI) comprises a broad swath of approaches for estimating latent parameters with uncertainties. Although flexible neural density estimators in SBI can be remark- ably expressive capturing highly structured, high-dimensional posteriors their credible regions can be badly mis-calibrated and are often only accompanied by heuristic coverage checks. We present the first SBI framework that delivers finite-sample local valid coverage guarantees that hold in the neighborhood of each observation. Our framework can couple any off-the-shelf hierarchical SBI engine with a confor- mal Bayesian post-processing step that operates on the posterior predictive density. A kernel-weighted conformity score adapts the conformal quantile to the local geometry of the data, yielding prediction sets that are simultaneously (i) marginally calibrated, (ii) locally valid, and (iii) hierarchical, handling global and observation-specific parameters in a single pass. Through experiments on synthetic data and benchmarks from neuroscience and physics, we show that our approach attains 1 − α coverage, where prior SBI methods under- or over-cover. Our approach also maintains a competitive, credible set size with minimal computational overhead. Finally, our approach can be used to make predictions on real data and give valid credible regions modulo weight-initialization-based model mis-specification.

Trivedi, Shubhendu [Fermilab]↗
DOE OSTI2026

PowerModelsGAT-AI: Physics-Informed Graph Attention for Multi-System Power Flow With Continual Learning

Solving the alternating current power flow equations in real time is essential for secure grid operation, yet classical Newton–Raphson solvers can be slow under stressed conditions. Existing graph neural networks for power flow are typically trained on a single system and often degrade on different systems. We present PowerModelsGAT-AI, a physics-informed graph attention network that predicts bus voltages and generator injections. The model uses bus-type-aware masking to handle different bus types and balances multiple loss terms, including a power-mismatch penalty, using learned weights. We evaluate the model on 14 benchmark systems (4 to 6,470 buses) and train a unified model on 13 of these under contingency conditions with up to two branch outages, achieving an average normalized mean absolute error of 0.89% for voltage magnitudes and R 2 >0.99 for voltage angles. We also show continual learning: when adapting a base model to a new 1,354-bus system, standard fine-tuning causes severe forgetting with error increases exceeding 1000% on base systems, while our experience replay and elastic weight consolidation strategy keeps error increases below 2% and in some cases improves base-system performance. Interpretability analysis shows that learned attention weights correlate with physical branch parameters (susceptance: r=0.38 ; thermal limits: r=0.22 ), and feature importance analysis supports that the model captures established power flow relationships.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Dataset for "Machine Learning Ensembles Can Enhance Hydrologic Predictions and Uncertainty Quantification" Willard et al. (2025).

This data release provides all data and code used in the paper " "Machine Learning Ensembles Can Enhance Hydrologic Predictions and Uncertainty Quantifications" Willard et al. (2025)" to model stream temperature, evaluate, and assess results. The associated manuscript explores the effect of different ensemble construction techniques across different common machine learning (ML) architectures for predictions in unmonitored basins. Modeling was done using long short-term memory (LSTM), gated recurrent unit (GRU), temporal convolution network (TCN), and extreme gradient boosting (XGBoost) models, and stream site coverage spans 1362 locations across the conterminous United States. The ensemble construction techniques investigated include ensemble by random weight initialization, differing hyperparameters, different random subsets of training data, different subselections of input features, different architectures, and Monte Carlo Dropout. The data is organized into these items items:Code repository and data for the paper " "Machine Learning Ensembles Can Enhance Hydrologic Predictions and Uncertainty Quantifications" Willard et al. (2025).Code: stream_temp_ml_regionalization.zip contains the code repositoryData to run the code:- data_dir.zip -- contains all files that should be moved to the "DATA_DIR" variable defined in the "set_env_vars.sh" script in the code repository- metadata_dir.zip -- contains all files that should be moved to the "METADATA_DIR" variable defined in the "set_env_vars.sh" script in the code repositoryData produced by the code and used in the paper:- outputs_dir.zip - contains model output and results (outputs_dir/results), model weights (outputs_dir/models), and all other outputs used for the paper including feature importances.To cite this code, please use the following BibTeX or MLA entries:bibtex:@misc{willard2025streamensembles,author = {Jared Willard and Charuleka Varadharajan},title = {Dataset for "Machine Learning Ensembles Can Enhance Hydrologic Predictions and Uncertainty Quantification"},year = {2024},doi = {10.15485/2527393},publisher = {ESS-DIVE Repository},url = {https://data.ess-dive.lbl.gov/datasets/doi:10.15485/2527393}}MLA: Willard, Jared, et al. Dataset for "Machine Learning Ensembles Can Enhance Hydrologic Predictions and Uncertainty Quantification". 2025. ESS-DIVE Repository, doi:10.15485/2448016.

54 ENVIRONMENTAL SCIENCES↗