Search NASA⌕ Search

SEARCH · Search NASA

Results for “Model Based”

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 217 records · Page 12
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

wa-hls4ml and lui-gnn: A benchmark and GNN-based surrogate model for hls4ml resource and latency estimation

As machine learning (ML) increasingly serves as a tool for addressing real-time challenges in scientific applications, the development of advanced tooling has significantly reduced the time required to iterate on various designs. These advancements have solved major obstacles, but also exposed new challenges. For example, processes that were not previously considered bottlenecks, such as model synthesis, are now becoming limiting factors in the rapid iteration of designs. To reduce these emerging constraints, multiple efforts are being launched toward designing an ML-based surrogate model that estimates resource usage of synthesized accelerator architectures. This model would reduce the design iteration time, especially when designing within a set of given hardware constraints. This approach shows considerable potential, but as it stands, the effort is early and would benefit from coordination and standardization to assist future work as it emerges. We introduce wa-hls4ml, a benchmark for ML accelerator resource and latency estimation, and its corresponding initial dataset of more than 100,000 fully connected neural networks, all synthesized using hls4ml and targeting Xilinx FPGAs. In addition to the resource utilization and latency data provided, the dataset includes generated artifacts and log files for many of the synthesized neural networks, in order to support future research in ML-based code generation. The benchmark evaluates the performance of resource and latency predictors against several common ML model architectures, primarily originating from scientific domains, as exemplar models, as well as the average performance across a subset of the dataset. We measure the performance of a given predictor model through multiple metrics, including $R^2$ score and SMAPE on regression tasks, as well as inference time to further characterize the estimator under test. Additionally, we introduce the latency/utilization inference graph neural network (lui-gnn), a surrogate model that uses a graph neural network to represent input architectures in the form of a directed graph. This graph representation allows for a diverse set of model architectures to all be effectively handled by a surrogate model. We present the architecture and performance of the model, as evaluated by the new proposed benchmark, including SMAPE, $R^2$ score, and inference times, and find that lui-gnn generally predicts latency and utilization for the 75\% quantile within several percent of the synthesized resources on the synthetic test dataset, indicating that this approach of estimating resource and latency via a surrogate models has promise and warrants further research.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2026

Data-based filtered dissipation rate modelling for multi-modal turbulent combustion: evaluating a priori model generalizability

Manifold-based models offer a computationally efficient alternative to directly transporting the thermochemical state in computational simulations of turbulent reacting flows, projecting the high-dimensional thermochemical state-space onto a low-dimensional manifold. Recent efforts have yielded a manifold-based model applicable to multi-modal combustion, enabling reconstruction of the thermochemical state from solutions to two-dimensional manifold equations in mixture fraction and generalized progress variable that are parameterised by three scalar dissipation rates. In coarse-grained simulations such as Large Eddy Simulation (LES), closure of the multi-modal manifold equations and subfilter variances/covariance requires closure of three filtered scalar dissipation rates. Here, the present work adopts a data-based approach, providing closure for the three filtered scalar dissipation rates via deep neural networks (DNNs). High-fidelity datasets corresponding to an autoigniting n-dodecane jet flame and a bluff body swirl-stabilized confined lifted spray flame of two aviation fuels (Jet-A and C1) with different ignition propensities are leveraged to generate training data that spans a diverse range of thermodynamic conditions and combustion modes, including low- and high-temperature ignition regimes in addition to premixed and nonpremixed behaviour. A final DNN model is trained to enforce inherent physical constraints by learning nonlinear functional transformations of the three filtered scalar dissipation rates. The generalizability of this constrained DNN model is demonstrated a priori via conditional statistics evaluated on the lifted spray flame with C1–a configuration that had not been included in the training data. Excellent DNN agreement with conditional DNS statistics is observed, and integrated gradients are computed to identify the most sensitive input variables. The similarity of the marginal PDFs of the most informative input variables and outputs across configurations are quantified via the Wasserstein metric, demonstrating that data-based models may successfully generalize to unseen parametric conditions so long as the most informative input variables share similar distributions across training and testing datasets.

Data-based modelling↗
DOE OSTI2025

STARTR: An Open-Source MARVEL model for the NRIC Virtual Test Bed [Poster]

The National Reactor Innovation Center (NRIC) seeks to improve the understanding of microreactor physics in industry and academia through the development of a Microreactor Applications Research Validation and Evaluation (MARVEL) reactor-based model, published on the Virtual Test Bed (VTB). To achieve this goal, the Sodium-cooled Thermal-spectrum Advanced Research Test Reactor (STARTR) model was built using publicly available MARVEL specifications where possible and approximations where applicable, and was optimized for fast runtimes for researchers to receive rapid simulation feedback. STARTR will fill a gap between stakeholder interest and available models, as the first Sodium-cooled Thermal Reactor (STR) hosted on the VTB with baseline performance sanctioned by INL. This project involved the definition of all materials used in the reactor, geometry and all reactor subcomponents, and assertion of tallies and simulation settings within OpenMC 0.13.3. This poster details a small subset of the overall reactor physics testing: the two-dimensional power peaking factors and the flux energy spectrum, as well as plots of the created geometry. Future work includes code-to-code verification between the OpenMC-based model and a separately designed MCNP 6.2-based model.

21 - SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLAN↗
DOE OSTI2025

HOLISTIC CREDIBILITY ASSESSMENT OF A MACHINE LEARNING-BASED SURROGATE MODEL IN AN AERODYNAMICS APPLICATION

Elements of ASME V&V 20 credibility assessment methodology are used in tandem with credibility assessment tools from the machine learning community to assess the credibility of a deep neural network based surrogate model. This surrogate model is trained, tested, validated, and employed in the context of aerodynamic coefficient prediction for a NACA 0012 airfoil in subsonic and transonic flow. The parameter space is defined by angle of attack, Reynolds number, and Mach number.

Kirsch, Jared Roelof [Sandia National Laboratories↗
DOE OSTI2024

Adaptive Patching for High-resolution Image Segmentation with Transformers

Attention-based models are proliferating in the space of image analytics, including segmentation. The standard method of feeding images to transformer encoders is to divide the images into patches and then feed the patches to the model as a linear sequence of tokens. For high-resolution images, e.g. microscopic pathology images, the quadratic compute and memory cost prohibits the use of an attention-based model, if we are to use smaller patch sizes that are favorable in segmentation. The solution is to either use custom complex multi-resolution models or approximate attention schemes. We take inspiration from Adapative Mesh Refinement (AMR) methods in HPC by adaptively patching the images, as a pre-processing step, based on the image details to reduce the number of patches being fed to the model, by orders of magnitude. This method has a negligible overhead, and works seamlessly with any attention-based model, i.e. it is a pre-processing step that can be adopted by any attention-based model without friction. We demonstrate superior segmentation quality over SoTA segmentation models for realworld pathology datasets while gaining a geomean speedup of 6.9× for resolutions up to 64K2, on up to 2, 048 GPUs.

Zhang, Enzhi↗
DOE OSTI2025

Standard Library Grid-Forming Hybrid Control Inverter-Based Resource Model Specification (REGFM_C1)

This document describes a standard library grid-forming (GFM) hybrid control inverter-based resource (IBR) model. The GFM hybrid control approach implements both a typical GFM control and a typical grid-following (GFL) control inside one single inverter simultaneously, so that it can take advantage of both methods without comprising the benefits of a typical GFM. The initial version of model specification was jointly developed by Pacific Northwest National Laboratory (PNNL), Tesla Energy, and EPRI, and it was revised multiple times later to incorporate suggestions from WECC MVS members. Tesla Energy provided main control blocks to support the development of this model specification. This standard library model is developed to help the utility industry better understand the GFM technology. The model could be used to represent equipment for long-term planning studies where vendor-specific models are not available. As equipment matures and improves, standard library models will be updated to capture the new functionalities of GFMs. It is not intended that these models will always remain representative of all future GFM technologies.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2026

Benchmarking of three DWM-based wake models at below-rated wind speeds

Wind turbine wake models are essential tools for predicting power losses and structural loads in wind farms. Among these, the dynamic wake meandering (DWM) model, included as a recommended approach in the International Electrotechnical Commission design standard, is a widely used engineering-fidelity method that balances accuracy and computational cost. This study compares the performance of three DWM-based wake model implementations (from the Technical University of Denmark, the National Renewable Energy Laboratory, and the Institute for Energy Technology) under below-rated wind speed conditions. Model predictions of wake flow, power output, and structural loads for a four-turbine row are evaluated across different ambient turbulence levels and wind-direction misalignments and compared against high-fidelity large-eddy simulation results. All three models captured the overall wake evolution and mean turbine performance with reasonable accuracy; their predicted time-averaged thrust and power were typically within 5 %–10 % of the large-eddy simulation benchmark. However, notable differences emerged in wake structure and unsteady load predictions, with discrepancies increasing for turbines further downstream. These differences highlight the importance of modelling choices such as wake summation and turbulence treatment, which strongly influence power-deficit and fatigue-load predictions. Comparison with large-eddy simulations reveals each approach's strengths and weaknesses, indicating where improvements are needed. Overall, the findings point to specific refinements for DWM models to improve their fidelity, ultimately enabling more robust wake predictions for wind farm design and operation.

17 WIND ENERGY↗
DOE OSTI2024

ORBIT: Oak Ridge Base Foundation Model for Earth System Predictability

Earth system predictability is challenged by the complexity of environmental dynamics and the multitude of variables involved. Current AI foundation models, although advanced by leveraging large and heterogeneous data, are often constrained by their size and data integration, limiting their effectiveness in addressing the full range of Earth system prediction challenges. To overcome these limitations, we introduce the Oak Ridge Base Foundation Model for Earth System Predictability (ORBIT), an advanced vision transformer model that scales up to 113 billion parameters using a novel hybrid tensor-data orthogonal parallelism technique. As the largest model of its kind, ORBIT surpasses the current climate AI foundation model size by a thousandfold. Performance scaling tests conducted on the Frontier supercomputer have demonstrated that ORBIT achieves 684 petaFLOPS to 1.6 exaFLOPS sustained throughput, with scaling efficiency maintained at 41% to 85% across 49,152 AMD GPUs. These breakthroughs establish new advances in AI-driven climate modeling and demonstrate promise to significantly improve the Earth system predictability.

Wang, Xiao↗
DOE OSTI2024

Deep learning-based predictive models for laser direct drive at the Omega Laser Facility

The rich and complex physics of inertial confinement fusion provides a unique and challenging space for high-fidelity first-principles modeling. Consequently, simulation codes that are used to design experiments are computationally expensive and lack the predictive capability required for extensive parameter exploration in search of a high-performing design for laser direct drive. In this article, we present two deep-learning-based predictive models intended to address these difficulties. The first model (TL DNN) acts as a fast emulator of simulations as well as experiments at the Omega Laser Facility. This model is trained on a simulation database and subsequently calibrated on experimental data using transfer learning. To facilitate the development of this model, an autoencoder is developed to reduce the dimensionality of the input space by compressing the laser pulse input. The model predicts key experimental scalar observables of Omega experiments with high accuracy and minimal computational cost. This deep neural net enables rapid exploration of a high-dimensional input parameter space for an optimal implosion design. The second model (DNN SM+) aims to extend the statistical modeling work of Lees et al. [Phys. Rev. Lett. 127, 105001 (2021)], by increasing the complexity of the model space and allowing for coupling between degradation terms. Since the model capacity of DNN SM+ is higher than the model of Lees et al., DNN SM+ can potentially provide an improvement in predictive capability, and we use this model to provide insight into complicated degradation dependencies.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

Generalization error guaranteed auto-encoder-based nonlinear model reduction for operator learning

Many physical processes in science and engineering are naturally represented by operators between infinite-dimensional function spaces. The problem of operator learning, in this context, seeks to extract these physical processes from empirical data, which is challenging due to the infinite or high dimensionality of data. An integral component in addressing this challenge is model reduction, which reduces both the data dimensionality and problem size. In this paper, we utilize low-dimensional nonlinear structures in model reduction by investigating Auto-Encoder-based Neural Network (AENet). AENet first learns the latent variables of the input data and then learns the transformation from these latent variables to corresponding output data. Our numerical experiments validate the ability of AENet to accurately learn the solution operator of nonlinear partial differential equations. Furthermore, we establish a mathematical and statistical estimation theory that analyzes the generalization error of AENet. Finally, our theoretical framework shows that the sample complexity of training AENet is intricately tied to the intrinsic dimension of the modeled process, while also demonstrating the robustness of AENet to noise.

Auto-encoder↗
DOE OSTI2024

Temperature and Composition Dependence Modeling of Viscosity and Electrical Conductivity of Low-Activity Waste Glass Melts

The development of models that accurately relate the properties of a glass melt to its temperature and composition is important for glass formulation, melter control, and modeling the melt flow, refractory corrosion, and production rate. Using a database consisting of more than 4,000 data points measured between 900 °C and 1250 °C for over 600 unique low-activity waste glass compositions, we developed models for the melt viscosity and electrical conductivity. Models based on the Gaussian process regression approach outperformed models based on the Vogel–Fulcher–Tammann equation according to four standard metrics and yielded reliable prediction intervals. The models found primarily linear effects between properties and individual components, except for the effect of the Na 2 O mass fraction on the electrical conductivity. The effects were found to be consistent with current theories on physical processes involved with those properties.

36 MATERIALS SCIENCE↗
DOE OSTI2025

GrainPaint: A multi-scale diffusion-based generative model for microstructure reconstruction of large-scale objects

Simulation-based approaches to microstructure generation can suffer from a variety of limitations, such as high memory usage, long computational times, and difficulties in generating complex geometries. Generative machine learning models present a way around these issues, but they have previously been limited by the fixed size of their generation area. Here, we present a new microstructure generation methodology leveraging advances in inpainting using denoising diffusion models to overcome this generation area limitation. We show that microstructures generated with the presented methodology are statistically similar to grain structures generated with a kinetic Monte Carlo simulator, SPPARKS.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Unrolled Video Super-Resolution Network with Autoregressive Prior for the Case of Known Motion

Real-time detection and classification of distant objects is necessary for many national security applications. However, when objects are far from the sensor, they occupy only a small number of pixels in the captured video, limiting the amount of visual detail available for recognition. State-of-the-art classification methods typically rely on high-resolution (HR) video streams to capture characteristic object features, but obtaining such detail is challenging for distant objects that occupy only a few pixels. This motivates the development of video super-resolution (VSR) methods that enhance object classification by recovering fine details from low-pixel representations. Current VSR methods rely either on model-based optimization, which is interpretable but computationally expensive, or on learning-based approaches, which are efficient and high-performing but often lack flexibility and interpretability. In this report, we propose an end-to-end trainable unrolled VSR network, UVSRNet, which super-resolves each frame in a video by exploiting sub-pixel motion between neighboring low-resolution (LR) frames as well as incorporating high-frequency detail from previously super-resolved frames. In particular, by unrolling a plug-and-play (PnP) half-quadratic splitting (HQS) algorithm, we leverage a model-based data-fitting module alongside a learning-based autoregressive prior module. This combination yields a method that maintains the flexibility and interpretability of model-based methods while achieving the performance advantages of learning-based methods.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗
DOE OSTI2025

Optimization based process modeling of an anaerobic membrane bioreactor system: Application to swine wastewater

To maintain current levels of consumption in the economy with the dwindling supply of non-renewable material and energy, alternative resource streams more traditionally viewed as waste streams must be considered. Fermentation of high-strength wastewaters is one such pathway that allows for the recovery of energy, nitrogen, phosphorus, and carbon compounds. Anaerobic membrane bioreactors (AnMBRs) are an emerging technology that allow for the digestion of wastewater in a much smaller footprint than traditional anaerobic digesters. Adoption of this technology into industry has been limited by membrane capital and cleaning costs, but these costs may be offset through the recovery of valuable products. To evaluate the viability of AnMBR technology in the context of swine wastewater treatment, an optimization-based process model built upon Anaerobic Digestion Model No. 1 (ADM1) has been developed. Modeling results show that a swine wastewater stream provides potential for net positive energy generation from the AnMBR system in most cases. Sensitivity analyses around important variables were conducted to determine focus areas for future research into AnMBR technology and evaluate the robustness of the model to microbial variables that may change with different microbial communities.

09 BIOMASS FUELS↗
DOE OSTI2026

Characterizing Spatial and Temporal Variability of California’s Coastal Upwelling Using a Satellite-Derived CUTI Index

Ocean upwelling off California is a wind-driven coastal process with complex interactions between spatial wind patterns and sea surface temperatures. Large-scale spatial and temporal upwelling characterizations are traditionally based on numerical models, while quantifying upwelling with direct observations is not straightforward. To complement model-based upwelling characterizations, here we use satellite estimates of winds, sea surface temperatures, and ocean currents along the California coast to calculate the coastal upwelling transport index (CUTI), originally calculated from a numerical ocean model. The CUTI framework accounts for both Ekman and geostrophic offshore-directed ocean transport, the latter of which is often neglected in satellite-based upwelling assessments. The approach yields the CUTI over a 30-yr period at a daily temporal and 0.25° spatial resolution to analyze upwelling patterns, with focus on potential Morro Bay and Humboldt wind energy areas. Morro Bay (CUTI median of 0.63 m 2 s −1 ) exhibits stronger, more consistent upwelling throughout the year, whereas Humboldt (CUTI median of 0.45 m 2 s −1 ) exhibits a pronounced seasonal cycle with strongest upwelling in the summer and occasional downwelling in winter. The cluster analysis of 1993–2022 satellite maps of CUTI identifies four characteristic spatial upwelling patterns along the coast, corresponding to distinct spatial distributions of sea surface temperature anomalies, Ekman transport, and geostrophic ocean water transport. This dataset provides an observation-based foundation for characterizing natural coastal upwelling off the California coast, showing good agreement with the original model CUTI while being based on satellite data and offering increased spatial resolution.

16 TIDAL AND WAVE POWER↗
DOE OSTI2024

Dataset for scientific paper "Simulated plant‑mediated oxygen input has strong impacts on fine‑scale porewater biogeochemistry and weak impacts on integrated methane fluxes in coastal wetlands", a modeling study based on field observation at the tidal salt marshes of the Parker River Estuary, Massachusetts, United States

This dataset is the raw and processed data for the paper "Simulated plant ‑ mediated oxygen input has strong impacts on fine ‑ scale porewater biogeochemistry and weak impacts on integrated methane fluxes in coastal wetlands". This study investigated how plant-mediated oxygen input affects subsurface biogeochemical reactions of organic carbon degradation and the resulting methane emissions of coastal wetlands by model simulation. We used the subsurface geochemical simulator PFLOTRAN for the modeling, which produced the simulated changes in porewater chemical substances and methane emissions over 10 days under different scenarios of plant-mediated oxygen input.Specifically, this dataset contains: 1) the input files for PFLOTRAN of all simulation runs conducted in this study. Those files are with an extension of ".in", containing information of the biogeochemical reaction network (stoichiometry, reaction rate, Monod constants, etc), fluid flow rate and oxygen concentration in the fluid which together simulated the plant-mediated oxygen input, the configuration of artificial reactions that simulated the methane fluxes, etc. The PFLOTRAN input files are text files, which can be opened by NotePad, but running these input files will require proper installation of PFLOTRAN (instruction: https://documentation.pflotran.org/user_guide/how_to/installation/installation.html). 2) the raw and processed model output from PFLOTRAN of all simulation runs, and 3) the python scripts used to process the raw model output, including random allocation of root cells, converting raw data into organized formats, calculating the methane fluxes based on the model output, data visualization, etc. The raw and processed model output from PFLOTRAN are in .spydata format, which can be viewed with Python. and 3) the python scripts for data processing and analysis are programming scripts, which can be opened with Python.This modeling work, in particular the model parameterization of root density and initial conditions of porewater concentrations of biogeochemical substances, was based on field measurements at the salt marsh of the Upper Parker River Estuary, Massachusetts, United States.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Meshfree simulation and prediction of recrystallized grain size in friction stir processed 316L stainless steel

Friction stir processing (FSP) is a promising solid-phase microstructural modification technique that can repair and enhance damaged stainless steel surfaces exposed to harsh environments. The quality of the repaired material is closely correlated to the recrystallized grain size in the stir zone (SZ), which is influenced by the thermomechanical conditions dictated by FSP process parameters. Thus, establishing a reliable relationship between these parameters and recrystallized grain size in the SZ is crucial for optimizing repair quality. However, existing experimental approaches often rely on indirect temperatures measured far from the SZ, along with rough strain rate estimations, which are imprecise and time-consuming. Meanwhile, existing mesh-based modeling methods usually face numerical challenges when dealing with the large material deformations inherent in FSP. Here, to address these issues, this study introduces a meshfree process model for FSP based on the smoothed particle hydrodynamics (SPH) method, aimed at predicting process conditions under different parameters. The model is validated using experimental data from 11 combinations of tool traverse and rotation speeds on 316 L stainless steel. Correlations between process parameters, material flow, temperature, strain, strain rate, and recrystallized grain size are revealed through SPH simulations and electron backscatter diffraction (EBSD) imaging. The results show that in situ SZ temperatures range from 1071 to 1322°C, which exceed the tool temperature by over 300°C. Furthermore, SZ temperature, strain rate, and grain size increase monotonically with higher tool temperature and faster traverse speed. A relationship is then established between the model-predicted Zener-Hollomon parameter and the recrystallized grain size based on EBSD data, expressed as ln(d) = -0.364 ln(Z) + 14.673. Finally, this relationship exhibits satisfactory accuracy with errors of less than 26.9% in predicting grain sizes at various SZ locations, which offers valuable insights for optimizing FSP repair processes for 316 L stainless steel.

316L stainless steel↗
DOE OSTI2025

Chromatic Transport Models for ImpactX

This note describes the basic levels of Hamiltonian approximation (for straight-axis elements) that are used in the symplectic beam dynamics modeling code ImpactX. These include: purely linear models, models based on a paraxial (chromatic) expansion of the Hamiltonian, and models based on the exact nonlinear Hamiltonian. The focus here is on paraxial (chromatic) models.

43 PARTICLE ACCELERATORS↗