Search NASA⌕ Search

SEARCH · Search NASA

Results for “model 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 181 records · Page 10
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Data Quality Monitoring for the Hadron Calorimeters Using Transfer Learning for Anomaly Detection

The proliferation of sensors brings an immense volume of spatio-temporal (ST) data in many domains, including monitoring, diagnostics, and prognostics applications. Data curation is a time-consuming process for a large volume of data, making it challenging and expensive to deploy data analytics platforms in new environments. Transfer learning (TL) mechanisms promise to mitigate data sparsity and model complexity by utilizing pre-trained models for a new task. Despite the triumph of TL in fields like computer vision and natural language processing, efforts on complex ST models for anomaly detection (AD) applications are limited. In this study, we present the potential of TL within the context of high-dimensional ST AD with a hybrid autoencoder architecture, incorporating convolutional, graph, and recurrent neural networks. Motivated by the need for improved model accuracy and robustness, particularly in scenarios with limited training data on systems with thousands of sensors, this research investigates the transferability of models trained on different sections of the Hadron Calorimeter of the Compact Muon Solenoid experiment at CERN. The key contributions of the study include exploring TL’s potential and limitations within the context of encoder and decoder networks, revealing insights into model initialization and training configurations that enhance performance while substantially reducing trainable parameters and mitigating data contamination effects.

47 OTHER INSTRUMENTATION↗
DOE OSTI2022

HPC Analytics of Fused Thermal Plants Data to Optimize Operating Envelope

In this project, ORNL extensively reviewed the ORAP RAM data, and it guided us to develop machine learning models that can predict time to next failures and forecast failure trends, which will be useful for optimizing power plant operation strategies. More specifically, we trained multiple random forest models and evaluated the model accuracy to validate with 10+ years of historical data. In addition, we implemented a web-based graphical user interface system for the models to show how our models can be used in more intuitive ways. This proof of concept allowed exploration of model use with power plant operators in mind. Developed machine learning models will be helpful for managing risks, planning maintenance and operation, ultimately reducing the down time and increasing the service hours. For future work, there are several interesting research topics including but not limited to model enhancement, creating synergy with traditional failure modeling approaches, and data-driven actionable recommendation and suggestions.

20 FOSSIL-FUELED POWER PLANTS↗
NASA NTRS1971

Propellant thermal stratification

The term thermal stratification is used to express nonuniform heat distribution within the bulk propellant. The nonuniform distribution of heat results in significant temperature variations in booster propulsion propellants and causes an undesirable increase in the self-pressurization rate of cryogen storage systems. A semiempirical prediction method has been developed for high gravity environments and is adequate for design purposes; model accuracy is somewhat limited to similarity in tank geometries, and additional work is needed to extend the correlation range. Several low gravity environment models that cover a broad range of predicted results have been developed. There are no applicable data by which any of these models may be selected in preference over the others.

Winstead, T. W.↗
NASA NTRS1986

Identification of linearized equations of motion for the fixed wing configuration of the rotor systems research aircraft

The purpose of this report is to establish linear, decoupled models of rigid body motion for the fixed wing configuration of the Rotor Systems Research Aircraft (RSRA). Longitudinal and lateral control surface fixed linear models were created from aircraft time histories using current system identification techniques. Models were obtained from computer simulation at 160 KCAS and 200 KCAS, and from flight data at 160 KCAS. Comparisons were performed to examine modeling accuracy, variation of dynamics with airspeed and correlation of simulation and flight data results. The results showed that the longitudinal and lateral linear models accurately predicted RSRA dynamics. The flight data results showed that no significant handling qualities problems were present in the RSRA fixed wing aircraft at the flight speed tested.

Balough, D. L.↗
DOE OSTI2025

Transfer learning of neural surrogates on multifidelity groundwater simulations

Multifidelity data used in the paper published in Advances in Water Resources 206 (2025) 105140, https://doi.org/10.1016/j.advwatres.2025.105140 The code used to process the data is openly available on GitHub at https://github.com/Model-Reduction-and-UQ-Group/Transfer_Learning_K_reconstruction Computationally inexpensive surrogates of process-based models, such as deep neural networks, enable ensemble-based computations used in risk assessment, data assimilation, etc. However, generation of large datasets required to train a neural network can be as expensive as the ensemble simulations themselves. We ameliorate this challenge by using data from multifidelity (MF) groundwater simulations and transfer learning (TL) to reduce data generation costs while maintaining model accuracy. As a computational example, we train a deep convolutional neural network (CNN) to reconstruct permeability fields from saturation maps derived from a multiphase flow model. Starting with very low- and low-fidelity data generated on increasingly coarse meshes, we pretrain the CNN, followed by output-layer training and fine-tuning using only a limited number of high-fidelity samples. We demonstrate the surrogate’s robustness when interpreting low-quality inputs—such as interpolated maps or data affected by noise—which has strong implications for the applicability in practical hydrogeological scenarios. This multilevel MF-TL strategy achieves a favorable trade-off between computational efficiency and predictive accuracy, significantly outperforming high-fidelity-only approaches under the same computational budget.

Chiofalo, Alessia [University of Bologna] (ORCID:0↗
DOE OSTI2021

A hierarchical Bayesian model for background variation in radiation source localization

In this paper, we apply a new model to account for varying background radiation in radiological source localization. We present a hierarchical Bayesian model that simultaneously infers background and source location parameters without requiring separate estimation of the background radiation at each detector location. We employ a simplified photon transport model to reduce the computational expense of Bayesian model calibration. Furthermore, we demonstrate the model accuracy by localizing a cesium-137 source in a simulated city block, and we analyze experimental field measurements with varying background. In both cases, the model provides sufficient fidelity that we can locate the source while simultaneously estimating background radiation.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2024

Large-Scale Visualization of 3D Unstructured Groundwater Model Using Cave Automated Virtual Environment

The immersive three-dimensional (3D) virtual reality (VR) visualization of groundwater models allows us to deepen our understanding of aquifer systems and provide better solutions to present groundwater-related problems, such as groundwater recharge, water quality, and sustainability. Visualization assists in accurately developing groundwater models and revealing important subsurface features, including faulting, folding, and unconformity. However, assessing model accuracy poses challenges due to the complexity of geology and groundwater systems. This research demonstrates a workflow to visualize and analyze raw 3D unstructured groundwater model data using an immersive Cave Automated Virtual Environment (CAVE). To visualize the unstructured groundwater model data, the raw dataset is converted into interactive CAVE-compatible formats utilizing a set of tools: ParaView, Blender, and Unity. This enables researchers to immerse themselves in the data, identifying influential patterns and relationships. e resulting insights can inform the development of sophisticated machine-learning models for groundwater level prediction. The CAVE’s immersive capabilities allow intuitive exploration from various perspectives, providing a more holistic understanding of the factors affecting groundwater levels. These insights are crucial to improve predictive models. The CAVE results also facilitate collaborative analysis and have potential applications in training and education. is research demonstrates the value of immersive VR tools such as the CAVE for unraveling intricacies within high-dimensional scientific data to drive real-world forecasting and modeling applications.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

Maximizing efficiency of dataset compression for machine learning potentials with information theory

Machine learning interatomic potentials (MLIPs) balance high accuracy and lower costs compared to density functional theory calculations, but their performance often depends on the size and diversity of training datasets. Large datasets improve model accuracy and generalization but are computationally expensive to produce and train on, while smaller datasets risk discarding rare but important atomic environments and compromising MLIP accuracy/reliability. Here, we develop an information-theoretical framework to quantify the efficiency of dataset compression methods and propose an algorithm that maximizes this efficiency. By framing atomistic dataset compression as an instance of the minimum set cover (MSC) problem over atom-centered environments, our method identifies the smallest subset of structures that contains as much information as possible from the original dataset while pruning redundant information. The approach is extensively demonstrated on the GAP-20 and TM23 datasets and validated on 64 varied datasets from the ColabFit repository. Across all cases, MSC consistently retains outliers, preserves dataset diversity, and reproduces the long-tail distributions of forces even at high compression rates, outperforming other subsampling methods. Furthermore, MLIPs trained on MSC-compressed datasets exhibit reduced error for out-of-distribution data even in low-data regimes. We explain these results using an outlier analysis and show that such quantitative conclusions could not be achieved with conventional dimensionality reduction methods. The algorithm is implemented in the open-source QUESTS package and can be used for several tasks in atomistic modeling, from data subsampling, outlier detection, and training improved MLIPs at a lower cost.

36 MATERIALS SCIENCE↗
NASA NTRS1984

The computation of mesh configurations for three-dimensional flow analysis

A geometry modeling method was developed to define three-dimensional mesh configurations, which were expressed by the set of surface intersections with a coordinate mesh. These configurations define bodies for transonic potential-flow computation in simple physical coordinates. Various configurations were prepared for 3-D potential flow analysis, including many bare inlet models in cylindrical coordinates. Trimmed surface models were used to prepare nacelle installation configurations. A variety of ducts and mixers were represented. Analytically defined mesh/surface intersections were compared with similar data obtained from the corresponding surface model. Parameters for an analytic surface definition from mesh-surface intersections obtained from a model of the surface were produced. In both studies the modeling accuracy was shown to be compatible with the flow analysis requirements. This technique fulfills the requirements of the associated three-dimensional potential-flow analysis. It preserves the flow analysis method's superior flexibility for adapting to unusual geometries. The geometry modeling technique is supported by a sufficient set of tools for effective use by general users, and sufficient accuracy was demonstrated.

Gibson, S. G.↗
DOE OSTI2024

Efficacy of using a dynamic length representation vs. a fixed-length for neuroarchitecture search

Deep learning neuroarchitecture and hyperparameter search are important in finding the best configuration that maximizes learned model accuracy. However, the number of types of layers, their associated hyperparameters, and the myriad of ways to connect layers poses a significant computational challenge in discovering ideal model configurations. Here, we assess two different approaches for neuroarchitecture search for a LeNet style neural network, one that uses a fixed-length approach where there is a preset number of possible layers that can be toggled on or off via mutation, and a variable-length approach where layers can be freely added or removed via special mutation operators. We found that the variable-length implementation trained better models while discovering unusual layer configurations worth further exploration.

Coletti, Mark↗
DOE OSTI2024

Analysis on Evaluations of Monterey Bay Aquarium Research Institute’s Wave Energy Converter’s Field Data Using WEC-Sim and Gazebo: A Simulation Tool Comparison

Although many studies have validated wave energy converter (WEC) numerical models against scaled prototype experimental data, there remains a notable lack of validation using data from full-scale deployed WECs. This paper compares two numerical models of Monterey Bay Aquarium Research Institute’s Wave Energy Converter (MBARI-WEC), a two-body point absorber with an electro-hydraulic power take-off system (PTO). The models are implemented in WEC-Sim/Simscape and Gazebo Simulator. A statistical analysis of the models was performed, and field results were obtained to compare the models’ accuracy in predicting the RMS piston velocity, RMS motor speed, and mean electric power compared to field data for 56 observations across varying sea states. The Gazebo model demonstrated a closer agreement across all three parameters for a majority of the observations. When compared to the field data, the Gazebo and WEC-Sim models exhibited average mean electric power overestimations of 13% and 22%, respectively.

16 TIDAL AND WAVE POWER↗
NASA NTRS1995

Comparison of simulated cloud cover with satellite obsrvations over the Western United States

Satellite imagery datasets and regional climate model results are intercompared for evaluation of model accuracy in the simulation of cloud cover. Both monthly average individual simulation times are analyzed. To provide a consistent comparison, satellite data are first mapped into the model's geographic projection, grid domain, and resolution. It is found that September 1988 monthly average cloud fraction results from the modeled simulations correspond to observations, in both spatial pattern and magnitude, with bias less than +/- 20% cloud fraction over the entire inland West. Agreement in the pattern of cloud fraction also is evident for monthly average cloud fraction in July, but there is no negative bias of 10%-30% cloud fraction in the model diagnosis of cloud cover. Correlations between the spatial distributions of model-derived and observed cloud fractions are found to exceed 0.80 for certain geographic regions of the West, and these correlations are largest over mountainous areas during summer. Case studies of a series of daily cloud cover demonstrate the ability of the model to simulate the effects of frontal passage on cloud distribution. The ability of the RegCM1 to simulate daily cloud fraction and diurnal cloud evolution is somewhat weak for the summer convective season. It is anticipated that a more recent version of the regional climate model may improve the simulation of summer season cloud cover, through changes in cloud parameterization and improvements in model resolution.

Wetzel, Melanie A.↗
NASA NTRSDate not supplied

A Knowledge Graph Framework for Organizing Heterogeneous Datasets for Utilization in Classical and Quantum Computing: Current Challenges and Future Directions

"The escalating impact of climate change induced extreme weather events in urban, suburban, and rural environments demands a rethink of how we have been using the single event-based or use-case-based knowledge graph models. The lack of representation in interaction within environmental variables found in literature led to the development of a novel framework that reflects the true nature of the interconnectedness in our environment. We propose an Environmental Interaction Knowledge Graph (EIKG) framework. This general EIKG framework works as the basis for interconnected environmental events by knitting interrelated events such as hurricanes leading to storm surges, which lead to flood events that could cause mudslides, landslides, etc., The cascading nature of one event leading to another related event in the environment requires an adequate understanding of each event using contextual information before conducting any data-driven analytics. This vision paper showcases how the EIKG:floods, EIKG:wildfire EIKG:landslides, etc, can be derived from a base case framework of EIKG as those individual events are interconnected with some common denominator variables. As an example, the precipitation variable is used in the flood case study as well as in the wildfire case study, as excessive precipitation levels lead to floods, and lack of precipitation leads to droughts and wildfires. We identify the precipitation variable as a “common-denominator-variable” in extreme weather events that play a key role in modeling the environment leading to different extreme weather events based on the variability of that variable (varying values where low precipitation leads to drought, and high values lead to floods). We use the insights gained from EIKG to conduct classical and Quantum Machine Learning (QML) based data analysis on the research questions developed. Our preliminary study shows how the Variational Quantum Classifier (VQC) and Quantum Support Vector Classifier (QSVC) are used along with the classical machine learning models to compare the model accuracies. Our study elaborates on how a quantitative analysis uses state-of-the-art machine learning techniques that include implementing both classical and quantum machine learning models and developing the knowledge graph. The EIKG is used to organize heterogeneous datasets and integrate the relations to case-specific extreme weather events such as floods. The study uses datasets such as county-to-country residential mobility data, socioeconomic datasets from the US Census Bureau, climate and weather-related Earth Observational data from NASA, and critical infrastructure data from the Homeland Infrastructure datasets."

Knowledge Graphs, Quantum Computing, Heterogenous ↗
DOE OSTI2024

Prediction of O and OH Adsorption on Transition Metal Oxide Surfaces from Bulk Descriptors

In the search for stable and active catalysts, density functional theory and machine learning (ML) based models can accelerate the screening of materials. While stability is conveniently addressed on the bulk level of computation, the modelling of catalytic activity requires expensive surface simulations. Here, in this work, we develop models for the surface adsorption energy of O and OH intermediates across a consistent and extensive dataset of pure transition metal oxide surfaces. We show that adsorption energies across metal oxidation states of +2 to +6 are well captured from the metal-oxygen bond strength extracted from the bulk level calculation. Specifically, we calculate the integrated crystal orbital Hamiltonian population (ICOHP) of the metal-oxygen bond in the bulk oxide and employ a simple normalization scheme to obtain a strong correlation with adsorption energetics. By combining our ICOHP descriptor with non DFT features in a Gaussian Process regression (GPR) model, we achieve high model accuracy with mean absolute errors of 0.166 and 0.219 eV for OH and O adsorption, respectively. By targeting the O-OH adsorption energy difference with our GPR model, we predict the the oxygen evolution reaction (OER) activity from bulk descriptors only. Furthermore, we utilize the strong correlation between the COHP and metal oxygen bond lengths to rapidly predict adsorption energetics and catalytic activity from the optimized bulk geometry. Our approach can enable an efficient search for active catalysts by eliminating the need for surface calculations in the initial screening phase.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

A Machine Learning–Based Tire Life Prediction Framework for Increasing Life of Commercial Vehicle Tires

In the commercial freight industry, tire retreading decisions are often conservative due to limited knowledge of a tire’s remaining service life. This practice leads to increased costs and material waste. This paper proposes a machine learning–based approach for estimating tire casing life and retreadability, focusing on usage data rather than wear information. This approach could extend the tire’s lifespan and reduce landfill waste. Data integration from diverse tire casing measurement sources presents challenges, including imbalanced removal data. Our methodology addresses these challenges by using historical inspection, telematics, and finite element modeling (FEM) datasets. We introduce “Tire Casing Energy” as a comprehensive usage input and apply a Variance-Reduction Synthetic Minority Oversampling Technique (VR-SMOTE) for data imbalance rectification. A random forest model is used to estimate the state of the tire casing and the casing removal probability, with Bayesian optimization applied for hyperparameter tuning, enhancing model accuracy. Here, the proposed prediction framework is able to differentiate different truck fleets and tire locations based on their usage parameters. With the aid of this machine learning model, the importance and sensitivity of different tire usage parameters can be obtained, which is beneficial to maximize tire life.

Data balancing↗
NASA NTRSDate not supplied

Convective Transport and Evolution of Clouds and aerosols in the Asian Summer Monsoon Region

The existence of a persistent layer in the lowermost stratosphere in the Asian Monsoon region is well-known and has been observed by satellites and also in situ by balloon-borne sensors. This aerosol layer has been observed to persist every year by both SAGE sensors and by CALIOP, between the tropopause and the lower boundary of the Junge stratospheric sulfate layer. But how does this layer form and why? Apparently, aerosols are lofted by convection form the Indian and Asian continents, into the upper troposphere/lower stratosphere (UT/LS) area in the middle of a persistent anticyclone associate with the Asian summer monsoon. But some mysteries remain. The top of this aerosol layer is well above the altitude of maximum convective outflow, so why is the top of the aerosol layer so high? Are the aerosols coming from China or from India? And finally, is there an observable impact of these aerosol on thin cirrus distributions in the UT/LS? We explore the interesting difference in altitude between the ATAL layer and the convective cloud top height, using observations from CALIOP and from SAGE. In the process of doing this we examine the accuracy of both CALIOP and SAGE cloud/aerosol discrimination, and the impact of various averaging lengths. We compare the apparent "observational tropopause" with observations from COSMIC, CALIOP (clouds), and with modeled interpolation from MERRA-2. We also compare CALIOP and CloudSat daytime cloud top heights for convective clouds with the vertical aerosol distribution, and evaluate convection in this region as represented by MERRA-2. Finally, and maybe most importantly we compare convective cloud top heights and temperatures with diurnal variability during the most recent years by using observations from the geostationary Himawari satellite. How representative are the twice-daily A-Train observations, when compared to the natural diurnal variability of convection? The goal is to establish the origins of these UT/LS aerosols, whether these aerosol distributions can be completely explained by convective transport, and to evaluate convective lofting of aerosol by models. Ultimately, the convective lofting of aerosols as modeled is needed to explain the Asian Monsoon aerosol distributions. The observations contribute much-needed information to enhance the model accuracy.

clouds↗
NASA NTRS1989

Sufficiency and necessity in reliability modeling

Limitations of current analytic techniques in estimating the reliability of life-critical electronics systems are discussed. A new framework for specification of recovery and fault-handling submodels is suggested, and is shown through several examples to provide substantially improved modeling accuracy and flexibility. Implementation of the new technique in an X-windows based system, XHARP, is also described. The implementation allows for an automated behavioral decomposition of full system models, heretofore unavailable in such tools.

Geist, Robert↗