Search NASA⌕ Search

SEARCH · Search NASA

Results for “evaluation datasets”

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 325 records · Page 18

Building fault detection and diagnostics: Achieved savings, and methods to evaluate algorithm performance

Fault detection and diagnosis (FDD) represents one of the most active areas of research and commercial product development in the buildings industry. This paper addresses two questions concerning FDD implementation and advancement 1) What are today's users of FDD saving and spending on the technology? 2) What methods and datasets can be used to evaluate and benchmark FDD algorithm performance? Relevant to the first question, 26 organizations that use FDD across a total 550 buildings and 97 M sf achieved median savings of 8%. Twenty-seven FDD users reported that the median base cost for FDD software, annual recurring software cost, and annual labor cost were $8, $2.7 and $8 per monitoring point, with a median implementation size of approximately 1300 points. To address the second question, this paper describes a systematic methodology for evaluating the performance of FDD algorithms, curates an initial test dataset of air handling unit (AHU) system faults, and completes a trial to demonstrate the evaluation process on three sample FDD algorithms. The work provided a first step toward a standard evaluation of different FDD technologies. Finally, it showed the test methodology is indeed scalable and repeatable, provided an understanding of the types of insights that can be gained from algorithm performance testing, and highlighted the priorities for further expanding the test dataset.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

A Sample of NASA Langley Unsteady Pressure Experiments for Computational Aerodynamics Code Evaluation

As computational fluid dynamics methods mature, code development is rapidly transitioning from prediction of steady flowfields to unsteady flows. This change in emphasis offers a number of new challenges to the research community, not the least of which is obtaining detailed, accurate unsteady experimental data with which to evaluate new methods. Researchers at NASA Langley Research Center (LaRC) have been actively measuring unsteady pressure distributions for nearly 40 years. Over the last 20 years, these measurements have focused on developing high-quality datasets for use in code evaluation. This paper provides a sample of unsteady pressure measurements obtained by LaRC and available for government, university, and industry researchers to evaluate new and existing unsteady aerodynamic analysis methods. A number of cases are highlighted and discussed with attention focused on the unique character of the individual datasets and their perceived usefulness for code evaluation. Ongoing LaRC research in this area is also presented.

Schuster, David M.↗

Digital twins and deep learning segmentation of defects in monolayer MX 2 phases

Developing methods to understand and control defect formation in nanomaterials offers a promising route for materials discovery. Monolayer MX 2 phases represent a particularly compelling case for defect engineering of nanomaterials due to the large variability in their physical properties as different defects are introduced into their structure. However, effective identification and quantification of defects remain a challenge even as high-throughput scanning transmission electron microscopy methods improve. This study highlights the benefits of employing first principles calculations to produce digital twins for training deep learning segmentation models for defect identification in monolayer MX 2 phases. Around 600 defect structures were obtained using density functional theory calculations, with each monolayer MX 2 structure being subjected to multislice simulations for the purpose of generating the digital twins. Several deep learning segmentation architectures were trained on this dataset, and their performances evaluated under a variety of conditions such as recognizing defects in the presence of unidentified impurities, beam damage, grain boundaries, and with reduced image quality from low electron doses. Further, this digital twin approach allows benchmarking different deep learning architectures on a theory dataset, which enables the study of defect classification under a broad array of finely controlled conditions. It thus opens the door to resolving the underpinning physical reasons for model shortcomings and potentially chart paths forward for automated discovery of materials defect phases in experiments.

36 MATERIALS SCIENCE↗

Predicting critical heat flux with uncertainty quantification and domain generalization using conditional variational autoencoders and deep neural networks

Deep generative models (DGMs) can generate synthetic data samples that closely resemble the original dataset, addressing data scarcity. In this work, we developed a conditional variational autoencoder (CVAE) to augment critical heat flux (CHF) data used for the 2006 Groeneveld lookup table. To compare with traditional methods, a fine-tuned deep neural network (DNN) regression model was evaluated on the same dataset. Both models achieved small mean absolute relative errors, with the CVAE showing more favorable results. Uncertainty quantification (UQ) was performed using repeated CVAE sampling and DNN ensembling. The DNN ensemble improved performance over the baseline, while the CVAE maintained consistent results with less variability and higher confidence. Both models achieved small errors inside and outside the training domain, with slightly larger errors outside. Altogether, the CVAE performed better than the DNN in predicting CHF and exhibited better uncertainty behavior.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Evaluation of adjoint-based observation impacts as a function of forecast length using an Observing System Simulation Experiment

Adjoints of numerical weather prediction models may be employed for Forecast Sensitivity to Observation (FSO) in order to monitor the contribution of ingested observation data on short-term forecast skill. However, the calculation of short-term forecast error is difficult due to the lack of a truly independent dataset for verification. In an Observing System Simulation Experiment framework, the Nature Run is able to provide a true and complete verification dataset and allows accurate evaluation of short term forecast errors. In this work, an OSSE developed at the National Aeronautics and Space Administration Global Modeling and Assimilation Office is used to explore the impact of observational data on forecasts in the 6 to 48 hour range. An adjoint of the Global Earth Observing System model is employed to compare the observation impacts estimated using both self-analysis verification and the true Nature Run verification. Self-analysis verification is found to inflate the estimated forecast error growth during the early forecast period, resulting in overestimations of observation impacts, particularly in the 6-12 hour forecast range. By 48 hours, the self-analysis verification estimates of forecast error and observation impacts more closely match the true values. The fraction of beneficial observations is also overinflated at short forecast times when self-analysis verification is used. The progression of impacts of an individual observation or data type depends on the character of the growth of the initial condition error that each observation affects.

numerical weather prediction↗

X-ray computed tomography using curvelet sparse regularization

Purpose: Reconstruction of x-ray computed tomography (CT) data remains a mathematically challenging problem in medical imaging. Complementing the standard analytical reconstruction methods, sparse regularization is growing in importance, as it allows inclusion of prior knowledge. The paper presents a method for sparse regularization based on the curvelet frame for the application to iterative reconstruction in x-ray computed tomography. Methods: In this work, the authors present an iterative reconstruction approach based on the alternating direction method of multipliers using curvelet sparse regularization. Results: Evaluation of the method is performed on a specifically crafted numerical phantom dataset to highlight the method’s strengths. Additional evaluation is performed on two real datasets from commercial scanners with different noise characteristics, a clinical bone sample acquired in a micro-CT and a human abdomen scanned in a diagnostic CT. The results clearly illustrate that curvelet sparse regularization has characteristic strengths. In particular, it improves the restoration and resolution of highly directional, high contrast features with smooth contrast variations. The authors also compare this approach to the popular technique of total variation and to traditional filtered backprojection. Conclusions: The authors conclude that curvelet sparse regularization is able to improve reconstruction quality by reducing noise while preserving highly directional features.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Multiscale ACI Satellite Database

The SATELLITE_EAGLES_PNNL NetCDF dataset contains a suite of satellite- and reanalysis-derived atmospheric and surface parameters on a regular latitude–longitude grid. The dataset includes core geophysical fields such as land fraction, aerosol optical depth at multiple wavelengths (465, 550, 667, and 865 nm), sea surface temperature, estimated inversion strength, and various thermodynamic and dynamic quantities (e.g., relative humidity, vertical velocity, boundary-layer height, and surface fluxes) from both MERRA and ERA reanalysis products, provided as daily-mean and instantaneous values. A major component of the dataset consists of MODIS-retrieved cloud microphysical properties, including cloud droplet number concentration, cloud effective radius, optical thickness, and liquid water path, provided for three compositing regimes (“All,” “Q06,” and “G18”). Corresponding cloud-top parameters—temperature, height, and pressure—along with total and domain-mean cloud fraction fields are also included. The file further integrates additional satellite data from AMSR-E (for cloud water, rain water, and surface precipitation retrievals) and CERES (for top-of-atmosphere radiative fluxes, cloud fractions, and albedo). This dataset is designed to evaluate aerosol–cloud interactions in warm clouds, emphasizing the use of MODIS for deriving cloud droplet number concentration and liquid water path statistics. The complementary satellite and reanalysis fields are co-located and time-matched to the same instantaneous MODIS observations, enabling consistent comparisons between cloud properties, aerosol loading, and large-scale meteorological conditions. The dataset is recently featured in Christensen et al. (2025), Machine Learning Reveals Strong Grid-Scale Dependence in the Satellite Nd–LWP Relationship, EGUsphere [preprint], https://doi.org/10.5194/egusphere-2025-3850, 2025.

Christensen, Matthew [Pacific Northwest National L↗

Multiscale ACI Satellite Database

The SATELLITE_EAGLES_PNNL NetCDF dataset contains a suite of satellite- and reanalysis-derived atmospheric and surface parameters on a regular latitude–longitude grid. The dataset includes core geophysical fields such as land fraction, aerosol optical depth at multiple wavelengths (465, 550, 667, and 865 nm), sea surface temperature, estimated inversion strength, and various thermodynamic and dynamic quantities (e.g., relative humidity, vertical velocity, boundary-layer height, and surface fluxes) from both MERRA and ERA reanalysis products, provided as daily-mean and instantaneous values. A major component of the dataset consists of MODIS-retrieved cloud microphysical properties, including cloud droplet number concentration, cloud effective radius, optical thickness, and liquid water path, provided for three compositing regimes (“All,” “Q06,” and “G18”). Corresponding cloud-top parameters—temperature, height, and pressure—along with total and domain-mean cloud fraction fields are also included. The file further integrates additional satellite data from AMSR-E (for cloud water, rain water, and surface precipitation retrievals) and CERES (for top-of-atmosphere radiative fluxes, cloud fractions, and albedo). This dataset is designed to evaluate aerosol–cloud interactions in warm clouds, emphasizing the use of MODIS for deriving cloud droplet number concentration and liquid water path statistics. The complementary satellite and reanalysis fields are co-located and time-matched to the same instantaneous MODIS observations, enabling consistent comparisons between cloud properties, aerosol loading, and large-scale meteorological conditions. The dataset is recently featured in Christensen et al. (2025), Machine Learning Reveals Strong Grid-Scale Dependence in the Satellite Nd–LWP Relationship, EGUsphere [preprint], https://doi.org/10.5194/egusphere-2025-3850, 2025.

54 ENVIRONMENTAL SCIENCES↗

Improving Progressive Retrieval for HPC Scientific Data using Deep Neural Network

As the disparity between compute and I/O on high-performance computing systems has continued to widen, it has become increasingly difficult to perform post-hoc data analytics on full-resolution scientific simulation data due to the high I/O cost. Error-bounded data decomposition and progressive data retrieval framework has recently been developed to address such a challenge by performing data decomposition before storage and reading only part of the decomposed data when necessary. However, the performance of the progressive retrieval framework has been suffering from the over-pessimistic error control theory, such that the achieved maximum error of recomposed data is significantly lower than the required error. Therefore, more data than required is fetched for recomposition, incurring additional I/O overhead. In order to tackle this issue, we propose a DNN-based progressive retrieval framework that can better identify the minimum amount of data to be retrieved. Our contributions are as follows: 1) We provide an in-depth investigation of the recently developed progressive retrieval framework; 2) We propose two designs of prediction models (named D-MGARD and E-MGARD) to estimate the amount of retrieved data size based on error bounds. 3) We evaluate our proposed solutions using scientific datasets generated by real-world simulations from two domains. Evaluation results demonstrate the effectiveness of our solution in accurately predicting the amount of retrieval data size, as well as the advantages of our solution over the traditional approach to reducing the I/O overhead. Based on our evaluation, our solution is shown to read significantly less data (5% - 40% with D-MGARD, 20% - 80% with E-MGARD).

Wang, Jinzhen↗

Phasor-Measurement-Unit-Based Data Analytics Using Digital Twin and PhasorAnalytics Software

A major objective of this project was to apply GE’s commercial machine learning and data analytics toolsets to large-scale, real-world, anonymized Phasor Measurement Unit (PMU) datasets in order to extract signatures, correlated and/or causal factors, and precursor patterns associated with significant power system phenomena. The project had a particular emphasis on extraction of insights relevant to asset health monitoring, real-time load modeling and cybersecurity monitoring. Additionally, the team was directed to undertake a comprehensive data quality analysis for the provided datasets and encouraged to estimate the ‘machine-learning readiness’ of the datasets by documenting any major obstacles to the application of commercial machine learning algorithms. To accomplish the aforementioned objectives, the project team’s work centered around the identification of key event signatures and application of the identified event signatures for event detection and event classification. The industry-validated, semi-supervised machine learning strategy employed for event signature identification involved several major tasks, including data-preprocessing, generation of an overabundance of features, normal data identification, normality modeling, and event signature identification through a methodical, quantitative ranking of features in order of relevance to each studied event type. Throughout the project, data quality issues and mitigation techniques were investigated. In this report, insights are provided regarding the readiness of the provided synchrophasor datasets for application of machine learning and data analytics. The methodologies employed for this technical strategy are summarized in this report. With regards to data preprocessing and feature generation, the provided Training and Test Datasets were ingested into GE’s big data environment. Subsequently, the team applied bad data cleansing and data imputation scripts, event detection scripts, and application programming interfaces (APIs) to the datasets for convenient data access. The project team completed development and validation of dozens of physics-based, statistics-based and transformation-based feature functions used for the extraction of over 60 synchrophasor features. Using a new parallel feature generation technology developed on this project, over 60 features have been rapidly generated for the full two years’ worth of Training and Test Dataset data associated with both the Eastern and Western interconnects. Even accommodating for temporal down-sampling inherent to the feature extraction procedure, this parallel feature generation activity resulted in a massive feature set with a storage requirement approximately equal to that of the raw training dataset itself. With regards to normal data identification and normality modeling, a normality model was built using the feature data extracted from the Training Dataset and iteratively refined subsequent to incremental adjustments and expansions of the Training Dataset feature data. With respect to event characterization and signature identification, an event signature identification pipeline was developed and used in conjunction with the normality model to identify over 15 event signatures for key event categories within the Training Dataset. The identified event signatures were used to characterize hundreds of key events in terms of relative severity, duration, and location of the event. An investigation was undertaken to identify correlated and causal factors involved in transformer events. A separate investigation into temporal trends in ring-down analysis results was undertaken to determine possible associations between system dynamics and various other factors such as loading, season or year. To validate the identified event signatures, additional work was undertaken to develop signature-based anomaly detection and classification tools suitable for convenient application to the synchrophasor datasets. The anomaly detection and classification tools, suitable for online application, were then applied to the entirety of the Eastern Interconnect Training and Test Datasets. Performance of the event detection and classification tools was evaluated upon receipt of the Test Dataset event logs (i.e., the labels for events contained in the Test Dataset), and promising results were obtained despite several challenges (documented herein) associated with application of supervised or semi-supervised machine learning methods to large-scale, anonymized datasets. Finally, the detection and classification tools were used to detect, classify, and characterize thousands of new events not included in the original event logs provided by the DOE within both the Training and Test Datasets.

24 POWER TRANSMISSION AND DISTRIBUTION↗

A Semantic Relatedness Approach for Traceability Link Recovery

Human analysts working with automated tracing tools need to directly vet candidate traceability links in order to determine the true traceability information. Currently, human intervention happens at the end of the traceability process, after candidate traceability links have already been generated. This often leads to a decline in the results accuracy. In this paper, we propose an approach, based on semantic relatedness (SR), which brings human judgment to an earlier stage of the tracing process by integrating it into the underlying retrieval mechanism. SR tries to mimic human mental model of relevance by considering a broad range of semantic relations, hence producing more semantically meaningful results. We evaluated our approach using three datasets from different application domains, and assessed the tracing results via six different performance measures concerning both result quality and browsability. The empirical evaluation results show that our SR approach achieves a significantly better performance in recovering true links than a standard Vector Space Model (VSM) in all datasets. Our approach also achieves a significantly better precision than Latent Semantic Indexing (LSI) in two of our datasets.

99 GENERAL AND MISCELLANEOUS↗

Evaluating China's fossil-fuel CO2 emissions from a comprehensive dataset of nine inventories

China's fossil-fuel CO2 (FFCO2) emissions accounted for approximately 28 % of the global total FFCO2 in 2016. An accurate estimate of China's FFCO2 emissions is a prerequisite for global and regional carbon budget analyses and the monitoring of carbon emission reduction efforts. However, significant uncertainties and discrepancies exist in estimations of China's FFCO2 emissions due to a lack of detailed traceable emission factors (EFs) and multiple statistical data sources. Here, we evaluated China's FFCO2 emissions from nine published global and regional emission datasets. These datasets show that the total emissions increased from 3.4 (3.0–3.7) in 2000 to 9.8 (9.2–10.4) Gt CO2 per yr in 2016. The variations in these estimates were largely due to the different EF (0.491–0.746 t C per t of coal) and activity data. The large-scale patterns of gridded emissions showed a reasonable agreement, with high emissions being concentrated in major city clusters, and the standard deviation mostly ranged from 10 % to 40 % at the provincial level. However, patterns beyond the provincial scale varied significantly, with the top 5 % of the grid level accounting for 50 %–90 % of total emissions in these datasets. Our findings highlight the significance of using locally measured EF for Chinese coal. To reduce uncertainty, we recommend using physical CO2 measurements and use these values for dataset validation, key input data sharing (e.g., point sources), and finer-resolution validations at various levels.

Pengfei Han↗

Comparisons of Impedance Prediction Models for Perforate-over-Honeycomb Liners

A large dataset is used to evaluate the efficacy of multiple impedance prediction models for perforate-over-honeycomb liners. Two-factorial analysis is used to explore the relative importance of the key parameters used in these models. Tests are conducted in the NASALangley Normal Incidence Tube and Grazing Flow Impedance Tube with over eighty perforate facesheets at multiple source sound pressure levels, Mach numbers and frequencies. Each prediction model is then compared with this dataset to determine how well each method predicts the measured data. Finally, an optimizer is used to further improve the ability of one of these models to reproduce the measured results.

acoustic↗

Comparisons of Impedance Prediction Models for Perforate-over-Honeycomb Liners

A large dataset is used to evaluate the efficacy of multiple impedance prediction models for perforate-over-honeycomb liners. Two-factorial analysis is used to explore the relative importance of the key parameters used in these models. Tests are conducted in the NASALangley Normal Incidence Tube and Grazing Flow Impedance Tube with over eighty perforate facesheets at multiple source sound pressure levels, Mach numbers and frequencies. Each prediction model is then compared with this dataset to determine how well each method predicts the measured data. Finally, an optimizer is used to further improve the ability of one of these models to reproduce the measured results.

acoustic↗

Enhancing segmentation fairness through curriculum learning and progressive loss: a centralized and federated perspective on radiograph analysis

Bias in medical image segmentation can lead to unequal performance across demographic subgroups, raising concerns about fairness and reliability in clinical AI systems. While deep learning models have achieved high segmentation accuracy, ensuring equitable performance across race and gender remains a significant challenge, particularly in privacy-sensitive healthcare environments. This study investigates fairness-aware medical image segmentation for hip and knee radiographs using deep learning models evaluated in both centralized and Federated Learning (FL) settings. We introduce Curriculum Learning (CL) strategies and Progressive Loss (PL) functions to regulate sample difficulty during training. In addition, we propose two novel fairness-oriented federated learning algorithms, Federated Intersection over Union (FedIoU) and Federated Intersection over Union with Outlier Analysis (FedIoUoutlier). Experiments are conducted using multiple segmentation backbones and simulated multi-site data partitions derived from the Osteoarthritis Initiative dataset. Model performance is evaluated using Intersection over Union (IoU), IoU standard deviation, Skewed Error Ratio (SER), and Min-Max Disparity across race and gender subgroups. Statistical significance was verified using paired t-tests to compare per-sample IoU performance against baseline configurations. Across both hip and knee segmentation tasks, curriculum learning and progressive loss strategies consistently improved segmentation accuracy and reduced demographic performance disparities in centralized training. In federated settings, fairness-aware aggregation further enhanced performance. Notably, FedIoUoutlier combined with balanced curriculum learning and tiered progressive loss achieved the highest mean IoU while yielding the lowest SER and Min-Max Disparity, indicating improved fairness without sacrificing accuracy. In several configurations, federated models matched or exceeded the performance of optimized centralized models, with statistically significant improvements in per-sample IoU over baseline configurations. The results demonstrate that structured training strategies and fairness-aware federated aggregation can jointly improve accuracy, stability, and demographic fairness in medical image segmentation. By integrating curriculum learning, progressive loss, and novel FL algorithms, this work provides a practical pathway toward equitable and privacy-preserving AI systems for medical imaging.

97 MATHEMATICS AND COMPUTING↗

MIC-DP: A Scalable Correlation-Aware Differential Privacy Framework for High-Dimensional Data

Conventional differential privacy (DP) assumes record independence, limiting effectiveness on real-world datasets with temporal, spatial, or structural correlations. These dependencies undermine privacy guarantees and degrade utility in domains like healthcare, IoT, and smart city analytics. We propose Maximum Information Correlated Differential Privacy (MIC-DP), a novel framework that dynamically calibrates noise based on statistical dependencies. MIC-DP uses the Maximum Information Coefficient (MIC) to capture both linear and nonlinear correlations without explicit modeling, enabling adaptive sensitivity adjustment and improved privacy–utility trade-offs. Evaluations on healthcare (MIMIC), demographic (ACI), and synthetic datasets show that MIC-DP reduces mean absolute error (MAE) by up to 5.2% under strict privacy budgets (ϵ≤1), with aggregate utility improvements reaching 18% across datasets and evaluation metrics. MIC-DP provides formal (ϵ,δ)-privacy guarantees, scales efficiently with feature count, and supports deployment in moderate-scale, privacy-sensitive applications. Its tunable performance and runtime efficiency make MIC-DP suitable for privacy-sensitive applications where low-latency analytics and strong privacy guarantees must coexist. These results demonstrate MIC-DP’s effectiveness as a correlation-aware solution for practical DP.

Yang, Wenjun [Univ. of Washington, Tacoma, WA (Uni↗

Autotuning PolyBench benchmarks with LLVM Clang/Polly loop optimization pragmas using Bayesian optimization

Here, we develop a ytopt autotuning framework that leverages Bayesian optimization to explore the parameter space search and compare four different supervised learning methods within Bayesian optimization and evaluate their effectiveness. We select six of the most complex PolyBench benchmarks and apply the newly developed LLVM Clang/Polly loop optimization pragmas to the benchmarks to optimize them. We then use the autotuning framework to optimize the pragma parameters to improve their performance. The experimental results show that our autotuning approach outperforms the other compiling methods to provide the smallest execution time for the benchmarks syr2k, 3mm, heat-3d, lu, and covariance with two large datasets in 200 code evaluations for effectively searching the parameter spaces with up to 170,368 different configurations. We find that the Floyd-Warshall benchmark did not benefit from autotuning. To cope with this issue, we provide some compiler option solutions to improve the performance. Then we present loop autotuning without a user's knowledge using a simple mctree autotuning framework to further improve the performance of the Floyd-Warshall benchmark. We also extend the ytopt autotuning framework to tune a deep learning application.

79 ASTRONOMY AND ASTROPHYSICS↗