Search NASA⌕ Search

SEARCH · Search NASA

Results for “data imputation”

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 19 records
All sourcesNASA NTRSDOE OSTI
NASA NTRS2021

Salvaging Data Records with Missing Data: Data Imputation using the Multivariate t Distribution

When doing multivariate data analysis, one commonobstacle is the presence of incomplete observations, i.e., observationsfor which one or more key fields are blank. Missing datais often countered by deleting entire observations that containmissing data. The negative effects of deleting entire observationsare multiple: deleting observations reduces sample size andcan also result in biased inferences even if data is missing atrandom. In addition, knowledge contained within incompleteobservations is knowledge lost when they are deleted– and theeffort spent collecting that knowledge is effort wasted. Data imputationmethods, or methods of statistically “filling-in” missingdata, can help combat small sample sizes by using the existinginformation in partially complete observations with the end goalof producing less biased and higher confidence inferences. Whena sample from a multivariate normal population is only partiallycomplete, and the missing data meets appropriate assumptions(missing at random), robust data imputation of the missing datacan be implemented with monotone data augmentation (MDA)using the multivariate t distribution.Missing data imputation is applied to data from the NASA InstrumentCost Model (NICM) using the MDA algorithm underthe assumption of having a multivariate t distribution with fixeddegrees of freedom. A sensitivity analysis to the degrees offreedom parameter is presented to demonstrate robustness ofthe multivariate t distribution when dealing with small samplesas compared to the multivariate normal distribution.

DiNicola, Michael↗
DOE OSTI2021

A Short-Term Solar Forecasting Platform Using a Physics-Based Smart Persistence Model and Data Imputation Method

Electrical energy plays vital role in our socio-economic activity and therefore ensuring the reliability of the electric grid, from the generation, transmission and distribution level is critical. In order to maintain the power system parameter viz., frequency, voltage, etc., optimally, balancing of generation and consumption is very much essential. However, solar energy is infirm power by nature this is due to cloud cover / other local phenomena. Hence, Photovoltaic (PV) power generation brings a significant challenge to the grid operator due to the variability of the solar energy. The complexity of this challenge in terms of planning and dispatch ability of PV resources, aggravates with the high penetration of solar energy into the electric grid. In this setting, reliable solar radiation forecasting models based on accurate and quality input data become essential. In order to develop a suitable model for predicting solar radiation, quality historical / real time measurement is also needed. Under this study NIWE and NREL jointly developed / tested short-term solar forecasting frameworks using a smart persistence and physics-based smart persistence models for intra-hour forecasting of solar radiation (PSPI) and benchmarked 9 different data imputation techniques in 15 Solar Radiation Resource Assessment (SRRA) stations, located at different parts of India. During any measurement campaign, due to various technical reasons, we may miss few observations. However, the missing observation often reduce the performance of any forecasting model. Therefore, suitable data imputation method would assist us to obtain continuous observation of solar radiation. A station-by-station and method-by-method analysis was carried out to understand the performance of each model. Based on our analysis, among all the data imputation methods, the Kalman data imputation method is better for Indian Weather condition. In addition, Kalman StructTS, Linear, Stine and Arima methods yield slightly inferior accuracy compared to Kalman, but outperform the other methods. The extended solar radiation data are used by solar forecasting models to provide the prediction of solar radiation at 15 SRRA stations. As far as short term forecasting model is concerned, the PSPI model outperforms the Smart Persistence model. However, the forecast error is increases with the forecasting horizon.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2023

Spatio-Temporal Denoising Graph Autoencoders with Data Augmentation for Missing Photovoltaic Data Imputation

The integration of the global Photovoltaic (PV) market with real time data-loggers has enabled large scale PV data analytical pipelines for power forecasting and long-term reliability assessment of PV fleets. Nevertheless, the performance of PV data analysis heavily depends on the quality of PV timeseries data. This paper proposes a novel Spatio-Temporal Denoising Graph Autoencoder (STD-GAE) framework to impute missing PV Power Data. STDGAE exploits temporal correlation, spatial coherence, and value dependencies from domain knowledge to recover missing data. It is empowered by two modules. (1) To cope with sparse yet various scenarios of missing data, STD-GAE incorporates a domain-knowledge aware data augmentation module that creates plausible variations of missing data patterns. This generalizes STD-GAE to robust imputation over different seasons and environment. (2) STD-GAE nontrivially integrates spatiotemporal graph convolution layers (to recover local missing data by observed “neighboring” PV plants) and denoising autoencoder (to recover corrupted data from augmented counterpart) to improve the accuracy of imputation accuracy at PV fleet level. We have evaluated our proposed model on two realworld PV datasets. Experimental results show that STD-GAE can achieve a gain of 43.14% in imputation accuracy and remains less sensitive to missing rate, different seasons, and missing scenarios, compared with state-of-the-art data imputation methods such as MIDA and LRTC-TNN.

Fan, Yangxin↗
DOE OSTI2026

Bayesian Physics Informed Spatio-Temporal Network for Streamflow Data Imputation

Reliable reconstruction of incomplete streamflow records is critical for improving hydrological forecasting, flood preparedness, and water resource management. However, large observational gaps and uncertainties in governing physical parameters limit the accuracy of traditional statistical and machinelearning imputation frameworks. To address these challenges, we develop a Bayesian Physics-Informed Spatio-Temporal Network (BPI-STNet) that jointly captures spatial and temporal dependencies while enforcing hydrologic consistency through embedded physical constraints. The framework integrates a GraphSAGE-LSTM architecture to model spatial connectivity across gauges and temporal flow dynamics, coupled with a Bayesian update mechanism to estimate uncertain parameters in a simplified water-balance framework. Unlike conventional physics-informed networks that rely on sampling-based posterior estimation, BPI-STNet derives an analytic solution to the inverse problem, allowing closed-form Bayesian updates of uncertain parameters Λ={α,β,k} using Gaussian priors and likelihoods. Applied to daily observations from the Susquehanna River Basin (1980-2022), BPI-STNet achieves substantial improvements over a purely data-driven RGNN baseline, which reduced RMSE by 23 % and MAE by 9 %, and achieving an average NSE values up to 0.96. The results demonstrate that coupling Bayesian inference with physics-informed learning yields physically consistent, uncertainty-aware reconstructions that preserve the temporal persistence and statistical distribution of observed flows. The proposed framework establishes a generalizable paradigm for data-sparse hydrologic systems where both data fidelity and physical interpretability are essential.

Krishnan Kutty Ambika, Anukesh [ORNL] (ORCID:00000↗
DOE OSTI2021

A Comparison of Time Series Gap-Filling Methods to Impute Solar Radiation Data

Complete solar resource datasets play a critical role at every stage of solar project phases. However, measured or modeled solar resource data come with significant uncertainties and usually suffer from several issues, including but not limited to, data gaps, data quality issue, etc. In order to mitigate these issues an appropriate data imputation method should be implemented to build a complete and reliable temporal (and spatial) database. Being motivated by this, in this study we compare the performances of eight different gap filling methods extensively by creating random and artificial data gaps in (i) hourly irradiance data for one year using a few locations of the National Solar Radiation Database (NSRDB) and (ii) one-minute ground measurement dataset from Surface Radiation Budget Network (SURFRAD) stations.

clearness index↗
DOE OSTI2022

A Comparison of Time-Series Gap-Filling Methods to Impute Solar Radiation Data: Preprint

Complete solar resource data sets play a critical role at every stage of solar energy projects; however, measured or modeled solar resource data come with significant uncertainties and usually suffer from several issues, including, but not limited to, data gaps and data quality issues. To mitigate these issues, an appropriate data imputation method should be implemented to build a complete and reliable temporal (and spatial) database. Motivated by this, in this study, we extensively compare the performance of eight different gap-filling methods by creating random and artificial data gaps in (i) hourly irradiance data for 1 year using a few locations of the National Solar Radiation Database (NSRDB) and (ii) 1-minute ground measurement data sets from the Surface Radiation Budget Network (SURFRAD) and the National Renewable Energy Laboratory (NREL) stations.

clearness index↗
DOE OSTI2023

A General Spatiotemporal Imputation Framework for Missing Sensor Data

Many applications from precision agriculture, environmental monitoring and transportation networks rely on data collected across space and time over a large geographic area. Missing data poses a significant challenge for any data-driven inference and control tasks. Data imputation or the estimation of missing data can help fill these gaps by utilizing inherent spatial relationships and temporal patterns. A variety of spatiotemporal imputation models have been developed to address missing data in spatiotemporal datasets. However, these classical methods rely on the assumption that the underlying data follows a smooth trend and fail to provide accurate estimates when there is a large number of missing points in the data. Even though there are machine learning driven tensor completion approaches such as convolutional neural network based tensor completion (CoSTCo) that capture the non-linear relationships in the dataset, the transductive nature makes the algorithm less scalable. Thus, existing approaches for estimating the missing information do not effectively capture all dimensions of the spatiotemporal data structure, resulting in erroneous predictions and poor performance. The main contributions of this paper are: (1) We propose a novel inductive framework (G-LSTM) for missing data imputation that integrates a graph neural network with LSTMs to effectively capture both spatial and temporal dependencies. (2) Experimental results on a traffic dataset demonstrate that the proposed GNN integrated with an LSTM framework achieves improved imputation and maintains steady performance even when there are extreme missing conditions in comparison with the state-of-the-art imputation framework (i.e, CoSTCo). (3) The simulation results on a traffic network show up to 69% reduction in mean absolute error and 61% reduction in root mean square error when compared to CoSTCo.

Tharzeen, Aabila↗
DOE OSTI2026

Leveraging large language models to address data scarcity in machine learning for graphene synthesis

Machine learning in experimental materials science faces significant challenges due to the scarcity of data, which are costly and time-consuming to generate, particularly when relying on in-house experiments. Literature data mining offers a potential solution but introduces issues like mixed data quality, inconsistent formats, and non-uniform reporting of synthesis parameters, resulting in partially missing and heterogeneous features across the dataset. Here, we propose data imputation and feature engineering methods that employ pre-trained large language models (LLMs) to enhance machine learning performance on scarce, heterogeneous datasets, demonstrated on graphene CVD synthesis data and the ML-HydPARK hydrogen storage dataset. GPT models perform data imputation via tailored prompting and semantic normalization of inconsistently reported features through embeddings, for example, to harmonize the complex nomenclature of CVD substrates. Beyond yielding more diverse and richer feature representations than traditional methods such as K-nearest neighbors (KNN) and Multivariate Imputation by Chained Equations (MICE), LLM-based data imputation is evaluated against dataset characteristics and prompting strategies. We vary the level of autonomy granted to the LLM, from generic prompting that leverages pre-trained knowledge for autonomous data generation to data-informed prompting that constrains outputs using target-specific information, and demonstrate which level of autonomy yields superior imputation performance across datasets and feature types. The proposed data engineering methods markedly improve downstream performance; for example, in graphene layer number classification using a support vector machine (SVM), binary accuracy increases from 39% to 65% and ternary accuracy from 52% to 72%. Fine-tuning experiments on both datasets show that combining our proposed LLM-based data imputation and feature encoding methods with numerical machine learning predictors outperforms standalone fine-tuned LLM predictors in data-scarce settings. The proposed strategies emphasize data enhancement techniques rather than refining learning architectures or regularizing loss functions, offering a broadly applicable framework for improving machine learning performance on scarce, inhomogeneous datasets.

Chemical vapor deposition↗
NASA NTRS2015

Astronaut Preflight Cardiovascular Variables Associated with Vascular Compliance are Highly Correlated with Post-Flight Eye Outcome Measures in the Visual Impairment Intracranial Pressure (VIIP) Syndrome Following Long Duration Spaceflight

The detection of the first VIIP case occurred in 2005, and adequate eye outcome measures were available for 31 (67.4%) of the 46 long duration US crewmembers who had flown on the ISS since its first crewed mission in 2000. Therefore, this analysis is limited to a subgroup (22 males and 9 females). A "cardiovascular profile" for each astronaut was compiled by examining twelve individual parameters; eleven of these were preflight variables: systolic blood pressure, pulse pressure, body mass index, percentage body fat, LDL, HDL, triglycerides, use of anti‐lipid medication, fasting serum glucose, and maximal oxygen uptake in ml/kg. Each of these variables was averaged across three preflight annual physical exams. Astronaut age prior to the long duration mission, and inflight salt intake was also included in the analysis. The group of cardiovascular variables for each crew member was compared with seven VIIP eye outcome variables collected during the immediate post‐flight period: anterior-posterior axial length of the globe measured by ultrasound and optical biometry; optic nerve sheath diameter, optic nerve diameter, and optic nerve to sheath ratio‐ each measured by ultrasound and magnetic resonance imaging (MRI), intraocular pressure (IOP), change in manifest refraction, mean retinal nerve fiber layer (RNFL) on optical coherence tomography (OCT), and RNFL of the inferior and superior retinal quadrants. Since most of the VIIP eye outcome measures were added sequentially beginning in 2005, as knowledge of the syndrome improved, data were unavailable for 22.0% of the outcome measurements. To address the missing data, we employed multivariate multiple imputation techniques with predictive mean matching methods to accumulate 200 separate imputed datasets for analysis. We were able to impute data for the 22.0% of missing VIIP eye outcomes. We then applied Rubin's rules for collapsing the statistical results across our 200 multiply imputed data sets to assess the canonical correlation between the eye outcomes and the twelve astronaut cardiovascular variables available for all 31 subjects. Results: A highly significant canonical correlation was observed among the canonical solutions (p<.00001), with an average best canonical correlation of.97. The results suggest a strong association between astronauts' measures of cardiovascular health and the seven eye outcomes of the VIIP syndrome used in this analysis. Furthermore, the "joint test" revealed a significant difference in cardiovascular profile between male and female astronauts (Prob > F = 0.00001). Overall, female astronauts demonstrated a significantly healthier cardiovascular status. Individually, the female astronauts had significantly healthier profiles on seven of twelve cardiovascular variables than the men (p values ranging from <0.0001 to <0.05). Male astronauts did not demonstrate significantly healthier values on any of the twelve cardiovascular variables measured

Otto, Christian↗
DOE OSTI2021

Evaluation of Time-Series Gap-Filling Methods for Solar Irradiance Applications

A complete solar resource data set is essential for any stage of a solar energy project - from feasibility studies to daily operations. But measured or modeled solar resource data are prone to data gaps and data quality issues. To mitigate these issues, a data imputation process should be implemented to obtain a complete and reliable temporal and spatial data series. This study focused on imputing temporal scales by applying random and artificial data gaps and then implementing eight imputation methods, including the Kalman filtering and smoothing and stine interpolations. These methods were implemented on 1-minute to half hourly irradiance data for 1 year using a few locations from the National Solar Radiation Database (NSRDB) and ground measurement data set. The results demonstrated that some of the simpler methods, such as the stine and linear interpolation methods, were the relatively best models based on the statistical metrics for imputing NSRDB and ground measurement data, respectively.

14 SOLAR ENERGY↗
DOE OSTI2022

Detection of Stealthy False Data Injection Attacks in Unobservable Distribution Networks

In this paper, a composite scheme is proposed for detecting stealthy data manipulation attacks on distribution system which is unobservable with standard least squares based state estimators. This technique has three stages where the process of data imputation, voltage phasor estimation and the bad data detection are carried out in a systematic manner. The proposed approach is then integrated with moving target defense strategies which perturbs the network parameters to reveal stealthy false data injection attacks. The proposed approach is tested is validated on a three-phase, unbalanced 37-node distribution system and its results are presented. It is shown that the proposed approach has the ability to accurately detect the presence of FDI attacks using limited measurements (i.e., the test system is unobservable).

Rajasekaran, James K.↗
DOE OSTI2021

Generating synthetic occupants for use in building performance simulation

Occupant behaviour simulation frameworks can employ synthetic populations to characterize occupancy and behavioural patterns in buildings based on observed demographic data at a certain geographical location. For buildings, very few synthetic occupant populations have been generated. This paper uses a Bayesian Networks (BN) structural learning approach to synthesize populations of occupants in a multi-family housing case study. Two additional cases of office occupants and senior housing residents are considered as a cross-case comparison. Furthermore, we draw upon the extended version of drivers-needs-actions-systems (DNAS) framework to guide the selection of variables and data imputation. Our results show that the BN approach is powerful in learning the structure of data sets. The synthetic data sets successfully match the joint distributions of the underlying combined data sets. Experiments on the multi-family housing particularly show better performance than the office and senior housing cases.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2021

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↗
NASA NTRS2014

Missing Data and Multiple Imputation: An Unbiased Approach

The default method of dealing with missing data in statistical analyses is to only use the complete observations (complete case analysis), which can lead to unexpected bias when data do not meet the assumption of missing completely at random (MCAR). For the assumption of MCAR to be met, missingness cannot be related to either the observed or unobserved variables. A less stringent assumption, missing at random (MAR), requires that missingness not be associated with the value of the missing variable itself, but can be associated with the other observed variables. When data are truly MAR as opposed to MCAR, the default complete case analysis method can lead to biased results. There are statistical options available to adjust for data that are MAR, including multiple imputation (MI) which is consistent and efficient at estimating effects. Multiple imputation uses informing variables to determine statistical distributions for each piece of missing data. Then multiple datasets are created by randomly drawing on the distributions for each piece of missing data. Since MI is efficient, only a limited number, usually less than 20, of imputed datasets are required to get stable estimates. Each imputed dataset is analyzed using standard statistical techniques, and then results are combined to get overall estimates of effect. A simulation study will be demonstrated to show the results of using the default complete case analysis, and MI in a linear regression of MCAR and MAR simulated data. Further, MI was successfully applied to the association study of CO2 levels and headaches when initial analysis showed there may be an underlying association between missing CO2 levels and reported headaches. Through MI, we were able to show that there is a strong association between average CO2 levels and the risk of headaches. Each unit increase in CO2 (mmHg) resulted in a doubling in the odds of reported headaches.

Foy, M.↗
DOE OSTI2024

Machine learning models of intermittent operation of RO wellhead water treatment for salinity reduction and nitrate removal

Machine learning models were developed for intermittent multi-mode operation of a wellhead reverse osmosis water purification and desalination system to predict salt passage, nitrate passage, and permeate flux. The models, based on long short-term memory (LSTM) recurrent neural network (RNN) architecture, included an attention mechanism to increase model performance in proximity of the regulatory limit for nitrate. Training and testing of the models for the Startup, Production, Shutdown and Flushing operational modes were based on operational data (consisting of 22 process variables per data sample) acquired every 2–5 s over a six-month period. The significant sets of model input attributes for the different operational modes were assessed via Spearman ranking correlation, Self-Organizing Map (SOM) analysis and feed forward feature selection (FFFS). Although the variability of nitrate passage, salt passage and permeate flux was significant over the four operational modes, prediction performance for the three outcomes were with R2 and Average Absolute Relative Error (AARE) of 0.78–0.95 and 2.96–6.16 %, respectively. Model updates post membrane elements replacement demonstrated similar levels of prediction accuracy. The study results suggest that there is merit in exploring the utility of multi-mode models for sensor fault detection, data imputation, and for potential use in model-predictive control.

Intermittent RO operation↗
DOE OSTI2021

Multi Time-scale Imputation aided State Estimation in Distribution System

With the transition to a smart grid, we are witnessing a significant growth in sensor deployments and smart metering infrastructure in the distribution system. However, information from these sensors and meters are typically unevenly sampled at different time-scales and are incomplete. It is critical to effectively aggregate these information sources for situational awareness. In order to reconcile the heterogeneous multi-scale time-series data, we present a multi-task Gaussian process framework. This framework exploits the spatio-temporal correlation across the time-series data to impute data at any desired timescale while providing confidence bounds on the imputations. The value of the imputed data for distribution system operation is illustrated via a matrix completion based state estimation strategy. Results on the IEEE 37 bus distribution system reveals the superior performance of the proposed approach relative to linear interpolation approaches.

Dahale, Shweta↗