Search NASA⌕ Search

SEARCH · Search NASA

Results for “Statistical Learning”

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 613 records · Page 34
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Big-data Efficient and Automated Science Transfer (BEAST): An Open-Source Software Architecture for Arc Jet Data Management, Modeling, and Automation

Big-data Efficient and Automated Science Transfer (BEAST) was conceived to address the existing ground testing data management of the NASA Ames arc jet facilities (e.g., manually entered Excel files and USB drive data transfers). These data management practices were seen as a choke point for future thermal protection system (TPS) development as they limit statistical tracking, resolution of diagnostics, coordination between video/time series, data throughput, and data processing speed/efficiency. Consequently, BEAST was developed to provide a new data infrastructure with streamlined data collection, processing, transfer, and analysis. This new framework also seeks to implement the FAIR principles of data stewardship: Findable, Accessible, Interoperable, and Reusable. The BEAST framework is based on a combination of the Python Django web framework and the Python data stack to provide a monolithic, open-source platform for data management, automation, and machine learning. This architecture was chosen for maintainability and scalability for a small, in-house development team. This paper will describe the application framework, deployment, and discuss the benefits and future plans for the system.

Data management↗
NASA NTRSDate not supplied

Big-data Efficient Automated Science Transfer (BEAST): an open-source software architecture for arc jet data management, modeling, and automation

Big-data Efficient and Automated Science Transfer (BEAST) was conceived to address the existing ground testing data management of the NASA Ames arc jet facilities (e.g., manually entered Excel files and USB drive data transfers). These data management practices were seen as a choke point for future thermal protection system (TPS) development as they limit statistical tracking, resolution of diagnostics, coordination between video/time series, data throughput, and data processing speed/efficiency. Consequently, BEAST was developed to provide a new data infrastructure with streamlined data collection, processing, transfer, and analysis. This new framework also seeks to implement the FAIR principles of data stewardship: Findable, Accessible, Interoperable, and Reusable. The BEAST framework is based on a combination of the Python Django web framework and the Python data stack to provide a monolithic, open-source platform for data management, automation, and machine learning. This architecture was chosen for maintainability and scalability for a small, in-house development team. This paper will describe the application framework, deployment, and discuss the benefits and future plans for the system.

Data management↗
NASA NTRS2004

Building Hybrid Rover Models for NASA: Lessons Learned

Particle filters have recently become popular for diagnosis and monitoring of hybrid systems. In this paper we describe our experiences using particle filters on a real diagnosis problem, the NASA Ames Research Center's K-9 rover. As well as the challenge of modelling the dynamics of the system, there are two major issues in applying a particle filter to such a model. The first is the asynchronous nature of the system-observations from different subsystems arrive at different rates, and occasionally out of order, leading to large amounts of uncertainty in the state of the system. The second issue is data interpretation. The particle filter produces a probability distribution over the state of the system, from which summary statistics that can be used for control or higher-level diagnosis must be extracted. We describe our approaches to both these problems, as well as other modelling issues that arose in this domain.

Willeke, Thomas↗
DOE OSTI2025

Network Anomaly Detection in Distributed Edge Computing Infrastructure

As networks continue to grow in complexity and scale, detecting anomalies has become increasingly challenging, particularly in diverse and geographically dispersed environments. Traditional approaches often struggle with managing the computational burden associated with analyzing large-scale network traffic to identify anomalies. This paper introduces a distributed edge computing framework that integrates federated learning with Apache Spark and Kubernetes to address these challenges. We hypothesize that our approach, which enables collaborative model training across distributed nodes, significantly enhances the detection accuracy of network anomalies across different network types. We show that by leveraging distributed computing and containerization technologies, our framework not only improves scalability and fault tolerance but also achieves superior detection performance compared to state-of-the-art methods. Extensive experiments on the UNSW-NB15 and ROAD datasets validate the effectiveness of our approach, demonstrating statistically significant improvements in detection accuracy and training efficiency over baseline models, as confirmed by MannWhitney U and Kolmogorov-Smirnov tests (p<0.05).

Marfo, William [University of Texas at El Paso,Dep↗
DOE OSTI2025

One-shot gas detection with transformer paired neural networks in Mako collected longwave infrared hyperspectral imagery

To date, careful data treatment workflows and statistical detectors are used to perform hyperspectral image (HSI) detection of any gas contained in a spectral library, which is often expanded with physics models to incorporate different spectral characteristics. In general, surrounding evidence or known gas-release parameters are used to provide confidence in or confirm detection capability, respectively. This makes quantifying detection performance difficult as it is nearly impossible to develop an absolute ground truth for gas target pixel presence in collected HSI. Consequently, developing and comparing new detection methods, especially machine learning (ML)-based methods, is susceptible to subjectivity in derived detection map quality. Here, in this work, we demonstrate the first use of transformer-based paired neural networks (PNNs) for one-shot gas target detection for multiple gases while providing quantitative classification and detection metrics for their use on labeled data. Terabytes of training data are generated from a database of long-wave infrared HSI obtained from historical Mako sensor campaigns over Los Angeles. By incorporating labels, singular signature representations, and a model development pipeline, we can tune and select PNNs to detect multiple gas targets that are not seen in training on a quantitative basis. We additionally assess our test set detections using interpretability techniques widely employed with ML-based predictors, but less common with detection methods relying on learned latent spaces.

Hyperspectral imaging↗
NASA NTRS2007

Mach 10 Stage Separation Analysis for the X43-A

This paper describes the pre-flight stage separation analysis that was conducted in support of the final flight of the X-43A. In that flight, which occurred less than eight months after the successful Mach 7 flight, the X-43A Research Vehicle attained a peak speed of Mach 9.6. Details are provided on how the lessons learned from the Mach 7 flight affected separation modeling and how adjustments were made to account for the increased flight Mach number. Also, the procedure for defining the feedback loop closure and feed-forward parameters employed in the separation control logic are described, and their effect on separation performance is explained. In addition, the range and nominal values of these parameters, which were included in the Mission Data Load, are presented. Once updates were made, the nominal pre-flight trajectory and Monte Carlo statistical results were determined and stress tests were performed to ensure system robustness. During flight the vehicle performed within the uncertainty bounds predicted in the pre-flight analysis and ultimately set the world record for airbreathing powered flight.

Tartabini, Paul V.↗
DOE OSTI2026

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

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

autoregressive prediction↗
DOE OSTI2025

Using Artificial Intelligence to Improve Reliability and Operational Efficiency of Small-Scale Hydroelectric Distributed Generation

Reliability and resilience are critical concerns for distributed generation (DG) at the rural electric level. The integration of renewable energy sources, such as small-scale hydroelectric distributed generators (hydro DGs), introduces operational challenges, particularly regarding aging infrastructure and grid stability. Artificial Intelligence (AI)-driven Machine Learning (ML) models and applications of Large Language Models (LLMs) offer promising solutions for optimizing DG operations and enhancing resilience. This paper explores AI-based models for improving efficiency, fault resolution, and outage mitigation in small-scale hydro DGs. Furthermore, it highlights the development of a centralized, AI-powered information portal for rural electric cooperatives and municipalities. The research evaluates hydro DG plant models and discusses the applicability of AI-powered question-answering tools for real-time operations, focusing on statistical data, load flow, voltage regulation, and generation power. The findings demonstrate AI’s potential to transform DG management to ensure greater stability and resilience in rural electric grids.

Bhattacharyya, Arjun [ORNL] (ORCID:000900060976046↗
NASA NTRS2009

Evaluating Failures and Near Misses in Human Spaceflight History for Lessons for Future Human Spaceflight

There have been a number of studies done in the past drawn on lessons learned with regard to human loss-of-life events. Generally, the systemic causes and proximate causes for fatal events have both been examined in considerable detail. However, an examination of near-fatal accidents and failures that narrowly missed being fatal could be equally useful, not only in detecting causes, both proximate and systemic, but also for determining what factors averted disaster, what design decisions and/or operator actions prevented catastrophe. Additionally, review of risk factors for upcoming or future programs will often look at trending statistics, generally focusing on failure/success statistics. Unfortunately, doing so can give a skewed or misleading view of past reliability or a reliability that cannot be presumed to apply to a new program. One reason for this might be that failure/success criteria aren't the same across programs, but also that apparent success can hide systemic faults that, under other circumstances, can be fatal to a program with different parameters. A program with a number of near misses can look more reliable than a consistently healthy program with a single out-of-family failure and provide very misleading data if it is not examined in detail. This is particularly true for a manned space program where failure/success includes more than making a particular orbit. Augmenting reliability evaluations with this near miss data can provide insight and expand on the limitations of a strictly pass/fail evaluation. Even more importantly, a thorough understanding of these near miss events can identify conditions that prevented fatalities. Those conditions may be key to a programs reliability, but, without insight to the repercussions if such conditions were not in place, their importance may not be readily clear. As programs mature and political and fiscal responsibilities come to the fore, often there is considerable incentive to eliminate unnecessary conservatism, design margin, redundancy, operational support, testing, training, or safety oversight. An evaluation that demonstrates how these features and capabilities averted disaster can ensure processes that saved lives or missions are not discarded without appropriate review and understanding. Close examination of accidents that almost were can also highlight differences in design from one program to another, either justifying reliability comparisons or negating them. It can also provide considerable insight into how those saving factors were developed and implemented so that similar methods can be used to ensure appropriate life-saving and mission saving factors can be developed, even for a dissimilar space program. The lessons are appropriate for seasoned manned space programs and agencies, but crucial for untried agencies and organizations that are interested in sending man into space. The large body of publicly available near miss and accident data available provide invaluable insight into programmatic, technical, and even political issues that can be addressed before they impact safety. In this paper, we examine a number of these near misses and accidents and steps a program, agency, or potential spacefaring company might take to improve their chances of success and avoid mission or safety disasters using this data.

Barr, Stephanie↗
NASA NTRS1990

Intelligent control and adaptive systems; Proceedings of the Meeting, Philadelphia, PA, Nov. 7, 8, 1989

Various papers on intelligent control and adaptive systems are presented. Individual topics addressed include: control architecture for a Mars walking vehicle, representation for error detection and recovery in robot task plans, real-time operating system for robots, execution monitoring of a mobile robot system, statistical mechanics models for motion and force planning, global kinematics for manipulator planning and control, exploration of unknown mechanical assemblies through manipulation, low-level representations for robot vision, harmonic functions for robot path construction, simulation of dual behavior of an autonomous system. Also discussed are: control framework for hand-arm coordination, neural network approach to multivehicle navigation, electronic neural networks for global optimization, neural network for L1 norm linear regression, planning for assembly with robot hands, neural networks in dynamical systems, control design with iterative learning, improved fuzzy process control of spacecraft autonomous rendezvous using a genetic algorithm.

Rodriguez, Guillermo↗
DOE OSTI2024

Automated Approach to Accurate, Precise, and Fast Detector Simulation and Reconstruction

Detector simulation and reconstruction are a significant computational bottleneck in particle physics. Here, we develop particle-flow neural-assisted simulations (parnassus) to address this challenge. Our deep learning model takes as input a point cloud (particles impinging on a detector) and produces a point cloud (reconstructed particles). By combining detector simulations and reconstruction into one step, we aim to minimize resource utilization and enable fast surrogate models suitable for application both inside and outside large collaborations. We demonstrate this approach using a publicly available dataset of jets passed through the full simulation and reconstruction pipeline of the Compact Muon Solenoid (CMS) experiment. We show that parnassus accurately mimics the CMS particle flow algorithm on the (statistically) same events it was trained on and can generalize to jet momentum and type outside of the training distribution.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
NASA NTRSDate not supplied

Continuing Long-term Global SO 2 Data Record with JPSS OMPS Instruments

NASA’s long-term Earth Observing System (EOS) SO 2 climate data record (CDR) started with Aura/Ozone Monitoring Instrument (OMI, launched in 2004) and is now being continued with the SNPP/Ozone Mapping and Profiler Suite (OMPS, launched in 2011). Both OMI and SNPP/OMPS SO 2 CDRs are produced with the Goddard principal component analysis (PCA) spectral fitting algorithm. By inherently accounting for various instrumental factors, the PCA technique enables highly consistent retrievals between different instruments. In this presentation, we will provide an overview on our effort to further extend the EOS SO 2 CDR, by implementing the PCA SO 2 algorithm with multiple OMPS instruments flying on the Joint Polar Satellite System (JPSS) constellation, including NOAA-20 (launched in 2017) and NOAA-21 (launched in 2022). We will present results analyzing our new NOAA-20/OMPS PCA SO 2 EOS continuity product, to be publicly released in fall of 2023. We will show statistical analyses on the quality of NOAA-20 PCA SO 2 product, such as retrieval noise, biases over background areas, and long-term stability. We will employ a previously established top-down method to estimate SO2 emissions from selected large point sources, using NOAA-20 SO 2 retrievals and assimilated wind fields as input. The SO 2 emission estimates derived from NOAA-20 retrievals will be compared with those from OMI, SNPP/OMPS, and S5P/TROPOMI (TROPOspheric Monitoring Instrument). We will also demonstrate the application of a new machine learning technique that further reduces the noise of NOAA-20 SO 2 retrievals. Finally, we will present preliminary PCA SO 2 retrievals from recently launched satellite sensors, including NOAA-21/OMPS and NASA’s geostationary TEMPO (Tropospheric Emissions: Monitoring of Pollution) instrument.

SO2↗
DOE OSTI2026

Revealing EDL-driven reduction mechanisms in binary, ternary, and quaternary fluorinated electrolytes via an integrated MD–DFT–ML framework

Accurately predicting solid electrolyte interphase (SEI) formation requires explicitly resolving the electric double layer (EDL) structure, which deviates significantly from that of the bulk electrolyte. Although an established molecular dynamics (MD) and Density Functional Theory (DFT) framework can model SEI formation by evaluating reduction reactions of local clusters in the EDL, it suffers from a combinatorial computational bottleneck. To overcome this limitation, we introduce a machine-learning-accelerated simulation workflow (MD–DFT–ML), integrating a gradient-boosted regression model trained on EDL composition data to efficiently predict reduction potentials. We apply this framework to seven fluorinated electrolytes comprising fluorinated anions, a fluorinated ester solvent, two types of diluent (ion-solvating ester vs. non-solvating ether), and an FEC additive. The analysis shows that the EDL selectively accumulates cation-binding species; consequently, the non–cation-binding ether diluent rarely enters the EDL and makes minimal contributions to SEI formation. DFT calculations on statistically representative EDL clusters provide reduction potentials and fluorine-release pathways, while the ML model, which substantially reduces the DFT workload, predicts cluster reduction energies with a mean absolute error of 0.1 eV. The combined MD–DFT–ML approach also quantifies contributions from different sources to LiF formation in the SEI. This methodology establishes a generalizable route for multiscale modeling electrolyte and interphase design for next-generation electrochemical energy-storage systems.

DFT-MD-ML workflow↗
NASA NTRS1997

Carbon in the Former Soviet Union: The Current Balance

This work has been carried out in a period of great changes in Russia that have brought extreme hardships to the scientific community. We have been fortunate in establishing excellent relationships with the Russian scientific community and believe we have helped to retain coherence in circumstances where the continuation of research was in doubt. We have learned much and have been effective in advancing, even establishing, scholars and programs in Russia that might not otherwise have survived the transition. The vigor of the International Boreal Forest Research Association (IBFRA) is one sign of the value and success of these activities. Largely due to the current political and economic transitions in the former Soviet Union, the forests of much of the FSU are under reduced logging pressure. In addition, there is a decline in air pollution as heavy industry has waned, at least for now. Russian forestry statistics and our personal experience indicate a decline, perhaps as high as 60%, in forest harvesting over the last few years. But, new international market pressures on the forests exist in European Russia and in the Far East. The central government, still the "owner" of Russian forests, is having difficulty maintaining control over forest use and management particularly in the Far East and among the southern territories that have large, nonRussian ethnic populations. Extraordinarily large areas of mixed forest and grasslands, sparse or open forests, and mixed forests and tundra must be considered when calculating forest area It is insufficient to think of Russia as simply forest and nonforest Forest productivity, measured as growth of timber, appears to be in decline in all areas of Russia except in European Russia. Most information and publications on the recent history of these forests is heavily dependent on statistical data from the Soviet era. The interpretation of these data is very much open to debate. Anatoly Shwidenko, a long term collaborator and former senior scientist (mensuration) for the Soviet Committee on Forests, now a scholar at the International Institute of Applied Systems Analysis (IIASA), Vienna, has provided abundant contributions from the data available to him and from his experience. Forest stand carbon is concentrated in the Russian Far East (i.e. Primorski Kray), Central-Southern Siberia and European Russia But, soil carbon can be 10 times forest stand C. Our efforts in mapping the area and changes in area (as well as the internal structure) of forests have made major contributions to our joint understanding of the scale and status of these forests. To realize the importance of this contribution one needs only to recognize that any large scale Soviet-era maps of the area did not include latitude and longitude. Even today, there is great reluctance to provide these data, the basis of any GIS.

Woodwell, G. M.↗
NASA NTRS1997

Development of Computer Models for the Assessment of Foreign Body Impact Events on Composite Structures

The objective of this project was to model the 5-3/4 inch pressure vessels used on the NASA RTOP program in an attempt to learn more about how impact damage forms and what are the residual effects of the resulting damage. A global-local finite element model was developed for the bottle and the states of stress in the bottles were determined down to the constituent level. The experimental data that was generated on the NASA RTOP program was not in a form that enabled the model developed under this grant to be correlated with the experimental data. As a result of this exercise it is recommended that an experimental program be designed using statistical design of experiment techniques to generate data that can be used to isolate the phenomenon that control the formation of impact damage. This data should include residual property determinations so that models for post impact structural integrity can be developed. It is also recommended that the global-local methodology be integrated directly into the finite element code. This will require considerable code development.

Bucinell, Ronald B.↗
NASA NTRSDate not supplied

Comparison of Multivariate Time Series Prediction Techniques for Emulating Noah-LSM Soil Moisture Outputs

Land surface models are crucial tools for many earth science applications including numerical weather prediction, water resource and crop monitoring, and climatological analysis. Given a set of atmospheric forcings, seasonal data, and static parameters, models like Noah-LSM solve for land surface quantities including skin temperature, sensible heat flux, and soil moisture. While these calculations are theoretically robust, they are often computationally expensive. Since artificial neural networks (ANNs) are universal function approximators, they can learn to emulate the output of a deterministic numerical model given a time series of input forcings, with the learned ANN having substantially shorter execution time. The ANN could efficiently parameterize other models, generate ensembles, and provide first-guess inputs for retrievals. As such, with the goal of developing a model that efficiently mimics the output of Noah-LSM given NLDAS2 forcings on a region covering much of the central US, we examine and compare several neural network architectures for the multi-horizon multivariate time series forecasting problem. Recent literature includes a diverse set of approaches including autoregressive architectures like LSTM and GRU, parametric and non-parametric statistical predictors (ForecastNet and MQRNN), self-attention (LSTM-attention-LSTM), and temporal convovlution (DeepTCN). We implement several of these models for the Noah-LSM prediction task, highlighting the features and challenges for each and providing practical insight on the training process.

Mitchell Dodson↗
DOE OSTI2024

Formation and retrieval of cell assemblies in a biologically realistic spiking neural network model of area CA3 in the mouse hippocampus

The hippocampal formation is critical for episodic memory, with area Cornu Ammonis 3 (CA3) a necessary substrate for auto-associative pattern completion. Recent theoretical and experimental evidence suggests that the formation and retrieval of cell assemblies enable these functions. Yet, how cell assemblies are formed and retrieved in a full-scale spiking neural network (SNN) of CA3 that incorporates the observed diversity of neurons and connections within this circuit is not well understood. Here, we demonstrate that a data-driven SNN model quantitatively reflecting the neuron type-specific population sizes, intrinsic electrophysiology, connectivity statistics, synaptic signaling, and long-term plasticity of the mouse CA3 is capable of robust auto-association and pattern completion via cell assemblies. Our results show that a broad range of assembly sizes could successfully and systematically retrieve patterns from heavily incomplete or corrupted cues after a limited number of presentations. Furthermore, performance was robust with respect to partial overlap of assemblies through shared cells, substantially enhancing memory capacity. These novel findings provide computational evidence that the specific biological properties of the CA3 circuit produce an effective neural substrate for associative learning in the mammalian brain.

hetero-association↗