Engineering Papers⌕ Search

SEARCH · Engineering Papers

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 1,225 records · Page 68
All sourcesNASA NTRSDOE OSTI
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 OSTI2024

Learning stochastic dynamics and predicting emergent behavior using transformers

We show that a neural network originally designed for language processing can learn the dynamical rules of a stochastic system by observation of a single dynamical trajectory of the system, and can accurately predict its emergent behavior under conditions not observed during training. We consider a lattice model of active matter undergoing continuous-time Monte Carlo dynamics, simulated at a density at which its steady state comprises small, dispersed clusters. We train a neural network called a transformer on a single trajectory of the model. The transformer, which we show has the capacity to represent dynamical rules that are numerous and nonlocal, learns that the dynamics of this model consists of a small number of processes. Forward-propagated trajectories of the trained transformer, at densities not encountered during training, exhibit motility-induced phase separation and so predict the existence of a nonequilibrium phase transition. Transformers have the flexibility to learn dynamical rules from observation without explicit enumeration of rates or coarse-graining of configuration space, and so the procedure used here can be applied to a wide range of physical systems, including those with large and complex dynamical generators.

97 MATHEMATICS AND COMPUTING↗
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 OSTI2021

Extracting the Galactic Center excess’ source-count distribution with neural nets

The two leading hypotheses for the Galactic Center excess (GCE) in the Fermi data are an unresolved population of faint millisecond pulsars (MSPs) and dark-matter (DM) annihilation. The dichotomy between these explanations is typically reflected by modeling them as two separate emission components. However, point sources (PSs) such as MSPs become statistically degenerate with smooth Poisson emission in the ultrafaint limit (formally where each source is expected to contribute much less than one photon on average), leading to an ambiguity that can render questions such as whether the emission is PS-like or Poissonian in nature ill defined. We present a conceptually new approach that describes the PS and Poisson emission in a unified manner and only afterwards derives constraints on the Poissonian component from the so obtained results. For the implementation of this approach, we leverage deep learning techniques, centered around a neural network-based method for histogram regression that expresses uncertainties in terms of quantiles. We demonstrate that our method is robust against a number of systematics that have plagued previous approaches, in particular DM/PS misattribution. In the Fermi data, we find a faint GCE described by a median source-count distribution (SCD) peaked at a flux of ~ 4 x 10 -11 counts cm -2 s -1 (corresponding to ~ 3-4 expected counts per PS), which would require N ~ $\mathscr{O}$(10 4 ) sources to explain the entire excess (median value N = 29,300 across the sky). Although faint, this SCD allows us to derive the constraint η ρ ≤ 66% for the Poissonian fraction of the GCE flux η ρ at 95% confidence, suggesting that a substantial amount of the GCE flux is due to PSs.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
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↗
DOE OSTI2020

Robust Medium-Voltage Distribution System State Estimation using Multi-Source Data

Due to the lack of sufficient online measurements for distribution system observability, pseudo-measurements from short-term load or distributed renewable energy resources (DERs) forecasting are used. However, the accuracy of them is low and thus significantly limits the performance of distribution system state estimation (DSSE). In this paper, a robust DSSE that integrates multi-source measurement data is proposed. Specifically, the historical low-voltage (LV) side smart meters are used to forecast load and DERs injections via the support vector machine (SVM) with optimally tuned parameters. By contrast, the online smart meters at LV side are utilized to derive equivalent power injections at the MV/LV transformers, yielding more accurate pseudo-measurements compared to the forecasted injections. Furthermore, to deal with bad data caused by communication loss, instrumental errors and cyber attacks, robust DSSE that relies on generalized maximum-likelihood (GM)-estimation criterion is developed. The projection statistics are developed to adjust the weights of each measurement, leading to better balance between pseudo- and real-time measurements. Numerical results conducted on modified IEEE 33-bus system with DG integration demonstrate the effectiveness and robustness of the proposed method.

distribution system state estimation↗
DOE OSTI2022

Deep Learning for Subgrid‐Scale Turbulence Modeling in Large‐Eddy Simulations of the Convective Atmospheric Boundary Layer

Abstract In large‐eddy simulations, subgrid‐scale (SGS) processes are parameterized as a function of filtered grid‐scale variables. First‐order, algebraic SGS models are based on the eddy‐viscosity assumption, which does not always hold for turbulence. Here we apply supervised deep neural networks (DNNs) to learn SGS stresses from a set of neighboring coarse‐grained velocity from direct numerical simulations of the convective boundary layer at friction Reynolds numbers Re τ up to 1243 without invoking the eddy‐viscosity assumption. The DNN model was found to produce higher correlation between SGS stresses compared to the Smagorinsky model and the Smagorinsky‐Bardina mixed model in the surface and mixed layers and can be applied to different grid resolutions and various stability conditions ranging from near neutral to very unstable. The DNN model can capture key statistics of turbulence in a posteriori (online) tests when applied to large‐eddy simulations of the atmospheric boundary layer.

54 ENVIRONMENTAL SCIENCES↗
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 OSTI2021

Machine learning for neutron reflectometry data analysis of two-layer thin films

Neutron reflectometry (NR) is a powerful tool for probing thin films at length scales down to nanometers. We investigated the use of a neural network to predict a two-layer thin film structure to model a given measured reflectivity curve. Application of this neural network to predict a thin film structure revealed that it was accurate and could provide an excellent starting point for traditional fitting methods. Employing prediction-guided fitting has considerable potential for more rapidly producing a result compared to the labor-intensive but commonly-used approach of trial and error searches prior to refinement. A deeper look at the stability of the predictive power of the neural network against statistical fluctuations of measured reflectivity profiles showed that the predictions are stable. We conclude that the approach presented here can provide valuable assistance to users of NR and should be further extended for use in studies of more complex n-layer thin film systems. This result also opens up the possibility of developing adaptive measurement systems in the future.

36 MATERIALS SCIENCE↗
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.↗
DOE OSTI2024

High dimensional predictions of suicide risk in 4.2 million US Veterans using ensemble transfer learning

We present an ensemble transfer learning method to predict suicide from Veterans Affairs (VA) electronic medical records (EMR). A diverse set of base models was trained to predict a binary outcome constructed from reported suicide, suicide attempt, and overdose diagnoses with varying choices of study design and prediction methodology. Each model used twenty cross-sectional and 190 longitudinal variables observed in eight time intervals covering 7.5 years prior to the time of prediction. Ensembles of seven base models were created and fine-tuned with ten variables expected to change with study design and outcome definition in order to predict suicide and combined outcome in a prospective cohort. The ensemble models achieved c-statistics of 0.73 on 2-year suicide risk and 0.83 on the combined outcome when predicting on a prospective cohort of ~4.2 M veterans. The ensembles rely on nonlinear base models trained using a matched retrospective nested case-control (Rcc) study cohort and show good calibration across a diversity of subgroups, including risk strata, age, sex, race, and level of healthcare utilization. In addition, a linear Rcc base model provided a rich set of biological predictors, including indicators of suicide, substance use disorder, mental health diagnoses and treatments, hypoxia and vascular damage, and demographics. Similar content being viewed by others

60 APPLIED LIFE SCIENCES↗