Search NASA⌕ Search

SEARCH · Search NASA

Results for “non-stationary data”

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
DOE OSTI2026

Uncertainty guided online ensemble for non-stationary data streams in fusion science

Machine Learning (ML) is poised to play a pivotal role in the development and operation of next-generation fusion devices. Fusion data shows non-stationary behavior with distribution drifts, resulted by both experimental evolution and machine wear-and-tear. ML models assume stationary distribution and fail to maintain performance when encountered with such non-stationary data streams. Online learning techniques have been leveraged in other domains, however it has been largely unexplored for fusion applications. In this paper, we investigate online learning for continuous adaptation to drifting data streams in the prediction of Toroidal Field (TF) coils deflection at the DIII-D fusion facility. We further address the short-term performance degradation inherent to standard online learning, which arises because ground truth is unavailable at prediction time. To mitigate this issue, we propose an uncertainty-guided online ensemble framework. The method leverages the Deep Gaussian Process Approximation (DGPA) for calibrated uncertainty estimation and uses these uncertainty measures to guide a meta-algorithm that aggregates predictions from learners trained over different historical horizons. Our results show that online learning reduces prediction error by 80% compared to a static model. The online ensemble and the proposed uncertainty-guided ensemble further reduce error by approximately 6%, and 10% respectively, relative to standard single-model online learning, while also providing calibrated uncertainty estimates to support operational decision-making.

AI↗
DOE OSTI2025

Uncertainty based Online Ensemble on Non-Stationary Data for Fusion Science

Machine Learning (ML) is poised to play a pivotal role in the development and operation of next-generation fusion devices. Fusion data shows non-stationary behavior due to drifts in the data. The drifts can arise from both experimental evolution and machine wear-and-tear. ML models assume stationary distribution and fail to maintain performance when encountered with non-stationary data streams.Online learning can be used to continuously adapt the models with new data as it is acquired. However, traditional online learning can suffer from short-term performance degradation, as ground truth are not available before making the prediction. To address this challenge, we propose uncertainty aware ensemble approach for online learning. We use Deep Gaussian Process Approximation (DGPA) technique for calibrated uncertainty estimation and use the uncertainty values to guide a meta-algorithm that produces predictions based on ensemble of learners. Moreover, DGPA also provides uncertainty estimation along with the predictions for decision makers. This paper demonstrates that the proposed method outperforms traditional online learning approach, and a naive ensemble without uncertainty guidance by about 7% and 6%, respectively, on B-coil deflection prediction at DIII-D Fusion Facility.

Rajput, Kishansingh [Thomas Jefferson National Acc↗
DOE OSTI2025

Uncertainty based Online Ensemble on Non-Stationary Data for Fusion Science

Machine Learning (ML) is poised to play a pivotal role in the development and operation of next-generation fusion devices. Fusion data shows non-stationary behavior due to drifts in the data. The drifts can arise from both experimental evolution and machine wear-and-tear. ML models assume stationary distribution and fail to maintain performance when encountered with non-stationary data streams.Online learning can be used to continuously adapt the models with new data as it is acquired. However, traditional online learning can suffer from short-term performance degradation, as ground truth are not available before making the prediction. To address this challenge, we propose uncertainty aware ensemble approach for online learning. We use Deep Gaussian Process Approximation (DGPA) technique for calibrated uncertainty estimation and use the uncertainty values to guide a meta-algorithm that produces predictions based on ensemble of learners. Moreover, DGPA also provides uncertainty estimation along with the predictions for decision makers. This paper demonstrates that the proposed method outperforms traditional online learning approach, and a naive ensemble without uncertainty guidance by about 7% and 6%, respectively, on B-coil deflection prediction at DIII-D Fusion Facility.

Rajput, Kishansingh [Thomas Jefferson National Acc↗
DOE OSTI2026

Continual Learning for Particle Accelerators

Particle accelerators operate under dynamically changing conditions, which often lead to data distribution drifts. These drifts pose significant challenges for Machine Learning (ML) models, which typically fail to maintain performance when faced with such non-stationary data. In particle accelerators, the primary sources of these data drifts include changes in accelerator settings and non-measured parameters such as machine degradation and environmental factors. Previous research has proposed conditional models to handle multiple beam configurations effectively; however, it is challenging to train the ML models on all possible configuration settings. Additionally, conditional models alone can not address performance degradation caused by drifts due to non-measured factors. These limitations contribute to a significant gap between ML development and its deployment in real-world operational settings. To bridge this gap, in this paper, we identify some of the key areas within particle accelerators where continual learning can help mitigate drift-induced performance degradation. In addition, we present a practical use case where a conditional Auto-Encoder model coupled with memory-based continual learning has been employed to demonstrate stable performance even when underlying data drifts.

Schram, Malachi [Thomas Jefferson National Acceler↗
DOE OSTI2026

Continual Learning for Particle Accelerators

Particle accelerators operate under dynamically changing conditions, which often lead to data distribution drifts. These drifts pose significant challenges for Machine Learning (ML) models, which typically fail to maintain performance when faced with such non-stationary data. In particle accelerators, the primary sources of these data drifts include changes in accelerator settings and non-measured parameters such as machine degradation and environmental factors. Previous research has proposed conditional models to handle multiple beam configurations effectively; however, it is challenging to train the ML models on all possible configuration settings. Additionally, conditional models alone can not address performance degradation caused by drifts due to non-measured factors. These limitations contribute to a significant gap between ML development and its deployment in real-world operational settings. To bridge this gap, in this paper, we identify some of the key areas within particle accelerators where continual learning can help mitigate drift-induced performance degradation. In addition, we present a practical use case where a conditional Auto-Encoder model coupled with memory-based continual learning has been employed to demonstrate stable performance even when underlying data drifts

Rajput, Kishansingh [Thomas Jefferson National Acc↗
NASA NTRS1980

Source detection for the infrared astronomical satellite

A recursive algorithm is described which detects and characterizes point sources and extended sources in the data obtained from the Infrared Astronomical Satellite (IRAS) in the presence of non-stationary noise. The analysis of tests using simulated data indicates that the performance of the point source detector is very close to that expected from a matched filter with stationary gaussian noise. The false alarm rate of the extended source detector tends to be higher than expected at a given SNR.

Aumann, H. H.↗
DOE OSTI2026

FLYING SERVING: On-the-Fly Parallelism Switching for Large Language Model Serving

Production LLM serving must simultaneously deliver high throughput, low latency, and sufficient context capacity under non-stationary traffic and mixed request requirements. Data parallelism (DP) maximizes throughput by running independent replicas, while tensor parallelism (TP) reduces per-request latency and pools memory for long-context inference. However, existing serving stacks typically commit to a static parallelism configuration at deployment; adapting to bursts, priorities, or long-context requests is often disruptive and slow. We present Flying Serving, a vLLM-based system that enables online DP-TP switching without restarting engine workers. Flying Serving makes reconfiguration practical by virtualizing the state that would otherwise force data movement: (i) a zero-copy Model Weights Manager that exposes TP shard views on demand, (ii) a KV Cache Adaptor that preserves request KV state across DP/TP layouts, (iii) an eagerly initialized Communicator Pool to amortize collective setup, and (iv) a deadlock-free scheduler that coordinates safe transitions under execution skew. Across three popular LLMs and realistic serving scenarios, Flying Serving improves performance by up to 4.79 × under high load and 3.47 × under low load while supporting latency- and memory-driven requests.

Gao, Shouwei [ORNL]↗
NASA NTRS1980

Polynomial striction algorithms in the detection and determination of the characteristics of non-stationary phenomena

The effectiveness of the algorithm of polynomial striction of the data is examined, and the selection of an algorithm is carried out, according to the results of measurements of the components of the permanent magnetic field in communication sequences from the Venera-9 space vehicle, where the shock waves were recorded. It is shown that the most effective algorithm, according to the coefficient of striction, is the algorithm of the zero order interpolator. Also examined is the increase in effectiveness with the introduction of a variable threshold of comparison. The root-mean-square deviation of the error of regeneration of the data with various thresholds is calculated, and qualitative analysis of the distortions is carried out, having shown a considerable change in the form of the small discontinuities, which may be interpreted as potential interplanetary shock waves.

Yevdokimov, V. P.↗
DOE OSTI2026

Continual Learning for Production-Level Machine Learning in Particle Accelerators

Particle accelerators operate in complex environments where data distribution can change dynamically, leading to data drifts that significantly challenge Machine Learning (ML) models. These non-stationary conditions often cause ML models to deteriorate in performance, making it difficult to maintain reliable predictions in operation. The primary sources of data drifts are changes in accelerator settings and changes in equipment performance which cannot be measured directly. To bridge this gap between ML development and long-term deployment in operational settings, we identify key areas within particle accelerators where continual learning can help mitigate drift-induced performance degradation. We will provide a practical guide on selecting the appropriate method given resource constraints and desired stability plasticity trade offs. As a concrete example, we will present a real-world use case for anomaly detection to predict errant beams at the Spallation Neutron Source accelerator, where continual learning has been employed to demonstrate stable performance on drifting data streams. We will present practical challenges, lessons learned, and the results from the deployed ML model.

Rajput, Kishansingh [Thomas Jefferson National Acc↗
NASA NTRS1993

Techniques used for the analysis of oculometer eye-scanning data obtained from an air traffic control display

The methodology and techniques used to collect and analyze look-point position data from a real-time ATC display-format comparison experiment are documented. That study compared the delivery precision and controller workload of three final approach spacing aid display formats. Using an oculometer, controller lookpoint position data were collected, associated with gaze objects (e.g., moving aircraft) on the ATC display, and analyzed to determine eye-scan behavior. The equipment involved and algorithms for saving, synchronizing with the ATC simulation output, and filtering the data are described. Target (gaze object) and cross-check scanning identification algorithms are also presented. Data tables are provided of total dwell times, average dwell times, and cross-check scans. Flow charts, block diagrams, file record descriptors, and source code are included. The techniques and data presented are intended to benefit researchers in other studies that incorporate non-stationary gaze objects and oculometer equipment.

Crawford, Daniel J.↗
NASA NTRS1992

Time-frequency representation of a highly nonstationary signal via the modified Wigner distribution

A new signal analysis technique called the modified Wigner distribution (MWD) is presented. The new signal processing tool has been very successful in determining time frequency representations of highly non-stationary multicomponent signals in both simulations and trials involving actual Space Shuttle Main Engine (SSME) high frequency data. The MWD departs from the classic Wigner distribution (WD) in that it effectively eliminates the cross coupling among positive frequency components in a multiple component signal. This attribute of the MWD, which prevents the generation of 'phantom' spectral peaks, will undoubtedly increase the utility of the WD for real world signal analysis applications which more often than not involve multicomponent signals.

Zoladz, T. F.↗
DOE OSTI2024

Data-driven projection pursuit adaptation of polynomial chaos expansions for dependent high-dimensional parameters

Uncertainty quantification (UQ) and inference involving a large number of parameters are valuable tools for problems associated with heterogeneous and non-stationary behaviors. The difficulty with these problems is exacerbated when these parameters are statistically dependent requiring statistical characterization over joint measures. Probabilistic modeling methodologies stand as effective tools in the realms of UQ and inference. Among these, polynomial chaos expansions (PCE), when adapted to low-dimensional quantities of interest (QoI), provide effective yet accurate approximations for these QoI in terms of an adapted orthogonal basis. These adaptation techniques have been cast as projection pursuits in Gaussian Hilbert space in what has been referred to as a projection pursuit adaptation (PPA) by Xiaoshu Zeng and Roger Ghanem (2023). The PPA method efficiently identifies an optimal low-dimensional space for representing the QoI and simultaneously evaluates an optimal PCE within that space. The quality of this approximation clearly depends on the size of the training dataset, which is typically a function of the adapted reduced dimension. Here, the complexity of the problem is thus mediated by the complexity of the low-dimensional quantity of interest and not the complexity of the high-dimensional parameter space.

Data-driven↗
NASA NTRS1988

Digital spectral estimation and modeling of Space Shuttle flight data

Application of the digital signal processing technique of autoregressive-moving-average (ARMA) modeling to the estimation of power spectra and shock spectra from Space Shuttle lift-off flight accelerograms is described in this paper. The background for application to ARMA of lift-off accelerograms which are non-stationary in nature is exemplified through a step-by-step discussion of actual numerical results. Included is a discussion of pertinent mathematical background for the ARMA approximations. Potential areas for application of ARMA modeling in payload integration activities are suggested.

Spanos, P. D.↗
DOE OSTI2025

Asymptotic coefficients of the attached-eddy model derived from an adiabatic atmosphere

The attached-eddy model (AEM) predicts that the mean streamwise velocity and streamwise velocity variance profiles follow a logarithmic shape, while the vertical velocity variance remains invariant with height in the overlap region of high Reynolds number wall-bounded turbulent flows. Moreover, the AEM coefficients are presumed to attain asymptotically constant values at very high Reynolds numbers. Here, the AEM predictions are examined using sonic anemometer measurements in the near-neutral atmospheric surface layer, with a focus on the logarithmic behaviour of the streamwise velocity variance. Utilizing an extensive 210-day dataset collected from a 62 m meteorological tower located in the Eastern Snake River Plain, Idaho, USA, the inertial sublayer is first identified by analysing the measured momentum flux and mean velocity profiles. The logarithmic behaviour of the streamwise velocity variance and the associated ‘−1’ scaling of the streamwise velocity energy spectra are then investigated. The findings indicate that the Townsend–Perry coefficient (A 1 ) is influenced by mild non-stationarity that manifests itself as a Reynolds number dependence. After excluding non-stationary runs, and requiring the bulk Reynolds number defined using the atmospheric boundary layer height to be larger than 4 × 10 7 , the inferred A 1 converges to values ranging between 1 and 1.25, consistent with laboratory experiments. Furthermore, nine benchmark cases selected through a restrictive quality control reveal a close relation between the ‘−1’ scaling in the streamwise velocity energy spectrum and the logarithmic behaviour of streamwise velocity variance. However, additional data are required to determine whether the plateau value of the pre-multiplied streamwise velocity energy spectrum is identical to A 1 .

atmospheric flows↗
DOE OSTI2025

Non-stationary precipitation design standards for stormwater infrastructure modernization at USAF installations

The resilience of defense infrastructure systems to a changing climate is critical for national security. Climate induced recurrent flooding is already impacting over 20 U.S. Air Force installations, underscoring the urgency of revisiting precipitation standards and stormwater infrastructure design. Despite growing scientific knowledge and an expanding set of tools for updating outdated precipitation standards based on the assumption of climate stationarity, the adoption of climate informed analyses remain limited in practice. This study utilizes an existing framework to update Intensity (or Depth)-Duration-Frequency (DDF) curves using an ensemble of future climate projections. Change factors in precipitation estimates are derived and applied to six USAF installations across the U.S. The analysis is further extended to evaluate the implications of climate-informed DDFs on stormwater infrastructure performance and flood analysis at Tyndall AFB. Results indicate that the current design precipitation estimates are likely to become obsolete in all six USAF bases by the end of the century. The wide range of change factors across 32 GCM ensembles highlights the need to integrate uncertainty and evolving scientific data into infrastructure planning. The study also finds that the impacts of a changing climate vary spatially and temporally, emphasizing the value of localized analysis for infrastructure decision-making. The work advances ongoing DoD and societal efforts to implement adaptation strategies aimed at enhancing infrastructure resilience.

Intensity-duration-frequency curves↗
DOE OSTI2025

Universal method for the optimization of HDC coating uniformity on non-planar, non-stationary substrates for inertial confinement fusion targets

The thickness uniformity of chemical vapor deposited (CVD) diamond coatings on non-planar, non-stationary substrates depends on both the intrinsic instantaneous coating thickness distribution (ICTD) of the coating conditions used and, if applicable, on the frequency of substrate reorientation. While important for many CVD diamond applications, the relative impact of the ICTD and substrate reorientation on the coating thickness uniformity has not been studied. In this work, we systematically investigate the effect of these factors for microwave-plasma chemical vapor deposition (MPCVD) of diamond (referred to as high density carbon (HDC) in the inertial confinement fusion (ICF) community) coatings on spherical, rolling substrates. This coating technique is used to fabricate capsules for ICF experiments, which require extreme coating uniformity with <0.3 % thickness variation (so-called Mode 1 or M1) to ensure symmetric compression of imploding targets. To extract the otherwise unobservable reorientation timescale (Δt), Monte Carlo simulations were performed using experimental ICTD data as input. This combined approach confirms scaling relationships between the substrate reorientation timescale as well as coating thickness and coating uniformity, as expected from a 3D random walk. Simulations confirm that M1 is Rayleigh-distributed and scales as (Δt) 1/2 , consistent with the randomization of two angles that determine orientation of a sphere. We also demonstrate that, under the conditions studied, Δt is the dominant factor in determining thickness uniformity while the intrinsic ICTD has minimal impact. Finally, experiments show that Δt can be affected by total batch size under constant agitation conditions due to space constraints that limit the capsule reorientation kinetics. In conclusion, this study highlights the utility of a combined experiment-simulation approach as a general methodology for understanding and improving coating uniformity on non-planar, non-stationary substrates.

Capsule↗
NASA NTRS1985

Experimental radar Doppler wind profile measurements at Kennedy Space Center

A wind profile radar demonstration project was sponsored by the Space Transportation System (STS) Program Office to study the feasibility of incorporating continuous, high time resolution radar wind data into STS operations. This project required wind profile radars to be deployed in the vicinity of the Shuttle launch site into an environment quite unlike typical VHF profiler sites. Two 50 MHz radars were operated at the Kennedy Space Center in environments that were noisy in terms of RFI, large stationary ground clutter sources, non-stationary clutter sources, and heavy local aircraft traffic. Processing compensation for these operational constraints magnified design limitations of the research-level radars used in the demonstration. This report addresses the importance of system design for unique or particular applications with reference to finite radiation patterns, zero-Doppler processing, radar frequency, and beam pointing.

Jost, R. J.↗
NASA NTRS1988

Signal Restoration of Non-stationary Acoustic Signals in the Time Domain

Signal restoration is a method of transforming a nonstationary signal acquired by a ground based microphone to an equivalent stationary signal. The benefit of the signal restoration is a simplification of the flight test requirements because it could dispense with the need to acquire acoustic data with another aircraft flying in concert with the rotorcraft. The data quality is also generally improved because the contamination of the signal by the propeller and wind noise is not present. The restoration methodology can also be combined with other data acquisition methods, such as a multiple linear microphone array for further improvement of the test results. The methodology and software are presented for performing the signal restoration in the time domain. The method has no restrictions on flight path geometry or flight regimes. Only requirement is that the aircraft spatial position be known relative to the microphone location and synchronized with the acoustic data. The restoration process assumes that the moving source radiates a stationary signal, which is then transformed into a nonstationary signal by various modulation processes. The restoration contains only the modulation due to the source motion.

Babkin, Alexander S.↗