Search NASA⌕ Search

SEARCH · Search NASA

Results for “Autoregressive model”

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 181 records · Page 10
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Representing the Sub-Grid Heterogeneity of Surface Precipitation in A General Circulation Model

Precipitation variability on spatial scales smaller than a typical general circulation model (GCM) grid box is often neglected, with the grid-mean precipitation rate being applied uniformly to underlying surface tiles. This reduces the extrema seen by the surface, with corresponding reductions in surface runoff and altered land-atmosphere fluxes. Here we present a novel approach to stochastically distribute precipitation across sub-grid surface tiles within a GCM. Based on 4 km Stage IV precipitation data, the scheme parameterizes the dry area fraction as a function of grid mean precipitation rate, and defines the relative distribution of intensities across non-dry surface tiles. To incorporate memory and mimic the persistence of precipitating storms, the relative intensity assigned to each sub-grid tile is determined by an autoregressive process. Using single column experiments, the scheme is shown to reproduce observed precipitation statistics at the scale of model surface tiles. We also document impacts on surface hydrology and energy partitioning, with notable increases in precipitation runoff, surface temperature variance, and the Bowen ratio.

GCM↗
NASA NTRS1992

Stratospheric ozone profile and total ozone trends derived from the SAGE I and SAGE II data

Global trends in both stratospheric column ozone and as a function of altitude are derived on the basis of SAGE I/II ozone data from the period 1979-1991. A statistical model containing quasi-biennial, seasonal, and semiannual oscillations, a linear component, and a first-order autoregressive noise process was fit to the time series of SAGE I/II monthly zonal mean data. The linear trend in column ozone above 17-km altitude, averaged between 65 deg S and 65 deg N, is -0.30 +/-0.19 percent/yr, or -3.6 percent over the time period February 1979 through April 1991. The data show that the column trend above 17 km is nearly zero in the tropics and increases towards the high latitudes with values of -0.6 percent/yr at 60 deg S and -0.35 percent/yr at 60 deg N. Both these results are in agreement with the recent TOMS results. The profile trend analyses show that the column ozone losses are occurring below 25 km, with most of the loss coming from the region between 17 and 20 km. Negative trend values on the order of -2 percent/yr are found at 17 km in midlatitudes.

Mccormick, M. P.↗
DOE OSTI2025

Enhancing Short-Range Weather Forecasts through Temporal Variation Encoding: A Multiperiod Embedding Approach

Machine learning (ML) techniques have emerged as promising approaches to improve regional weather forecast accuracy and reliability through data-driven methods. We propose a novel ML-based weather forecasting model, the Multiperiod Embed Net (MPENet). A key distinguishing feature of MPENet is its explicit utilization of the inherent cyclic nature in weather dynamics, unlike the autoregressive strategies commonly used in other ML weather forecasting approaches. Critical cyclic structures are identified via Fourier analyses of dynamic time series. Cyclicity in the convolutional representation is achieved by transforming one-dimensional time series of meteorological variables into two-dimensional tensors based on identified periods. This approach enables the model to leverage intrinsic weather patterns, enhancing regional forecast performance. To demonstrate the effectiveness of MPENet, we conduct a comparative analysis with Nvidia’s FourCastNet. Both models are trained on High-Resolution Rapid Refresh (HRRR) data from 2015 to 2022, over a 192 km × 192 km region in Tennessee. The comparisons are performed locally at two specific locations known to have different weather dynamics due to orographic effects: Crossville, on the relatively flat Cumberland Plateau with fewer topographic airflow disruptions, and Oak Ridge, in the ridge-and-valley region, where airflow is heavily influenced by surrounding valleys and mountains. Our results indicate that FourCastNet achieves strong accuracy at very short lead times, while MPENet maintains competitive skill and shows advantages in capturing temporal evolution over longer periods. Cross-correlation analyses of MPENet and FourCastNet predictions with the HRRR data suggest that encoding critical cyclicity into the network architecture leads to improvements in the forecasting skill.

Artificial intelligence↗
DOE OSTI2021

Self-Supervised Anomaly Detection via Neural Autoregressive Flows with Active Learning

Many self-supervised methods have been proposed with the target of image anomaly detection. These methods often rely on the paradigm of data augmentation with predefined transformations such as flipping, cropping, and rotations. However, it is not straightforward to apply these techniques for non-image data, such as time series or tabular data, while the performance of the existing deep approaches has been under our expectation on tasks beyond images. In this work, we propose a novel active learning (AL) scheme that relied on neural autoregressive flows (NAF) for self-supervised anomaly detection, specifically on small-scale data. Unlike other generative models such as GANs or VAEs, flow-based models allow to explicitly learn the probability density and thus can assign accurate likelihoods to normal data which makes it usable to detect anomalies. The proposed NAF-AL method is achieved by efficiently generating random samples from latent space and transforming them into feature space along with likelihoods via invertible mapping. The samples with lower likelihoods are selected and further checked by outlier detection using Mahalanobis distance. The augmented samples incorporating with normal samples are used for training a better detector so as to approach decision boundaries. Compared with random transformations, NAF-AL can be interpreted as a likelihood-oriented data augmentation that is more efficient and robust. Extensive experiments show that our approach outperforms existing baselines on multiple time series and tabular datasets, and a real-world application in advanced manufacturing, with significant improvement on anomaly detection accuracy and robustness over the state-of-the-art.

Zhang, Jiaxin↗
DOE OSTI2025

Intercomparison of Deep Learning Model Architectures for Atmospheric River Prediction

With a rapid surge in the application of machine learning (ML) for a diverse range of tasks in climate science, the present study addresses a challenge for climate scientists when selecting the optimal ML or deep learning (DL) architecture for a given application. In particular, a DL intercomparison study was performed with a focus on forecasting the position of atmospheric rivers (ARs) on short-range time scales (up to 5-day lead times). AR predictions from multiple DL architectures, including various types of convolutional autoencoders and a vision transformer (ViT), were compared against ECMWF ERA5 reanalysis and hindcasts from a global climate model. DL models with similar trainable parameters were trained on ERA5 reanalysis data and AR positions derived from a thresholding algorithm to ensure a fair comparison among the DL models. Each model’s performance and accuracy in forecasting AR location and key input fields within a 5-day window were assessed using metrics of root-mean-square error, anomaly correlation, and mean intersection over union. The ViT architecture outperformed other autoencoder models in most of the metrics. Incorporating additional meteorological fields only yielded slight improvements in forecasting certain fields at longer lead times. The results also suggest that a smaller number of input time steps or smaller number of autoregressive steps can achieve better prediction skills, while also improving the overall computational efficiency. This research offers valuable insights into the strengths and weaknesses of different DL techniques for AR forecasting, hopefully guiding the development of improved models for forecasting this phenomenon.

54 ENVIRONMENTAL SCIENCES↗
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↗
NASA NTRSDate not supplied

Generalized Predictive Control for Active Stability Augmentation and Vibration Reduction on an Aeroelastic Tiltrotor Model

Tiltrotor aircraft are defining the state-of-the-art in vertical lift technology as they have the potential to greatly expand rotary-wing operational boundaries. However, they are often limited in forward flight speed due to complex coupled rotor and wing dynamic instabilities. The U.S. Army and NASA have been developing a new wind tunnel model, the TiltRotor Aeroelastic Stability Testbed(TRAST), to test proprotors in the NASA Langley Research Center Transonic Dynamics Tunnel (TDT) to investigate aeroelastic stability in cruise. The test is intended to provide high-quality research data for analytical tool development and validation. In addition, the TRAST model will support, develop, and mature new technologies for the design of advanced proprotor aircraft. Stability augmentation and vibration reduction during testing is planned with the use of an active control methodology known as Generalized Predictive Control(GPC). GPC is an autoregressive control law that experimentally acquires a system identification to derive the input-output relation of controls and corresponding sensors. This type of control law is especially useful for complex dynamic interactions that are difficult to explicitly model such as proprotor pylon instability, often referred to as whirl flutter. GPC has been successfully employed on other tiltrotor vehicles to suppress whirl flutter instabilities and vibrations. To aid in the characterization of the wind-tunnel model and in tool development, an analytical representation of the wind-tunnel model was developed using the rotorcraft comprehensive analysis system (RCAS) that simulates structural dynamics and aerodynamics. RCAS was used to derive state-space estimates of the physical plant at various flight conditions to test control law effectiveness. This paper will present an overview of the test article development, a description of RCAS, an explanation of the GPC methodology, and results of GPC being applied to state-space plant estimates of the TRAST model. In these simulations, GPC was effective at stabilizing the aircraft beyond the whirl-flutter boundary while simultaneously reducing vibrations across the flight regime. Additionally, a modern advancement to GPC, termed advanced GPC (AGPC), is introduced that enables a self-adapting system identification. Preliminary results show that AGPC is successful at self-correction as the plant changes from what was used for system identification.

tiltrotor↗
NASA NTRS1990

Representation of high frequency Space Shuttle data by ARMA algorithms and random response spectra

High frequency Space Shuttle lift-off data are treated by autoregressive (AR) and autoregressive-moving-average (ARMA) digital algorithms. These algorithms provide useful information on the spectral densities of the data. Further, they yield spectral models which lend themselves to incorporation to the concept of the random response spectrum. This concept yields a reasonably smooth power spectrum for the design of structural and mechanical systems when the available data bank is limited. Due to the non-stationarity of the lift-off event, the pertinent data are split into three slices. Each of the slices is associated with a rather distinguishable phase of the lift-off event, where stationarity can be expected. The presented results are rather preliminary in nature; it is aimed to call attention to the availability of the discussed digital algorithms and to the need to augment the Space Shuttle data bank as more flights are completed.

Spanos, P. D.↗
NASA NTRS1994

Spectral representation of high-frequency Space Shuttle data

High frequency Space Shuttle liftoff data are treated by autoregressive (AR) and autoregressive-moving-average (ARMA) digital algorithms. These algorithms provide useful information on the spectral densities of the data. Further, they yield spectral models, which lend themeselves to incorporation into the concept of the random response spectrum. This concept yields a reasonably smooth power spectrum for the design of structural and mechanical systems when the available data bank is limited. Due to the nonstationary of the liftoff event, the pertinent data are split into three slices. Each of the slices is associated with a rather distinguished phase of the liftoff event, in which stationarity can be expected. The presented results are preliminary in nature; they aim to call attention to the availability of the discussed concepts and to the need to augment the Space Shuttle data bank as more flights are completed.

Spanos, P. D.↗
DOE OSTI2022

Examining AGN UV/Optical Variability beyond the Simple Damped Random Walk

We present damped harmonic oscillator (DHO) light-curve modeling for a sample of 12,714 spectroscopically confirmed quasars in the Sloan Digital Sky Survey Stripe 82 region. DHO is a second-order continuous-time autoregressive moving-average process, which can be fully described using four independent parameters: a natural oscillation frequency (ω 0 ), a damping ratio (ξ), a characteristic perturbation timescale (τ perturb ), and an amplitude for the perturbing white noise (σ ϵ ). The asymptotic variability amplitude of a DHO process is quantified by σ DHO —a function of ω 0 , ξ, τ perturb , and σ ϵ . We find that both τ perturb and σ ϵ follow different dependencies with rest-frame wavelength (λ RF ) on either side of 2500 Å, whereas σ DHO follows a single power-law relation with λ RF . After correcting for wavelength dependence, σ DHO exhibits anticorrelations with both the Eddington ratio and the black hole mass, while τ perturb —with a typical value of days in the rest frame—shows an anticorrelation with the bolometric luminosity. Modeling active galactic nuclei (AGN) variability as a DHO offers more insight into the workings of accretion disks close to the supermassive black holes at the center of AGN. The newly discovered short-term variability (characterized by τ perturb and σ ϵ ) and its correlation with bolometric luminosity pave the way for new algorithms that will derive fundamental properties (e.g., Eddington ratio) of AGN using photometric data alone.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRS1988

Statistical analysis of effective singular values in matrix rank determination

A major problem in using SVD (singular-value decomposition) as a tool in determining the effective rank of a perturbed matrix is that of distinguishing between significantly small and significantly large singular values to the end, conference regions are derived for the perturbed singular values of matrices with noisy observation data. The analysis is based on the theories of perturbations of singular values and statistical significance test. Threshold bounds for perturbation due to finite-precision and i.i.d. random models are evaluated. In random models, the threshold bounds depend on the dimension of the matrix, the noisy variance, and predefined statistical level of significance. Results applied to the problem of determining the effective order of a linear autoregressive system from the approximate rank of a sample autocorrelation matrix are considered. Various numerical examples illustrating the usefulness of these bounds and comparisons to other previously known approaches are given.

Konstantinides, Konstantinos↗
DOE OSTI2026

Improving Spectral Resolution from Real-time Evolution for Correlated Systems

Abstract The quality of numerically simulated spectra using real-time evolution methods for strongly correlated systems is affected by both the length of simulation time and the system size, limiting resolution in both frequency and momentum. In this work, we propose a computationally cheap, linear autoregressive machine learning-based framework to extend short-time and short-distance results over a wider range. We use the proposed method to extend the lesser Green’s function for both the Hubbard model and the much more computationally challenging Hubbard-extended Holstein model. This technique significantly improves both the frequency and momentum resolution of the single-particle removal spectrum $${\mathcal{A}}(k,\omega )$$ A ( k , ω ) , allowing the observation of otherwise obscured spectral features due to electron-phonon coupling.

Tang, Ta↗
DOE OSTI2023

Efficient 3D Molecular Design with an E(3) Invariant Transformer VAE

This work introduces a three-dimensional (3D) invariant graph-to-string transformer variational autoencoders (VAE) (Vagrant) for generating molecules with accurate density functional theory (DFT)-level properties. Vagrant learns to model the joint probability distribution of a 3D molecular structure and its properties by encoding molecular structures into a 3D-aware latent space. Directed navigation through this latent space implicitly optimizes the 3D structure of a molecule, and the latent embedding can be used to condition a generative transformer to predict the candidate structure as a one-dimensional (1D) sequence. Additionally, we introduce two novel sampling methods that exploit the latent characteristics of a VAE to improve performance. Here, we show that our method outperforms comparable 3D autoregressive and diffusion methods for predicting quantum chemical property values of novel molecules in terms of both sample quality and computational efficiency.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
NASA NTRS1992

Search for deterministic pulse trends in gamma ray burst temporal profiles

Most cosmic gamma-ray burst temporal profiles appear to be comprised of several individual pulses, many of which overlap. It is advantageous to deconvolve the temporal structures into their constituent pulses, and thereby investigate the shape, intensity and temporal distributions of the pulses as a function of energy. Such fundamental pulse descriptors would provide constraints for theoretical modeling of the burst emission process, such as indications of source size, optical depth and geometry, as a function of time. We have developed a deconvolution algorithm which treats sequences of pulse shapes that change deterministically. The algorithm, a generalization of autoregressive techniques, has been applied to a few bright bursts observed by BATSE. Results indicate that, even within short intervals, constituent pulses are not self-similarly shaped, nor do pulse shapes evolve in a simple manner throughout a burst. Hence, the direction of our future work on pulse deconvolution will focus on analysis methods which allow pulse shape to vary.

Norris, J. P.↗
NASA NTRS2005

Construction of Covariance Functions with Variable Length Fields

This article focuses on construction, directly in physical space, of three-dimensional covariance functions parametrized by a tunable length field, and on an application of this theory to reproduce the Quasi-Biennial Oscillation (QBO) in the Goddard Earth Observing System, Version 4 (GEOS-4) data assimilation system. These Covariance models are referred to as multi-level or nonseparable, to associate them with the application where a multi-level covariance with a large troposphere to stratosphere length field gradient is used to reproduce the QBO from sparse radiosonde observations in the tropical lower stratosphere. The multi-level covariance functions extend well-known single level covariance functions depending only on a length scale. Generalizations of the first- and third-order autoregressive covariances in three dimensions are given, providing multi-level covariances with zero and three derivatives at zero separation, respectively. Multi-level piecewise rational covariances with two continuous derivatives at zero separation are also provided. Multi-level powerlaw covariances are constructed with continuous derivatives of all orders. Additional multi-level covariance functions are constructed using the Schur product of single and multi-level covariance functions. A multi-level powerlaw covariance used to reproduce the QBO in GEOS-4 is described along with details of the assimilation experiments. The new covariance model is shown to represent the vertical wind shear associated with the QBO much more effectively than in the baseline GEOS-4 system.

Gaspari, Gregory↗
NASA NTRS1991

Implementation of a modal filter on a five meter truss structure

Modal filtering is a spatial filtering technique which uses a weighted sum of a number of response measurements to extract the modal coordinates of the system from the physical response coordinates. No moving average or autoregressive calculations are required to implement the modal filter thus the modal coordinates may be calculated in real time. For practical implementation of the modal filter, the number and location of response locations must be chosen carefully. A modal filter is implemented on a five meter model space truss as a case study. The modal coordinates are extracted in real time using Hewlett Packard 3565 data acquisition and processig hardware. The effect of the number and location of response measurements on the performance of the modal filter is investigated. Applications of the modal filter to modal control and fast parameter identification are also discussed.

Shelly, S.↗
DOE OSTI2022

Sampling lattices in semi-grand canonical ensemble with autoregressive machine learning

Calculating thermodynamic potentials and observables efficiently and accurately is key for the application of statistical mechanics simulations to materials science. However, naive Monte Carlo approaches, on which such calculations are often dependent, struggle to scale to complex materials in many state-of-the-art disciplines such as the design of high entropy alloys or multi-component catalysts. To address this issue, we adapt sampling tools built upon machine learning-based generative modeling to the materials space by transforming them into the semi-grand canonical ensemble. Furthermore, we show that the resulting models are transferable across wide ranges of thermodynamic conditions and can be implemented with any internal energy model U, allowing integration into many existing materials workflows. We demonstrate the applicability of this approach to the simulation of benchmark systems (AgPd, CuAu) that exhibit diverse thermodynamic behavior in their phase diagrams. Finally, we discuss remaining challenges in model development and promising research directions for future improvements.

36 MATERIALS SCIENCE↗
NASA NTRS1989

A two dimensional power spectral estimate for some nonstationary processes

A two dimensional estimate for the power spectral density of a nonstationary process is being developed. The estimate will be applied to helicopter noise data which is clearly nonstationary. The acoustic pressure from the isolated main rotor and isolated tail rotor is known to be periodically correlated (PC) and the combined noise from the main and tail rotors is assumed to be correlation autoregressive (CAR). The results of this nonstationary analysis will be compared with the current method of assuming that the data is stationary and analyzing it as such. Another method of analysis is to introduce a random phase shift into the data as shown by Papoulis to produce a time history which can then be accurately modeled as stationary. This method will also be investigated for the helicopter data. A method used to determine the period of a PC process when the period is not know is discussed. The period of a PC process must be known in order to produce an accurate spectral representation for the process. The spectral estimate is developed. The bias and variability of the estimate are also discussed. Finally, the current method for analyzing nonstationary data is compared to that of using a two dimensional spectral representation. In addition, the method of phase shifting the data is examined.

Smith, Gregory L.↗