Search NASA⌕ Search

SEARCH · Search NASA

Results for “TIME SERIES”

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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Long-term missing value imputation for time series data using deep neural networks

We present an approach that uses a deep learning model, in particular, a MultiLayer Perceptron, for estimating the missing values of a variable in multivariate time series data. We focus on filling a long continuous gap (e.g., multiple months of missing daily observations) rather than on individual randomly missing observations. Our proposed gap filling algorithm uses an automated method for determining the optimal MLP model architecture, thus allowing for optimal prediction performance for the given time series. We tested our approach by filling gaps of various lengths (three months to three years) in three environmental datasets with different time series characteristics, namely daily groundwater levels, daily soil moisture, and hourly Net Ecosystem Exchange. We compared the accuracy of the gap-filled values obtained with our approach to the widely used R-based time series gap filling methods ImputeTS and mtsdi. The results indicate that using an MLP for filling a large gap leads to better results, especially when the data behave nonlinearly. Thus, our approach enables the use of datasets that have a large gap in one variable, which is common in many long-term environmental monitoring observations.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Series

Anomaly detection is a widely studied task for a broad variety of data types; among them, multiple time series appear frequently in applications, including for example, power grids and traffic networks. Detecting anomalies for multiple time series, however, is a challenging subject, owing to the intricate interdependencies among the constituent series. We hypothesize that anomalies occur in low density regions of a distribution and explore the use of normalizing flows for unsupervised anomaly detection, because of their superior quality in density estimation. Moreover, we propose a novel flow model by imposing a Bayesian network among constituent series. A Bayesian network is a directed acyclic graph (DAG) that models causal relationships; it factorizes the joint probability of the series into the product of easy-to-evaluate conditional probabilities. We call such a graph-augmented normalizing flow approach GANF and propose joint estimation of the DAG with flow parameters. We conduct extensive experiments on real-world datasets and demonstrate the effectiveness of GANF for density estimation, anomaly detection, and identification of time series distribution drift.

Dai, Enyan↗
DOE OSTI2020

JWST Noise Floor. I. Random Error Sources in JWST NIRCam Time Series

James Webb Space Telescope (JWST) transmission and emission spectra will provide invaluable glimpses of transiting exoplanet atmospheres, including possible biosignatures. This promising science from JWST, however, will require exquisite precision and understanding of systematic errors that can impact the time series of planets crossing in front of and behind their host stars. Here, we provide estimates of the random noise sources affecting JWST Near-Infrared Camera (NIRCam) time-series data on the integration-to-integration level. We find that 1/f noise can limit the precision of grism time series for two groups (230–1000 ppm depending on the extraction method and extraction parameters), but will average down like the square root of N frames/reads. The current NIRCam grism time-series mode is especially affected by 1/f noise because its GRISMR dispersion direction is parallel to the detector fast-read direction, but could be alleviated in the GRISMC direction. Care should be taken to include as many frames as possible per visit to reduce this 1/f noise source: thus, we recommend the smallest detector subarray sizes one can tolerate, four output channels, and readout modes that minimize the number of skipped frames (RAPID or BRIGHT2). We also describe a covariance-weighting scheme that can significantly lower the contributions from 1/f noise as compared to sum extraction. We evaluate the noise introduced by pre-amplifier offsets, random telegraph noise, and high dark current resistor capacitor (RC) pixels and find that these are correctable below 10 ppm once background subtraction and pixel masking are performed. We explore systematic error sources in a companion paper.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

Distribution Function Instead of Steady-State Assumption in Time-Series Simulation

The quasi-steady-state assumption in time-series simulation is inadequate to model phenomena of interest to energy system integration such as inverter clipping, sell-back of excess electricity to a utility and utility hosting capacity, and battery throughput. Researchers are working on stochastic modeling, higher-resolution time series data, and machine learning approaches to address this need. This poster describes a distribution function that allows a maximum value, minimum value, and shape to the curve that can vary within each time-step based only on data inputs at the resolution of that time step (eg. Hourly). The distribution function is not used to synthesize high-resolution data, rather scalar integrals are used to calculate the quantities of interest within each time step. The form of the distribution function shows significant reduction in error when compared to 1 minute data and commercial software employing the distribution function (HOMER Pro version 14.3 and higher) shows a much improved estimate of inverter clipping in an example.

battery↗
DOE OSTI2022

MAD: Self-Supervised Masked Anomaly Detection Task for Multivariate Time Series

In this paper, we introduce Masked Anomaly Detection (MAD), a general self-supervised learning task for multivariate time series anomaly detection. With the increasing availability of sensor data from industrial systems, being able to detecting anomalies from streams of multivariate time series data is of significant importance. Given the scarcity of anomalies in real-world applications, the majority of literature has been focusing on modeling normality. The learned normal representations can empower anomaly detection as the model has learned to capture certain key underlying data regularities. A typical formulation is to learn a predictive model, i.e., use a window of time series data to predict future data values. In this paper, we propose an alternative self-supervised learning task. By randomly masking a portion of the inputs and training a model to estimate them using the remaining ones, MAD is an improvement over the traditional left-to-right next step prediction (NSP) task. Our experimental results demonstrate that MAD can achieve better anomaly detection rates over traditional NSP approaches when using exactly the same neural network (NN) base models, and can be modified to run as fast as NSP models during test time on the same hardware, thus making it an ideal upgrade for many existing NSP-based NN anomaly detection models.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Explainable AI for Multivariate Time Series Pattern Exploration: Latent Space Visual Analytics With Temporal Fusion Transformer and Variational Autoencoders in Power Grid Event Diagnosis

Detecting and analyzing complex patterns in multivariate time-series data is crucial for decision-making in urban and environmental system operations. However, challenges arise from the high dimensionality, intricate complexity, and interconnected nature of complex patterns, which hinder the understanding of their underlying physical processes. Existing AI methods often face limitations in interpretability, computational efficiency, and scalability, reducing their applicability in real-world scenarios. This paper proposes a novel visual analytics framework that integrates two generative AI models, Temporal Fusion Transformer (TFT) and Variational Autoencoders (VAEs), to reduce complex patterns into lower-dimensional latent spaces and visualize them in 2D using dimensionality reduction techniques such as PCA, t-SNE, and UMAP with DBSCAN. These visualizations, presented through coordinated and interactive views and tailored glyphs, enable intuitive exploration of complex multivariate temporal patterns, identifying patterns’ similarities and uncover their potential correlations for a better interpretability of the AI outputs. The framework is demonstrated through a case study on power grid signal data, where it identifies multi-label grid event signatures, including faults and anomalies with diverse root causes. Additionally, novel metrics and visualizations are introduced to validate the models and assess the performance, efficiency, and consistency of latent maps generated by VAE, which have been utilized in prior studies for latent space cartography and used as a benchmark in this study, and the emerging TFT architecture under various configurations. These analyses provide actionable insights for model parameter tuning and reliability improvements. Comparative results highlight that TFT achieves shorter run times and superior scalability to diverse time-series data shapes compared to VAE. This work advances fault diagnosis in multivariate time series, fostering explainable AI to support critical system operations.

Explainable AI↗
DOE OSTI2021

Screening candidate supplementary cementitious materials under standard and accelerated curing through time-series surface resistivity measurements and change-point detection

Time-series surface resistivity (SR) measurements are evaluated as an indicator of pozzolanicity in concretes containing 13 materials of both known and unknown pozzolanicity, under standard and accelerated curing conditions, and the results were validated against portlandite consumption obtained through thermogravimetric analysis. Change-point detection (CPD) analysis is applied to the data to provide a rigorous indicator of hydration age of the onset and rate of the pozzolanic reaction, if occurring. The SR measurements were able to capture the onset of the pozzolanic reactions in concretes curing at elevated temperature regimes, which allows determination of pozzolanicity weeks earlier than at standard curing temperatures. Using CPD along with slope analysis allows a comprehensive analysis of a material's reactivity and determination of pozzolanicity in as quickly as two days. Time-series SR measurements at elevated curing conditions, along with limits on material composition, are recommended for determination of pozzolanic reactivity in novel or variable materials.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Monitoring of Liquid Metal Reactor Heater Zones with Recurrent Neural Network Learning of Temperature Time Series

Advanced high-temperature fluid reactors (ARs), such as sodium fast reactors (SFRs) and molten salt cooled reactors (MSCRs) utilize high-temperature fluids at ambient pressure. To melt the fluid during reactor startup and prevent fluid freezing during cooldown, the thermal–hydraulic systems of such ARs include heater zones consisting of specific heaters with controllers, temperature sensors, and thermal insulation. The failure of heater zones due to insulation material degradation or improper installation, resulting in parasitic heat losses, can lead to fluid freezing. The detection of faults using a heat-transfer model is difficult because of a lack of knowledge of the experimental details. Data-driven machine learning of heater zone temperature time series offers a viable alternative. In this study, we benchmarked the performance of recurrent neural networks (RNNs) in an analysis of heat-up transient temperature time series of heater zones installed on a liquid sodium vessel. The RNN models include long short-term memory (LSTM) and gated recurrent unit (GRU) networks, as well as their bi-directional variants, BiLSTM and BiGRU. Anomalous temperature points were designated using a percentile-based threshold applied to residual fluctuations in the detrended temperature time series. Additionally, the impact of the exponentially weighted moving average (EWMA) method on detection accuracy was examined. The RNN models’ performance was assessed using precision, recall, and F 1 score metrics. Results demonstrated that RNN models effectively detect anomalies in temperature time series with the best models for each heater zone achieving F 1 scores of over 93%. To explain the variations in RNN model performance across different heater zones, we used Kullback–Leibler (KL) divergence to quantify the relative entropy between training and testing data, and the Detrended Fluctuation Analysis (DFA) to assess long-range temporal correlations. For datasets with strong long-range correlations and minimal relative entropy between training and testing data, GRU is the best-performing model. When the data exhibits weaker long-term correlations and a significant relative entropy between training and testing distributions, BiGRU shows the best performance. For the data sets with intermediate values of both KL divergence and DFA, the best performance is obtained with LSTM and BiLSTM, respectively.

gated recurrent unit↗
DOE OSTI2024

Machine-learned closure of URANS for stably stratified turbulence: connecting physical timescales & data hyperparameters of deep time-series models

Stably stratified turbulence (SST), a model that is representative of the turbulence found in the oceans and atmosphere, is strongly affected by fine balances between forces and becomes more anisotropic in time for decaying scenarios. Moreover, there is a limited understanding of the physical phenomena described by some of the terms in the Unsteady Reynolds-Averaged Navier–Stokes (URANS) equations—used to numerically simulate approximate solutions for such turbulent flows. Rather than attempting to model each term in URANS separately, it is attractive to explore the capability of machine learning (ML) to model groups of terms, i.e. to directly model the force balances. We develop deep time-series ML for closure modeling of the URANS equations applied to SST. We consider decaying SST which are homogeneous and stably stratified by a uniform density gradient, enabling dimensionality reduction. We consider two time-series ML models: long short-term memory and neural ordinary differential equation. Both models perform accurately and are numerically stable in a posteriori (online) tests. Furthermore, we explore the data requirements of the time-series ML models by extracting physically relevant timescales of the complex system. We find that the ratio of the timescales of the minimum information required by the ML models to accurately capture the dynamics of the SST corresponds to the Reynolds number of the flow. The current framework provides the backbone to explore the capability of such models to capture the dynamics of high-dimensional complex dynamical system like SST flows.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Time Series Classification for Locating Forced Oscillation Sources

Here, this article presents a machine learning based time-series classification method for using synchrophasor measurements to locate the source of forced oscillation (FO) for fast disturbance removal. First, multivariate time series (MTS) matrices are constructed by the most informative measurements selected by sequential feature selection from each power plant. Then, the Mahalanobis matrix is trained such that the Mahalanobis distance between the MTSs from the same class (i.e., with the same FO source location) are minimized and from different classes (i.e., with different FO source locations) are maximized. This allows MTSs to be classified by classifiers with class membership corresponding to the location of each FO source. To meet the runtime requirements of online matching, class templates are constructed to reduce data size and improve matching efficiency. To account for uncertainty in identifying the exact beginning of an FO event, dynamic time warping is used to align the out-of-sync MTSs. IEEE 39bus and WECC 179bus systems are used for algorithm development and validation. Simulation results demonstrate that the algorithm meets online operation runtime requirement with high accuracy using misaligned data sets.

42 ENGINEERING↗
DOE OSTI2020

Time-series machine-learning error models for approximate solutions to parameterized dynamical systems

This work proposes a machine-learning framework for modeling the error incurred by approximate solutions to parameterized dynamical systems. In particular, we extend the machine-learning error models (MLEM) framework proposed in Ref. Freno and Carlberg (2019) to dynamical systems. The proposed Time-Series Machine-Learning Error Modeling (T-MLEM) method constructs a regression model that maps features – which comprise error indicators that are derived from standard a posteriori error-quantification techniques – to a random variable for the approximate-solution error at each time instance. The proposed framework considers a wide range of candidate features, regression methods, and additive noise models. We consider primarily recursive regression techniques developed for time-series modeling, including both classical time-series models (e.g., autoregressive models) and recurrent neural networks (RNNs), but also analyze standard non-recursive regression techniques (e.g., feed-forward neural networks) for comparative purposes. Finally, numerical experiments conducted on multiple benchmark problems illustrate that the long short-term memory (LSTM) neural network, which is a type of RNN, outperforms other methods and yields substantial improvements in error predictions over traditional approaches.

42 ENGINEERING↗
DOE OSTI2022

PVAnalytics: A Python Package for Automated Processing of Solar Time Series Data

Multiple publicly available software packages exist that analyze solar time series data, including RdTools and Solar Data Tools, among others. Several of these packages contain their own unique quality assurance (QA) and feature recognition algorithms. The python PVAnalytics package was developed to offer an internally consistent source for these analysis tools, making it easier for the end user to deploy these routines on his or her solar data. The PVAnalytics package currently contains routines for outlier detection, inverter clipping detection, irradiance and temperature checks, orientation checks, and data shift detection, among other functions. These functions have been aggregated from various sources including Solar Forecast Arbiter, RdTools, and the QA process developed by NREL's PV Fleets Initiative. We are continuously adding new functionality to the package, including documentation, examples and algorithms. By bundling QA functionality into a single software package, we hope to make PVAnalytics a comprehensive software library to support analysis of solar metadata and time series data.

data cleaning↗
DOE OSTI2020

Hylia: Time-Series Library for Network Operations (Hylia) v1

The ability to analyze time-series data in network operations is critical to ensure optimal operations and management in wide area networks, sensor networks, and cloud networks. Hylia is a collection of multiple time-series prediction algorithms designed specifically to work with network monitoring data sets such as SNMP, NETFLOW and other monitoring data. It is designed to recognize these features and perform the extrapolation of the data.

Kiran, Mariam↗
DOE OSTI2023

QA/QC-ed Groundwater Level Time Series in PLM-1 and PLM-6 Monitoring Wells, East River, Colorado (2016-2022)

This data set contains QA/QC-ed (Quality Assurance and Quality Control) water level data for the PLM1 and PLM6 wells. PLM1 and PLM6 are location identifiers used by the Watershed Function SFA project for two groundwater monitoring wells along an elevation gradient located along the lower montane life zone of a hillslope near the Pumphouse location at the East River Watershed, Colorado, USA. These wells are used to monitor subsurface water and carbon inventories and fluxes, and to determine the seasonally dependent flow of groundwater under the PLM hillslope. The downslope flow of groundwater in combination with data on groundwater chemistry (see related references) can be used to estimate rates of solute export from the hillslope to the floodplain and river. QA/QC analysis of measured groundwater levels in monitoring wells PLM-1 and PLM-6 included identification and flagging of duplicated values of timestamps, gap filling of missing timestamps and water levels, removal of abnormal/bad and outliers of measured water levels. The QA/QC analysis also tested the application of different QA/QC methods and the development of regular (5-minute, 1-hour, and 1-day) time series datasets, which can serve as a benchmark for testing other QA/QC techniques, and will be applicable for ecohydrological modeling. The package includes a Readme file, one R code file used to perform QA/QC, a series of 8 data csv files (six QA/QC-ed regular time series datasets of varying intervals (5-min, 1-hr, 1-day) and two files with QA/QC flagging of original data), and three files for the reporting format adoption of this dataset (InstallationMethods, file level metadata (flmd), and data dictionary (dd) files).QA/QC-ed data herein were derived from the original/raw data publication available at Williams et al., 2020 (DOI: 10.15485/1818367). For more information about running R code file (10.15485_1866836_QAQC_PLM1_PLM6.R) to reproduce QA/QC output files, see README (QAQC_PLM_readme.docx). This dataset replaces the previously published raw data time series, and is the final groundwater data product for the PLM wells in the East River. Complete metadata information on the PLM1 and PLM6 wells are available in a related dataset on ESS-DIVE: Varadharajan C, et al (2022). https://doi.org/10.15485/1660962. These data products are part of the Watershed Function Scientific Focus Area collection effort to further scientific understanding of biogeochemical dynamics from genome to watershed scales. 2022/09/09 Update: Converted data files using ESS-DIVE’s Hydrological Monitoring Reporting Format. With the adoption of this reporting format, the addition of three new files (v1_20220909_flmd.csv, V1_20220909_dd.csv, and InstallationMethods.csv) were added. The file-level metadata file (v1_20220909_flmd.csv) contains information specific to the files contained within the dataset. The data dictionary file (v1_20220909_dd.csv) contains definitions of column headers and other terms across the dataset. The installation methods file (InstallationMethods.csv) contains a description of methods associated with installation and deployment at PLM1 and PLM6 wells. Additionally, eight data files were re-formatted to follow the reporting format guidance (er_plm1_waterlevel_2016-2020.csv, er_plm1_waterlevel_1-hour_2016-2020.csv, er_plm1_waterlevel_daily_2016-2020.csv, QA_PLM1_Flagging.csv, er_plm6_waterlevel_2016-2020.csv, er_plm6_waterlevel_1-hour_2016-2020.csv, er_plm6_waterlevel_daily_2016-2020.csv, QA_PLM6_Flagging.csv). The major changes to the data files include the addition of header_rows above the data containing metadata about the particular well, units, and sensor description. 2023/01/18 Update: Dataset updated to include additional QA/QC-ed water level data up until 2022-10-12 for ER-PLM1 and 2022-10-13 for ER-PLM6. Reporting format specific files (v2_20230118_flmd.csv, v2_20230118_dd.csv, v2_20230118_InstallationMethods.csv) were updated to reflect the additional data. R code file (QAQC_PLM1_PLM6.R) was added to replace the previously uploaded HTML files to enable execution of the associated code. R code file (QAQC_PLM1_PLM6.R) and ReadMe file (QAQC_PLM_readme.docx) were revised to clarify where original data was retrieved from and to remove local file paths.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Delegated Regressor, A Robust Approach for Automated Anomaly Detection in the Soil Radon Time Series Data

We propose a new method based on the idea of delegating regressors for predicting the soil radon gas concentration (SRGC) and anomalies in radon or any other time series data. The proposed method is compared to different traditional boosting e.g., Extreme Gradient Boosting (EGB) and simple regression methods e.g., support vector regressors with linear kernel and radial kernel in terms of accurate predictions. R language has been used for the statistical analysis of radon time series (RTS) data. The results obtained show that the proposed methodology predicts SRGC more accurately when compared to different traditional boosting and regression methods. The best correlation is found between the actual and predicted radon concentration for window size of 2 i.e., two days before and after the start of seismic activities. RTS data was collected from 05 February 2017 to 16 February 2018, including 7 seismic events recorded during the study period. Findings of study show that the proposed methodology predicts the SRGC with more precision, for all the window sizes, by overlapping predicted with the actual radon time series concentrations.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Implementing Spatio-Temporal 3D-Convolution Neural Networks and UAV Time Series Imagery to Better Predict Lodging Damage in Sorghum

Unmanned aerial vehicle (UAV)-based remote sensing is gaining momentum in a variety of agricultural and environmental applications. Very-high-resolution remote sensing image sets collected repeatedly throughout a crop growing season are becoming increasingly common. Analytical methods able to learn from both spatial and time dimensions of the data may allow for an improved estimation of crop traits, as well as the effects of genetics and the environment on these traits. Multispectral and geometric time series imagery was collected by UAV on 11 dates, along with ground-truth data, in a field trial of 866 genetically diverse biomass sorghum accessions. We compared the performance of Convolution Neural Network (CNN) architectures that used image data from single dates (two spatial dimensions, 2D) versus multiple dates (two spatial dimensions + temporal dimension, 3D) to estimate lodging detection and severity. Lodging was detected with 3D-CNN analysis of time series imagery with 0.88 accuracy, 0.92 Precision, and 0.83 Recall. This outperformed the best 2D-CNN on a single date with 0.85 accuracy, 0.84 Precision, and 0.76 Recall. The variation in lodging severity was estimated by the best 3D-CNN analysis with 9.4% mean absolute error (MAE), 11.9% root mean square error (RMSE), and goodness-of-fit (R2) of 0.76. This was a significant improvement over the best 2D-CNN analysis with 11.84% MAE, 14.91% RMSE, and 0.63 R2. The success of the improved 3D-CNN analysis approach depended on the inclusion of “before and after” data, i.e., images collected on dates before and after the lodging event. The integration of geometric and spectral features with 3D-CNN architecture was also key to the improved assessment of lodging severity, which is an important and difficult-to-assess phenomenon in bioenergy feedstocks such as biomass sorghum. This demonstrates that spatio-temporal CNN architectures based on UAV time series imagery have significant potential to enhance plant phenotyping capabilities in crop breeding and Precision agriculture applications.

3D-convolution neural networks↗
DOE OSTI2022

Improved Data Interpretation through Identification of Time Series Periodicity Changes

Analysis and interpretation of time series data is easiest when the data values occur at uniform intervals in time, but actual data may have differing data sampling frequencies, such as monthly and daily readings. Applying data analysis techniques, such as smoothing, to such a data set may not give a representative result between time segments. The ability to automatically distinguish time segments of differing data frequency would provide a means for applying data analysis independently to each segment, though a suitable blending at segment boundaries would be required. A method for detecting frequency changes was developed and applied to Gaussian and median smoothing of hydraulic head data from groundwater wells at the U.S. Department of Energy Hanford Site in southeastern Washington state. The process identifies time segments of high-frequency (daily) or low-frequency (greater than daily) data using adjusted-bandwidth Gaussian kernel density estimation and a threshold value, which are further refined to address small blocks of low-frequency data within larger blocks of high-frequency data. User-selectable levels of smoothing are then applied independently to the time segments prior to combining the segment results for a single smoothed data set. This time segment identification approach provides effective low- and high-frequency data separation, which provides a method to apply data analysis independently to each time segment.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Relation Inference among Sensor Time Series in Smart Buildings with Metric Learning

Smart Building Technologies hold promise for better livability for residents and lower energy footprints. Yet, the rollout of these technologies, from demand response controls to fault detection and diagnosis, significantly lags behind and is impeded by the current practice of manual identification of sensing point relationships, e.g., how equipment is connected or which sensors are co-located in the same space. This manual process is still error-prone, albeit costly and laborious.We study relation inference among sensor time series. Our key insight is that, as equipment is connected or sensors co-locate in the same physical environment, they are affected by the same real-world events, e.g., a fan turning on or a person entering the room, thus exhibiting correlated changes in their time series data. To this end, we develop a deep metric learning solution that first converts the primitive sensor time series to the frequency domain, and then optimizes a representation of sensors that encodes their relations. Built upon the learned representation, our solution pinpoints the relationships among sensors via solving a combinatorial optimization problem. Extensive experiments on real-world buildings demonstrate the effectiveness of our solution.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗