Search NASA⌕ Search

SEARCH · Search NASA

Results for “test approach”

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 145 records · Page 8
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

State-Space Model to Estimate Salmon Escapement Using Multiple Data Sources

Abstract Accurate estimates of salmonids passing Lower Granite Dam on the Snake River, by species and origin, are a critical input to assessing the status and trends of various populations as well as successful management of fisheries in the Snake River basin. Here, we describe a state-space model that estimates such escapement past a dam by using window counts, PIT tag observations, and data from an adult fish trap, accounting for issues such as nighttime passage, fallback and reascension, potential observation error at the window, and uncertainty in the adult trap rate. We tested the approach using a simulation framework that mimicked several levels of observation error, differences between nighttime passage and reascension rates, and the possibility of the adult trap being closed for some period of time. Our results demonstrate that the model produced unbiased estimates across all tested scenarios. We also applied this model to empirical data from Lower Granite Dam to produce estimates of wild, clipped hatchery, and unclipped hatchery spring/summer-run Chinook Salmon Oncorhynchus tshawytscha and steelhead O. mykiss from spawn years 2010–2019.

See, Kevin E. (ORCID:0000000297626442)↗
DOE OSTI2022

Photometric calibration in u -band using blue halo stars

ABSTRACT We develop a method to calibrate u-band photometry based on the observed colour of blue Galactic halo stars. The Galactic halo stars belong to an old stellar population of the Milky Way and have relatively low metallicity. The ‘blue tip’ of the halo population – the main sequence turn-off (MSTO) stars – is known to have a relatively uniform intrinsic edge u-g colour with only slow spatial variation. In SDSS data, the observed variation is correlated with Galactic Latitude, which we attribute to contamination by higher metallicity disc stars and fit with an empirical curve. This curve can then be used to calibrate u-band imaging if g-band imaging of matching depth is available. Our approach can be applied to single-field observations at |b| > 30°, and removes the need for standard star observations or overlap with calibrated u-band imaging. We include in our method the calibration of g-band data with ATLAS-Refcat2. We test our approach on stars in KiDS DR 4, ATLAS DR 4, and DECam imaging from the NOIRLab Source Catalog (NSC DR2), and compare our calibration with SDSS. For this process, we use synthetic magnitudes to derive the colour equations between these data sets, in order to improve zero-point accuracy. We find an improvement for all data sets, reaching a zero-point precision of 0.016 mag for KiDS (compared to the original 0.033 mag), 0.020 mag for ATLAS (originally 0.027 mag), and 0.016 mag for DECam (originally 0.041 mag). Thus, this method alone reaches the goal of 0.02 mag photometric precision in u-band for the Rubin Observatory’s Legacy Survey of Space and Time (LSST).

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2024

Simultaneous energy and mass calibration of large-radius jets with the ATLAS detector using a deep neural network

The energy and mass measurements of jets are crucial tasks for the Large Hadron Collider experiments. This paper presents a new calibration method to simultaneously calibrate these quantities for large-radius jets measured with the ATLAS detector using a deep neural network (DNN). To address the specificities of the calibration problem, special loss functions and training procedures are employed, and a complex network architecture, which includes feature annotation and residual connection layers, is used. The DNN-based calibration is compared to the standard numerical approach in an extensive series of tests. The DNN approach is found to perform significantly better in almost all of the tests and over most of the relevant kinematic phase space. In particular, it consistently improves the energy and mass resolutions, with a 30% better energy resolution obtained for transverse momenta $p$ T > $500$ GeV.

47 OTHER INSTRUMENTATION↗
DOE OSTI2025

Modification and analysis of context-specific genome-scale metabolic models: methane-utilizing microbial chassis as a case study

ABSTRACT Context-specific genome-scale model (CS-GSM) reconstruction is becoming an efficient strategy for integrating and cross-comparing experimental multi-scale data to explore the relationship between cellular genotypes, facilitating fundamental or applied research discoveries. However, the application of CS modeling for non-conventional microbes is still challenging. Here, we present a graphical user interface that integrates COBRApy, EscherPy, and RIPTiDe, Python-based tools within the BioUML platform, and streamlines the reconstruction and interrogation of the CS genome-scale metabolic frameworks via Jupyter Notebook. The approach was tested using -omics data collected for Methylotuvimicrobium alcaliphilum 20Z R , a prominent microbial chassis for methane capturing and valorization. We optimized the previously reconstructed whole genome-scale metabolic network by adjusting the flux distribution using gene expression data. The outputs of the automatically reconstructed CS metabolic network were comparable to manually optimized i IA409 models for Ca-growth conditions. However, the CS model questions the reversibility of the phosphoketolase pathway and suggests higher flux via primary oxidation pathways. The model also highlighted unresolved carbon partitioning between assimilatory and catabolic pathways at the formaldehyde-formate node. Only a very few genes and only one enzyme with a predicted function in C1 metabolism, a homolog of the formaldehyde oxidation enzyme ( fae1-2 ), showed a significant change in expression in La-growth conditions. The CS-GSM predictions agreed with the experimental measurements under the assumption that the Fae1-2 is a part of the tetrahydrofolate-linked pathway. The cellular roles of the tungsten (W)-dependent formate dehydrogenase ( fdhAB ) and fae homologs ( fae1-2 and fae3 ) were investigated via mutagenesis. The phenotype of the f dhAB mutant followed the model prediction. Furthermore, a more significant reduction of the biomass yield was observed during growth in La-supplemented media, confirming a higher flux through formate. M. alcaliphilum 20Z R mutants lacking fae1-2 did not display any significant defects in methane or methanol-dependent growth. However, contrary to fae1, the fae1-2 homolog failed to restore the formaldehyde-activating enzyme function in complementation tests. Overall, the presented data suggest that the developed computational workflow supports the reconstruction and validation of CS-GSM networks of non-model microbes. IMPORTANCE The interrogation of various types of data is a routine strategy to explore the relationship between genotype and phenotype. An efficient approach for integrating and cross-comparing experimental multi-scale data in the context of whole-genome-based metabolic network reconstruction becomes a powerful tool that facilitates fundamental and applied research discoveries. The present study describes the reconstruction of a context-specific (CS) model for the methane-utilizing bacterium, Methylotuvimicrobium alcaliphilum 20Z R . M. alcaliphilum 20Z R is becoming an attractive microbial platform for the production of biofuels, chemicals, pharmaceuticals, and bio-sorbents for capturing atmospheric methane. We demonstrate that this pipeline can help reconstruct metabolic models that are similar to manually curated networks. Furthermore, the model is able to highlight previously overlooked pathways, thus advancing fundamental knowledge of non-model microbial systems or promoting their development toward biotechnological or environmental implementations.

Kulyashov, M. A.↗
DOE OSTI2025

Numerical simulation of compressible fluid-dynamics in the chamber of inertial fusion energy systems

Here, this paper aims to establish new and innovative modeling capabilities for analyzing chambers in Inertial Fusion Energy (IFE) systems. IFE is emerging as a promising method to achieve fusion power production, but several challenges must be overcome to develop an IFE pilot plant or deploy commercial IFE systems. These challenges are both theoretical and technical, encompassing a deeper understanding of the underlying physical phenomena and the development of new technologies and materials. One of the needs is to develop mathematical models to describe IFE systems and numerical tools to simulate them. This paper contributes to this endeavor by presenting a new OpenFOAM solver for IFE systems, focusing on gas dynamics in their chambers. The analysis and development of chamber designs will play a significant role in the transition from single-shot experiments to high-repetition rates, as there is a need to protect the chamber walls from the intense radiation fields produced by fusion reactions. A promising design option, normally referred to as thick wall chamber design, consists in using lithium or molten salt jet arrays within the chamber. A critical phenomenon is the venting of high-pressure gases from the center to the external part of the chamber, passing through the blanket array. This process involves the propagation and attenuation of strong pressure waves, requiring suitable modeling approaches for compressible fluid-dynamics. The solver proposed in this work implements a multi-material hydrodynamics model tailored to accurately describe the non-linear propagation of pressure waves while avoiding numerical oscillation issues typical of high-velocity compressible simulation. This solver is verified against numerical test cases, validated against experimental data, and applied to the analysis of the High-Yield Lithium-Injection Fusion-Energy (HYLIFE-I) concept. The relevance of this paper is threefold. Firstly, it contributes to developing and testing modeling approaches for compressible fluid-dynamics phenomena, with specific focus on the new and unexplored topic of IFE thick-liquid-wall blanket modeling. Secondly, it marks one of the first applications of the OpenFOAM library in the research field of IFE systems. Finally, the investigated problem is of practical interest for IFE developers, as it provides useful indications about relevant phenomena in pressure wave propagation in the chamber of these systems.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2023

COUPLING SMOOTHED PARTICLE HYDRODYNAMICS WITH FINITE ELEMENT METHOD TO SIMULATE RESIDUAL STRESSES FROM FRICTION STIR PROCESSING

Friction stir processing (FSP) is a solid-state material processing technique that locally modifies the microstructure but also induces undesirable residual stresses. A robust numerical model for the FSP can help in mitigating these residual stresses. Heat source models within a finite element method (FEM) framework suffer from inaccuracies. In contrast, smoothed particle hydrodynamics (SPH) model that explicitly captures the material flow near the tool and the associated heat generation are accurate. However, the computational expense of SPH simulations can be prohibitive. In this work, we propose a coupled SPH-FEM framework. SPH is used to model the heat generation accurately near the tool and which is then inserted into to the FEM model as a heat source. To verify this proposed coupling approach, a test case is set up with typical FSP conditions and it is modeled in both SPH and SPH-FEM. The temperatures profiles were compared after the simulations have reached steady-state temperatures. The similarity of the temperature profiles from SPH-FEA and SPH validated the proposed coupling approach. This proposed approach achieves the accuracy of the SPH method while potentially retaining the low computational expense of FEM.

smoothed particle hydrodynamics, Finite Element Me↗
DOE OSTI2022

New data-driven approach to bridging power system protection gaps with deep learning

Protection is a critical function in power systems to avoid equipment damage, maintain personnel safety, and support system reliability. However, current protective relay technology cannot adequately protect equipment and personnel from effects of some events; these deficiencies are termed protection gaps. In this paper, a data-driven approach is proposed to complement traditional protection technology and distinguish fault conditions from transients caused by normal operations. A combined convolutional neural network and long short-term memory (CNN-LSTM) network is implemented to achieve data translation invariance and capture the temporal correlation of the time-series input data. As a result, the data-driven method can accurately detect system faults despite variation and noise in the input data. In addition, using the CNN-LSTM--based method avoids the complicated, manual feature extraction procedure required by many traditional data-driven methods. The effectiveness of the proposed approach is tested on two kinds of protection gaps: high-impedance faults and transformer inter-turn faults. Lastly, a transfer learning method is also proposed to address the common issue of data-driven methods for which real-world training data are scarce. Extensive study results demonstrate that the proposed approach can accurately bridge power system protection gaps.

42 ENGINEERING↗
DOE OSTI2023

Range wide genetic differentiation in the bull kelp Nereocystis luetkeana with a seascape genetic focus on the Salish Sea

Introduction: In temperate regions, one of the most critical determinants of present range-wide genetic diversity was the Pleistocene climate oscillations, the most recent one created by the last glacial maximum (LGM). This study aimed to describe N. luetkeana genetic structure across its entire range (Alaska to California) and test different models of population connectivity within the Salish Sea. This region was colonized after the LGM and has been under increased disturbance in recent decades. Methods: We utilized microsatellite markers to study N. luetkeana genetic diversity at 53 sites across its range. Using higher sampling density in the Salish Sea, we employed a seascape genetics approach and tested isolation by hydrodynamic transport and environment models. Results: At the species distribution scale, we found four main groups of genetic co-ancestry, Alaska; Washington with Vancouver Island’s outer coast and Juan de Fuca Strait; Washington’s inner Salish Sea; and Oregon with California. The highest allelic richness (AR) levels were found in California, near the trailing range edge, although AR was also high in Alaska. The inner Salish Sea region had the poorest diversity across the species distribution. Nevertheless, a pattern of isolation by hydrodynamic transport and environment was supported in this region. Discussion: The levels of allelic, private allele richness and genetic differentiation suggest that during the LGM, bull kelp had both northern and southern glacial refugia in the Prince of Wales Island-Haida Gwaii region and Central California, respectively. Genetic diversity in Northern California sites seems resilient to recent disturbances, whereas the low levels of genetic diversity in the inner Salish Sea are concerning.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Balanced k -means clustering on an adiabatic quantum computer

Adiabatic quantum computers are a promising platform for efficiently solving challenging optimization problems. Therefore, many are interested in using these computers to train computationally expensive machine learning models. We present a quantum approach to solving the balanced k-means clustering training problem on the D-Wave 2000Q adiabatic quantum computer. In order to do this, we formulate the training problem as a quadratic unconstrained binary optimization (QUBO) problem. Unlike existing classical algorithms, our QUBO formulation targets the global solution to the balanced k-means model. We test our approach on a number of small problems and observe that despite the theoretical benefits of the QUBO formulation, the clustering solution obtained by a modern quantum computer is usually inferior to the solution obtained by the best classical clustering algorithms. Nevertheless, the solutions provided by the quantum computer do exhibit some promising characteristics. We also perform a scalability study to estimate the run time of our approach on large problems using future quantum hardware. Finally, as a final proof of concept, we used the quantum approach to cluster random subsets of the Iris benchmark data set.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Eddy covariance towers as sentinels of abnormal radioactive material releases

Ensuring accurate detection and attribution of abnormal releases of radioactive material is critical for protecting human health and safety. Most commonly, such detection is accomplished via active monitoring approaches involving the collection of physical samples. Further, this is labor intensive and limits the temporal and spatial resolution of any detected events to a relatively coarse level. As an alternative first step towards passive monitoring, we developed an approach using eddy flux tower data records to identify signals from a known abnormal release and quantify the extent to which that signal also occurs at other times in the data record. Through two case studies, one of which targeted the Fukushima nuclear disaster and the other targeting an abnormal release event at a radioisotope production facility in Fleurus, Belgium, we tested our approach and identified several potential heretofore unidentified abnormal events that were consistent with atmospheric circulation patterns and/or wind direction from known release sites. Because our approach is relatively simple and is resistant to systematic errors in the observational record, it has broad applicability beyond specific constituents and ecosystem types to identify a wide variety of limited-duration anomalies in flux tower data to ensure human health and industrial safety.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Smart technologies enable homes to be efficient and interactive with the grid

Oak Ridge National Laboratory researchers compare two different approaches to test how advanced, energy-efficient building technologies such as smart thermostats, heat pump water heaters, and advanced heat pump HVAC (heating, ventilation and air conditioning) can be optimized within a home and connected at a neighborhood-scale load to a community microgrid in the Alabama Power Smart Neighborhood located in Hoover. Working with Southern Company and Alabama Power, ORNL researchers are pioneering that future where smart homes and smart neighborhoods can benefit both homeowners and utilities, by reducing energy consumption by 44% and peak demand by 34%.This project is one of two neighborhoods in the U.S Department of Energy’s (DOE’s) Connected Neighborhood project, supported by Building Technologies Office , where ORNL researchers leverages DOE investment in micro-grids and responsive, flexible building loads research to improve grid reliability – a goal of DOE’s Grid-interactive Efficient Buildings (GEB) Initiative. Researchers control the neighborhood and microgrid to enable utilities achieve their desired load and cost profiles while ensuring the comfort of homeowners in the Smart Neighborhood. This transactive control approach maximizes the utilization of technical resources of the microgrid and controllable loads, while reducing costs for both the homeowners and Alabama Power. These tests partially seek to determine a more precise range of tolerance with respect to occupant comfort as researchers work to facilitate customer acceptance and perception of new building technologies that enable energy savings.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

SUHMO: an adaptive mesh refinement SUbglacial Hydrology MOdel v1.0

Abstract. Water flowing under ice sheets and glaciers can have a strong influence on ice dynamics, particularly through pressure changes, suggesting that a comprehensive ice sheet model should include the effect of basal hydrology. Modeling subglacial hydrology remains a challenge, however, mainly due to the range of spatial and temporal scales involved – from subglacial channels to vast subglacial lakes. Additionally, networks of subglacial drainage channels dynamically evolve over time. To address some of these challenges, we have developed an adaptive mesh refinement (AMR) model based on the Chombo software framework. We extend the model proposed by Sommers et al. (2018) with a small but significant change to accommodate the transition from unresolved to resolved flow features. We handle the strong nonlinearities present in the equations by resorting to an efficient nonlinear full approximation scheme multigrid (FAS-MG) algorithm. We outline the details of the algorithm and present convergence analysis results demonstrating its good performance. Additionally, we present results validating our approach, using test cases from the Subglacial Hydrology Model Intercomparison Project (SHMIP) (de Fleurian et al., 2018). We finish by presenting a more complex, 100 km-by-100 km synthetic test case with peaks and valleys that we use to investigate the effective pressure distribution as the number of AMR levels increases. These preliminary results suggest that a minimum spatial resolution is needed to properly capture channel features, but additional work is required to precisely quantify this and its impact on accurately modeling the coupled ice sheet–hydrology system. The efficiency of our approach, relying on localized refinement, is also demonstrated. Future work will include coupling the SUbglacial Hydrology MOdel (SUHMO) with the BISICLES AMR ice sheet model (Cornford et al., 2013), both built on the same numerical framework.

58 GEOSCIENCES↗
DOE OSTI2023

Defining the Minimal Set of Microbial Genes Required for Valorization of Lignin Biomass (Final Report)

Project Goals: Lignin is the second most abundant biopolymer on earth and represents a critically underutilized biomass resource for hydrocarbon feedstocks. Despite substantial effort, there is still no efficient process to convert lignin to useable carbon-based platform chemicals and materials. The goal of this project is identify a minimal set of microbial enzymes necessary for lignin breakdown and sufficient for the synthesis of valuable chemical intermediates from lignin isolated as a byproduct of lignocellulosic ethanol production. These genes will be then used to engineer functional whole cell biocatalysts for tunable lignin metabolism. To date, although a number of enzymes have been associated with lignin degradation, most have been tested in isolation (as individual enzymes) and on drastically different substrates -- often dyes that are not related to lignin. In contrast, lignin utilization in nature likely occurs by microbial consortia with multiple enzymes acting synergistically. We propose to examine two separate stages of lignin breakdown carried out by the microbes that do it best: (1) early breakdown of native polymeric lignin into soluble fragments by a set of sequenced wood-rotting fungal species, and (2) downstream metabolism of these soluble lignin fragments to useful chemical intermediates by a panel of sequenced soil saprophytes. Our approach involves testing sets of genes that will be assayed combinatorially in the context of a heterologous expression host. The resulting engineered strains will be systematically assayed using soluble lignin fragments, synthetic defined polymeric lignin, and finally lignin directly sourced from lignocellulosic processing streams. In addition to resulting in a functional whole cell biocatalyst for lignin utilization, we anticipate that this approach will allow us to address key unanswered questions about lignin metabolism in nature, including: (1) Why does the Trametes versicolor genome contain 25 different class II peroxidases? (2) What is the role of laccases in lignin metabolism? Why do some aggressive lignin degraders have many laccases (e.g. >7 in T. versicolor) while others have none (e.g. P. chrysosporium)? (3) How is peroxide provided in a controlled manner to drive peroxidase activity without causing the enzyme inhibition that is so often observed in vitro? (4) What strategies do microbial lignin degraders use to avoid the problem of repolymerization during active lignin degradation? and (5) Can microbial lignin metabolism be diverted for high level production of defined aromatics? A final critical question is whether combining key minimal sets of enzymes from a wide range of organisms will result in engineered strains capable of highly efficient, streamlined pathways for lignin utilization that can be tuned for a specific carbon output. This effort will leverage DOE investments in microbial genome sequencing, and secure a critical channel for lignin biomass utilization that will also help to render lignocellulosic a viable feedstock for the production of renewable liquid biofuels.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2020

Measuring Thickness-Dependent Relative Light Yield and Detection Efficiency of Scintillator Screens

Digital camera-based neutron imaging systems consisting of a neutron scintillator screen optically coupled to a digital camera are the most common digital neutron imaging system used in the neutron imaging community and are available at any state-of-the-art imaging facility world-wide. Neutron scintillator screens are the integral component of these imaging system that directly interacts with the neutron beam and dictates the neutron capture efficiency and image quality limitations of the imaging system. This work describes a novel approach for testing neutron scintillators that provides a simple and efficient way to measure relative light yield and detection efficiency over a range of scintillator thicknesses using a single scintillator screen and only a few radiographs. Additionally, two methods for correlating the screen thickness to the measured data were implemented and compared. An example 6LiF:ZnS scintillator screen with nominal thicknesses ranging from 0–300 μm was used to demonstrate this approach. The multi-thickness screen and image and data processing methods are not exclusive to neutron scintillator screens but could be applied to X-ray imaging as well. This approach has the potential to benefit the entire radiographic imaging community by offering an efficient path forward for manufacturers to develop higher-performance scintillators and for imaging facilities and service providers to determine the optimal screen parameters for their particular beam and imaging system.

42 ENGINEERING↗
DOE OSTI2021

Organic contamination detection for isotopic analysis of water by laser spectroscopy

Hydrogen and oxygen stable isotope ratios (δ 2 H, δ 17 O, and δ 18 O values) are commonly used tracers of water. These ratios can be measured by isotope ratio infrared spectroscopy (IRIS). However, IRIS approaches are prone to errors induced by organic compounds present in plant, soil, and natural water samples. A novel approach using 17 O-excess values has shown promise for flagging spectrally contaminated plant samples during IRIS analysis. A systematic assessment of this flagging system is needed to prove it useful. Errors induced by methanol and ethanol water mixtures on measured IRIS and isotope ratio mass spectrometry (IRMS) results were evaluated. For IRIS analyses both liquid- and vapour-mode (via direct vapour equilibration) methods are used. The δ 2 H, δ 17 O, and δ 18 O values were measured and compared with known reference values to determine the errors induced by methanol and ethanol contamination. In addition, the 17 O-excess contamination detection approach was tested. This is a post-processing detection tool for both liquid and vapour IRIS triple-isotope analyses, utilizing calculated 17 O-excess values to flag contaminated samples. Organic contamination induced significant errors in IRIS results, not seen in IRMS results. Methanol caused larger errors than ethanol. Results from vapour-IRIS analyses had larger errors than those from liquid-IRIS analyses. The 17 O-excess approach identified methanol driven error in liquid- and vapour-mode IRIS samples at levels where isotope results became unacceptably erroneous. For ethanol contaminated samples, a mix of erroneous and correct flagging occurred with the 17 O-excess method. Here our results indicate that methanol is the more problematic contaminant for data corruption. The 17 O-excess method was therefore useful for data quality control. Organic contamination caused significant errors in IRIS stable isotope results. These errors were larger during vapour analyses than during liquid IRIS analyses, and larger for methanol than ethanol contamination. The 17 O-excess method is highly sensitive for detecting narrowband (methanol) contamination error in vapour and liquid analysis modes in IRIS.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2021

Bridging Power System Protection Gaps with Data-driven Approaches

Protection is a critical function in power systems to avoid equipment damage, maintain personnel safety, and support system reliability. However, current protective relay technology cannot adequately protect equipment and personnel from effects of some events; these deficiencies are termed protection gaps. In this research, a data-driven approach is proposed to complement traditional protection technology and distinguish fault conditions from transients caused by normal operations. A convolutional neural network (CNN) based fault detection approach is implemented to achieve data translation invariance of the time-series input data. As a result, the data-driven method can accurately detect system faults despite variation and noise in the input data. In addition, using the CNN–based method avoids the complicated manual feature extraction procedure required by many traditional data-driven methods. The effectiveness of the proposed approach is tested on four kinds of protection gaps: high impedance faults, transformer/generator inter-turn faults, distribution system PV circuit faults, and the mis-operation situations of Zone 3 line protection relays operating under system stress. Finally, a transfer learning method is also proposed to address the common issue of data-driven methods for which real-world training data are scarce. Extensive study results demonstrate that the proposed approach can accurately bridge power system protection gaps.

24 POWER TRANSMISSION AND DISTRIBUTION↗
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↗