Search NASA⌕ Search

SEARCH · Search NASA

Results for “Graph Methods”

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 811 records · Page 45
All sourcesNASA NTRSDOE OSTI
DOE OSTI2013

A Flow-Channel Analysis for the Mars Hopper

The Mars Hopper is an exploratory vehicle designed to fly on Mars using carbon dioxide from the Martian atmosphere as a rocket propellant. The propellent gasses are thermally heated while traversing a radioisotope ther- mal rocket (RTR) engine’s core. This core is comprised of a radioisotope surrounded by a heat capacitive material interspersed with tubes for the propellant to travel through. These tubes, or flow channels, can be manu- factured in various cross-sectional shapes such as a special four-point star or the traditional circle. Analytical heat transfer and computational fluid dynamics (CFD) anal- yses were performed using flow channels with either a circle or a star cross- sectional shape. The nominal total inlet pressure was specified at 2,805,000 Pa; and the outlet pressure was set to 2,785,000 Pa. The CO2 inlet tem- perature was 300 K; and the channel wall was 1200 K. The steady-state CFD simulations computed the smooth-walled star shape’s outlet temper- ature to be 959 K on the finest mesh. The smooth-walled circle’s outlet temperature was 902 K. A circle with a surface roughness specification at 0.01 mm gave 946 K and at 0.1 mm yielded 989 K. The The effects of a slightly varied inlet pressure were also examined. The analytical calculations were based on the mass flow rates computed in the CFD simulations and provided significantly higher outlet temperature results while displaying the same comparison trends. Research relating to the flow channel heat transfer studies was also done. Mathematical methods to geometrically match the cross-sectional areas of the circle and star, along with a square and equilateral triangle, were derived. A Wolfram Mathematica 8 module was programmed to analyze CFD results using Richardson Extrapolation and calculate the grid convergence index (GCI). A Mathematica notebook, also composed, computes and graphs the bulk mean temperature along a flow channel’s length while the user dynam- ically provides the input variables, allowing their effects on the temperature to be more easily observed.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2023

Scalable Incremental Checkpointing using GPU-Accelerated De-Duplication

Writing large amounts of data concurrently to stable storage is a typical I/O pattern of many HPC workflows. This pattern introduces high I/O overheads and results in increased storage space utilization especially for workflows that need to capture the evolution of data structures with high frequency as checkpoints. In this context, many applications, such as graph pattern matching, perform sparse updates to large data structures between checkpoints. For these applications, incremental checkpointing techniques that save only the differences from one checkpoint to another can dramatically reduce the checkpoint sizes, I/O bottlenecks, and storage space utilization. However, such techniques are not without challenges: it is non-trivial to transparently determine what data has changed since a previous checkpoint and assemble the differences in a compact fashion that does not result in excessive metadata. State-of-art data reduction techniques (e.g., compression and de-duplication) have significant limitations when applied to modern HPC applications that leverage GPUs: slow at detecting the differences, generate a large amount of metadata to keep track of the differences, and ignore crucial spatiotemporal checkpoint data redundancy. This paper addresses these challenges by proposing a Merkle tree-based incremental checkpointing method to exploit GPUs' high memory bandwidth and massive parallelism. Experimental results at scale show a significant reduction of the I/O overhead and space utilization of checkpointing compared with state-of-the-art incremental checkpointing and compression techniques.

Tan, Nigel↗
DOE OSTI2020

A conservative, consistent, and scalable meshfree mimetic method

Mimetic methods discretize divergence by restricting the Gauss theorem to mesh cells. Because point clouds lack such geometric entities, construction of a compatible meshfree divergence remains a challenge. In this work, we define an abstract Meshfree Mimetic Divergence (MMD) operator on point clouds by contraction of field and virtual face moments. This MMD satisfies a discrete divergence theorem, provides a discrete local conservation principle, and is first-order accurate. We consider two MMD instantiations. The first one assumes a background mesh and uses generalized moving least squares (GMLS) to obtain the necessary field and face moments. This MMD instance is appropriate for settings where a mesh is available but its quality is insufficient for a robust and accurate mesh-based discretization. The second MMD operator retains the GMLS field moments but defines virtual face moments using computationally efficient weighted graph-Laplacian equations. This MMD instance does not require a background grid and is appropriate for applications where mesh generation creates a computational bottleneck. It allows one to trade an expensive mesh generation problem for a scalable algebraic one, without sacrificing compatibility with the divergence operator. We demonstrate the approach by using the MMD operator to obtain a virtual finite-volume discretization of conservation laws on point clouds. Finally, numerical results in the paper confirm the mimetic properties of the method and show that it behaves similarly to standard finite volume methods.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2025

Geometric GNNs for charged particle tracking at GlueX

Nuclear physics experiments are aimed at uncovering the fundamental building blocks of matter. The experiments involve high-energy collisions that produce complex events with many particle trajectories. Tracking charged particles resulting from collisions in the presence of a strong magnetic field is critical to enable the reconstruction of particle trajectories and precise determination of interactions. It is traditionally achieved through combinatorial approaches that scale worse than linearly as the number of hits grows. Since particle hit data naturally form a point cloud and can be structured as graphs, graph neural networks (GNNs) emerge as an intuitive and effective choice for this task. In this study, we evaluate the GNN model for track finding on the data from the GlueX experiment at Jefferson Lab. We use simulation data to train the model and test on both simulation and real GlueX measurements. We demonstrate that GNN-based track finding outperforms the currently used traditional method at GlueX in terms of segment-based efficiency at a fixed purity while providing faster inferences. We show that the GNN model can achieve significant speedup by processing multiple events in batches, which exploits the parallel computation capability of graphical processing units (GPUs). Finally, we compare the GNN implementation on GPU and field-programmable gate array and describe the trade-off.

batched GNN pipeline↗
DOE OSTI2026

Energy-Screened Many-Body Expansion for Protein–Ligand Interactions: Examining Convergence for Metalloenzymes Through Seven–Body Interactions

Fragment-based quantum chemistry is a powerful strategy for calculating protein−ligand interaction energies using quantum chemistry methods. Rigorous convergence often requires hundreds of atoms in the protein binding-site model, especially if that model is constructed using distance-based criteria to select amino acid residues, while three- and four-body calculations exhibit instability related to combinatorial proliferation in the number of subsystem calculations. Here, we report an energy-based screening protocol for the many-body expansion applied to protein−ligand interactions, implemented in the open-source FRAGME∩T code. Using a combination of aggressive screening based on semiempirical quantum chemistry, with an improved graph-theoretical algorithm to eliminate unimportant subsystems, we are able to perform n-body calculations up to n = 7 using density functional theory in triple-ζ basis sets. Distance cutoffs further reduce the cost without compromising accuracy. Rapid and stable convergence of the many-body expansion is obtained by n = 4, for a pair of metalloenzymes in which a divalent ion coordinates directly to the ligand. As compared to previous results that relied solely on distance cutoffs, oscillations in the n-body corrections are reduced or eliminated, although residual errors remain in one case. This work demonstrates that benchmark-quality protein−ligand interaction energies can be systematically converged using a method with excellent parallel efficiency and scalability.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2019

An Agile Design-to-Simulation Workflow Using a New Conforming Moving Least Squares Method

This report summarizes the accomplishments and challenges of a two year LDRD effort focused on improving design-to-simulation agility. The central bottleneck in most solid mechanics simulations is the process of taking CAD geometry and creating a discretization of suitable quality, i.e., the "meshing" effort. This report revisits meshfree methods and documents some key advancements that allow their use on problems with complex geometries, low quality meshes, nearly incompressible materials or that involve fracture. The resulting capability was demonstrated to be an effective part of an agile simulation process by enabling rapid discretization techniques without increasing the time to obtain a solution of a given accuracy. The first enhancement addressed boundary-related challenges associated with meshfree methods. When using point clouds and Euclidean metrics to construct approximation spaces, the boundary information is lost, which results in low accuracy solutions for non-convex geometries and mate rial interfaces. This also complicates the application of essential boundary conditions. The solution involved the development of conforming window functions which use graph and boundary information to directly incorporate boundaries into the approximation space.

42 ENGINEERING↗
DOE OSTI2020

ExpoKids: An R-based tool for characterizing aggregate chemical exposure during childhood

Background: Aggregate exposure, the combined exposures to a single chemical from all pathways, is a critical children’s health issue. Objective: The primary objective is to develop a tool to illustrate potential differences in aggregate exposure at various childhood lifestages and the adult lifestage. Methods: We developed ExpoKids (an R-based tool) using oral exposure estimates across lifestages generated by US EPA’s Exposure Factors Interactive Resource for Scenarios Tool (ExpoFIRST). Results: ExpoKids is applied to illustrate aggregate oral exposure, for ten media, as average daily doses (ADD) and lifetime average daily doses (LADD) in five graphs organized across seven postnatal childhood lifestages and the adult lifestage. This data visualization tool conveys ExpoFIRST findings, from available exposure data, to highlight the relative contributions of media and lifestages to chemical exposure. To evaluate the effectiveness of ExpoKids, three chemical case examples (di[2-ethylhexyl] phthalate [DEHP], manganese, and endosulfan) were explored. Data available from the published literature and databases for each case example were used to explore research questions regarding media and lifestage contributions to aggregate exposure. Significance: These illustrative case examples demonstrate ExpoKids’ versatile application to explore a diverse set of children’s health risk assessment and management questions by visually depicting specific media and lifestage contributions to aggregate exposure.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Enhancing stability, magnetic anisotropy, and coercivity of manganese aluminum: Machine learning, ab initio , and micromagnetic modeling

The binary manganese aluminum (MnAl) alloy with L⁢1 0 crystal structure is a promising rare earth (RE) element-free permanent magnetic material because of its exceptional magnetic properties. However, experimentally synthesizing it in a stable bulk form is extremely challenging. Here, in this study, an alternative method of stabilizing the material, a pathway for experimental synthesis and validation, is proposed and theoretically verified. This is done by partially substituting Mn and Al sites with Fe and Ni and identifying its enhanced phase stability, saturation magnetization density, magnetic anisotropy, and coercivity from density functional theory (DFT), machine learning (ML) crystal graph convolution neural network (CGCNN), and micro-magnetic modeling. When considering a fixed 50% Ni, the magnetic anisotropy increases with the increasing Fe content but decreases the formation energy. The calculated formation energies, elastic constants, and phonon frequencies demonstrate that the binary and quaternary compositions are stable. Most importantly, in 50% Fe and Ni-substituted-equiatomic phase, magnetic anisotropy constants and saturation magnetization density increase by 56% and 23% as compared to the MnAl. Further, the coercivity of the equiatomic phase predicted with micro-magnetic modeling is higher by 17% than the parent compound.

Bhandari, Churna [Ames National Laboratory, and Io↗
DOE OSTI2015

SU-E-T-250: Determining VMAT Machine Limitations of An Elekta Linear Accelerator with Agility MLC for Accurate Modeling in RayStation and Robust Delivery

Purpose: To implement VMAT in RayStation with the Elekta Synergy linac with the new Agility MLC, and to utilize the same vendor softwares to determine the optimum Elekta VMAT machine parameters in RayStation for accurate modeling and robust delivery. Methods: iCOMCat is utilized to create various beam patterns with user defined dose rate, gantry, MLC and jaw speed for each control point. The accuracy and stability of the output and beam profile are qualified for each isolated functional component of VMAT delivery using ion chamber and Profiler2 with isocentric mounting fixture. Service graphing on linac console is used to verify the mechanical motion accuracy. The determined optimum Elekta VMAT machine parameters were configured in RayStation v4.5.1. To evaluate the system overall performance, TG-119 test cases and nine retrospective VMAT patients were planned on RayStation, and validated using both ArcCHECK (with plug and ion chamber) and MapCHECK2. Results: Machine output and profile varies <0.3% when only variable is dose rate (35MU/min-600MU/min). <0.9% output and <0.3% profile variation are observed with additional gantry motion (0.53deg/s–5.8deg/s both directions). The output and profile variation are still <1% with additional slow leaf motion (<1.5cm/s both direction). However, the profile becomes less symmetric, and >1.5% output and 7% profile deviation is seen with >2.5cm/s leaf motion. All clinical cases achieved comparable plan quality as treated IMRT plans. The gamma passing rate is 99.5±0.5% on ArcCheck (<3% iso center dose deviation) and 99.1±0.8% on MapCheck2 using 3%/3mm gamma (10% lower threshold). Mechanical motion accuracy in all VMAT deliveries is <1°/1mm. Conclusion: Accurate RayStation modeling and robust VMAT delivery is achievable on Elekta Agility for <2.5cm/s leaf motion and full range of dose rate and gantry speed determined by the same vendor softwares. Our TG-119 and patient results have provided us with the confidence to use VMAT clinically.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2024

Data-Driven Unit Commitment Refinement - a Scalable Approach for Complex Modern Power Grids

Integration of renewable generation, which is often intermittent and decentralized, substantially increases the stochasticity and complexity of power grid operations. Future power systems planning will require significant computational capability to evaluate balance between demand and supply under varying conditions, both temporally and spatially. The standard approach for generation unit commitment is to use mixed-integer linear programming to find the optimal generation schedule considering ramping and generator constraints. In the future grid this poses computational scalability challenges because generation and demand are not known with certainty due to stochasticity in weather and complexity of the grid. To address this challenge, we present a data-driven unit commitment approach that can efficiently include stochastic weather impacts and contingency considerations to improve unit commitment. Our approach uses graph-based data analytics techniques on solutions to the security constrained (and possibly stochastic) economic dispatch problem to identify potential improvements to a given unit commitment. Recent breakthroughs in fully-parallel stochastic economic dispatch software allow this approach to be scalably deployed. Simulations on synthetic South Carolina and Texas grids show this method can improve grid reliability with security constraints over a set of contingencies, while also meaningfully lowering total generation cost.

Holt, Timothy↗
DOE OSTI2013

Synthesis and characterization of aluminum–boron co-doped ZnO nanostructures

Graphical abstract: In this paper, we have reported the development of aluminum boron co-doped ZnO (AZB) nanostructures deposited by sol–gel method using spin coating technique. The structure of AZB nanostructure films has been found to exhibit the hexagonal wurtzite structure. The shape of nanostructures has been changed from seed structure to tetra-pods, tetra-pods to nanorods and finally nanorods to nanofiber with variation in Al concentration. The structural, electrical and optical properties of AZB nanostructures are tuned with shape and size of the nanostructures. The effect of Al concentration on the resistivity (ρ), carrier concentration (n) and mobility (μ) of nanostructure films is shown in graph below. A minimum resistivity of 6.8 × 10{sup −4} Ω cm is obtained in AZB films at doping concentration of B 0.6 at.% and Al 0.4 at.% with a sheet resistance of 24 Ω/□ and transmittance of ∼88% for nanorods structure. These nanostructures could be applicable for a various nano-regime devices such as photovolatics, gas sensing and field emission device. Display Omitted Highlights: ► Synthesis of Al and B co-doped ZnO (AZB) nanostructures. ► Minimum resistivity (ρ) of 6.8 × 10{sup −4} Ω cm in AZB films. ► Minimum sheet resistance (R{sub s}) 24 Ω/□ in nanorods (NRs). ► Maximum transmittance ∼88% in NRs. ► Application in nano-electronic devices. -- Abstract: In this paper, we have reported the development of aluminum boron co-doped ZnO (AZB) nanostructures deposited by sol–gel method using spin coating technique. The structure of AZB nanostructure films has been found to exhibit the hexagonal wurtzite structure. The shape of AZB nanostructures has changed from seed structure to tetra-pods, tetra-pods to nanorods and finally to nanofibers with increase in aluminum concentration. The structural, electrical and optical properties of AZB films are tuned with shape and size of the nanostructures. These AZB nanostructures could be applicable for various nano-regime devices such as photovoltaic cells, gas sensors and field emission devices.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2016

IMRT QA: Selecting gamma criteria based on error detection sensitivity

Purpose: The gamma comparison is widely used to evaluate the agreement between measurements and treatment planning system calculations in patient-specific intensity modulated radiation therapy (IMRT) quality assurance (QA). However, recent publications have raised concerns about the lack of sensitivity when employing commonly used gamma criteria. Understanding the actual sensitivity of a wide range of different gamma criteria may allow the definition of more meaningful gamma criteria and tolerance limits in IMRT QA. We present a method that allows the quantitative determination of gamma criteria sensitivity to induced errors which can be applied to any unique combination of device, delivery technique, and software utilized in a specific clinic. Methods: A total of 21 DMLC IMRT QA measurements (ArcCHECK®, Sun Nuclear) were compared to QA plan calculations with induced errors. Three scenarios were studied: MU errors, multi-leaf collimator (MLC) errors, and the sensitivity of the gamma comparison to changes in penumbra width. Gamma comparisons were performed between measurements and error-induced calculations using a wide range of gamma criteria, resulting in a total of over 20 000 gamma comparisons. Gamma passing rates for each error class and case were graphed against error magnitude to create error curves in order to represent the range of missed errors in routine IMRT QA using 36 different gamma criteria. Results: This study demonstrates that systematic errors and case-specific errors can be detected by the error curve analysis. Depending on the location of the error curve peak (e.g., not centered about zero), 3%/3 mm threshold = 10% at 90% pixels passing may miss errors as large as 15% MU errors and ±1 cm random MLC errors for some cases. As the dose threshold parameter was increased for a given %Diff/distance-to-agreement (DTA) setting, error sensitivity was increased by up to a factor of two for select cases. This increased sensitivity with increasing dose threshold was consistent across all studied combinations of %Diff/DTA. Criteria such as 2%/3 mm and 3%/2 mm with a 50% threshold at 90% pixels passing are shown to be more appropriately sensitive without being overly strict. However, a broadening of the penumbra by as much as 5 mm in the beam configuration was difficult to detect with commonly used criteria, as well as with the previously mentioned criteria utilizing a threshold of 50%. Conclusions: We have introduced the error curve method, an analysis technique which allows the quantitative determination of gamma criteria sensitivity to induced errors. The application of the error curve method using DMLC IMRT plans measured on the ArcCHECK® device demonstrated that large errors can potentially be missed in IMRT QA with commonly used gamma criteria (e.g., 3%/3 mm, threshold = 10%, 90% pixels passing). Additionally, increasing the dose threshold value can offer dramatic increases in error sensitivity. This approach may allow the selection of more meaningful gamma criteria for IMRT QA and is straightforward to apply to other combinations of devices and treatment techniques.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2016

SU-F-I-59: Quality Assurance Phantom for PET/CT Alignment and Attenuation Correction

Purpose: This study utilizes a commercial PET/CT phantom to investigate two specific properties of a PET/CT system: the alignment accuracy of PET images with those from CT used for attenuation correction and the accuracy of this correction in PET images. Methods: A commercial PET/CT phantom consisting of three aluminum rods, two long central cylinders containing uniform activity, and attenuating materials such as air, water, bone and iodine contrast was scanned using a standard PET/CT protocol. Images reconstructed with 2 mm slice thickness and a 512 by 512 matrix were obtained. The center of each aluminum rod in the PET and CT images was compared to evaluate alignment accuracy. ROIs were drawn on transaxial images of the central rods at each section of attenuating material to determine the corrected activity (in BQML). BQML values were graphed as a function of slice number to provide a visual representation of the attenuation-correction throughout the whole phantom. Results: Alignment accuracy is high between the PET and CT images. The maximum deviation between the two in the axial plane is less than 1.5 mm, which is less than the width of a single pixel. BQML values measured along different sections of the large central rods are similar among the different attenuating materials except iodine contrast. Deviation of BQML values in the air and bone sections from the water section is less than 1%. Conclusion: Accurate alignment of PET and CT images is critical to ensure proper calculation and application of CT-based attenuation correction. This study presents a simple and quick method to evaluate the two with a single acquisition. As the phantom also includes spheres of increasing diameter, this could serve as a straightforward means to annually evaluate the status of a modern PET/CT system.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2015

De Novo Sequencing of Peptides from Top-Down Tandem Mass Spectra

De novo sequencing of proteins and peptides is one of the most important problems in mass spectrometry-driven proteomics. A variety of methods have been developed to accomplish this task from a set of bottom-up tandem (MS/MS) mass spectra. However, a more recently emerged top-down technology, now gaining more and more popularity, opens new perspectives for protein analysis and characterization, implying a need in efficient algorithms for processing this kind of MS/MS data. Here we describe a method that allows to retrieve from a set of top-down MS/MS spectra long and accurate sequence fragments of the proteins contained in a sample. To this end, we outline a strategy for generating high-quality sequence tags from top-down spectra, and introduce the concept of a T-Bruijn graph by adapting to the case of tags the notion of an A-Bruijn graph widely used in genomics. The output of the proposed approach represents the set of amino acid strings spelled out by optimal paths in the connected components of a T-Bruijn graph. We illustrate its performance on top-down datasets acquired from carbonic anhydrase 2 (CAH2) and the Fab region of alemtuzumab.

Environmental Molecular Sciences Laboratory↗
DOE OSTI2023

Structural inference of networked dynamical systems with universal differential equations

Networked dynamical systems are common throughout science in engineering; e.g., biological networks, reaction networks, power systems, and the like. For many such systems, nonlinearity drives populations of identical (or near-identical) units to exhibit a wide range of nontrivial behaviors, such as the emergence of coherent structures (e.g., waves and patterns) or otherwise notable dynamics (e.g., synchrony and chaos). Here, we seek to infer (i) the intrinsic physics of a base unit of a population, (ii) the underlying graphical structure shared between units, and (iii) the coupling physics of a given networked dynamical system given observations of nodal states. These tasks are formulated around the notion of the Universal Differential Equation, whereby unknown dynamical systems can be approximated with neural networks, mathematical terms known a priori (albeit with unknown parameterizations), or combinations of the two. We demonstrate the value of these inference tasks by investigating not only future state predictions but also the inference of system behavior on varied network topologies. The effectiveness and utility of these methods are shown with their application to canonical networked nonlinear coupled oscillators.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Deep graph representations embed network information for robust disease marker identification

We report that the accurate disease diagnosis and prognosis based on omics data rely on the effective identification of robust prognostic and diagnostic markers that reflect the states of the biological processes underlying the disease pathogenesis and progression. In this article, we present GCNCC, a Graph Convolutional Network-based approach for Clustering and Classification, that can identify highly effective and robust network-based disease markers. Based on a geometric deep learning framework, GCNCC learns deep network representations by integrating gene expression data with protein interaction data to identify highly reproducible markers with consistently accurate prediction performance across independent datasets possibly from different platforms. GCNCC identifies these markers by clustering the nodes in the protein interaction network based on latent similarity measures learned by the deep architecture of a graph convolutional network, followed by a supervised feature selection procedure that extracts clusters that are highly predictive of the disease state. By benchmarking GCNCC based on independent datasets from different diseases (psychiatric disorder and cancer) and different platforms (microarray and RNA-seq), we show that GCNCC outperforms other state-of-the-art methods in terms of accuracy and reproducibility.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Inverse Reinforcement Learning based Bayesian Goal Inference Method for Early Nuclear Proliferation Detection

Traditional methods for detection of nuclear proliferation indicators are usually applied after nuclear proliferation has already occurred. There is a need to advance these methods to perform early detection of nuclear proliferation indicators. In this project, we formulated an early detection problem as a sequential, decision-making, goal inference problem based on research publications of authors, to determine whether it is possible to infer whether an author will publish on a research activity before it has occurred. To develop and test our approach, we selected a civil nuclear activity for our case study. We constructed a state-action-state transition graph from publications of authors associated with the activity and the co-authors of their publications, using titles, abstracts, and author publication sequences. We then used inverse reinforcement learning to model the goal-directed behavior of authors in trajectories that terminate at selected goal states. Using a Bayesian formulation, we computed the probability that authors would reach each selected state from partially observed trajectories of their state transitions in their research topic space. The state with the highest probability was selected as the most probable goal state. Based on our results, we found that 60% of the times we can infer the correct goal state early; sometimes the inference is either delayed, or multiple states could be inferred as goal states. Overall, our results show that it is possible to perform early detection of research activities of authors in a nuclear technology area. Further research is necessary to establish a more accurate understanding of how topic modeling, topic space grid discretization, and the extent of overlap among trajectories of different goal states, affect the goal inference results. The methods developed in this work may be used to enhance data-driven methods for early detection of nuclear proliferation indicators.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Spatio-Temporal Deep Graph Network for Event Detection, Localization, and Classification in Cyber-Physical Electric Distribution System

This work proposes a deep graph learning framework to identify, locate, and classify power, cyber, and cyber power events at the distribution system level. The proposed algorithm jointly exploits spatial, temporal, and node-level cyber and physical data features. The developed graph neural network, together with a deep autoencoder, utilizes physical measurements from distribution level phasor measurement units and cyber data from communication network logs. The spatial structure of the synchrophasor measurements and network is incorporated through a weighted adjacency matrix. The temporal structure is incorporated by defining a spatial operation in the gated recurrent unit. This spatio-temporal learning element resides inside a power event detection, localization, and classification module that provides the degree of confidence for an event label. To accurately pinpoint the location of an event to the nearest bus equipped with a measurement unit, a combination of squared error and proximity score is utilized. Also included is a cyber event detection module that employs heteroskedasticity to analyze the significance of various cyber features during different types of attacks. Finally, a dual-bit cyber-power decision table determines the nature of the event. The proposed method is validated on two distribution systems modeled in OPAL-RT/Hypersim with limited phasor measurement units for different possible physical and cyber events. Further analyses include comparison with other state-of-the-art methods and validation in the presence of measurement noise. As a result, our method outperforms existing approaches and achieves an average detection accuracy of 97.97%, F1-score of 96.88%, precision of 96.53%, and recall of 98.57%.

24 POWER TRANSMISSION AND DISTRIBUTION↗