Search NASA⌕ Search

SEARCH · Search NASA

Results for “Graph embedding”

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 199 records · Page 11
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

FLASH: FPGA-Accelerated Smart Switches with GCN Case Study

Some communication switches, e.g., the Mellanox SHArP and those in the IBM BlueGene clusters, are augmented to process packets at the application level with fixed-function collectives. This approach, however, lacks flexibility, which limits their applicability in diverse and dynamic workloads. Recently, a new type of programmable packet processor, which uses high-level languages, e.g., P4, has emerged as possible candidates. P4-based switches, however, fall short in certain applications, including machine learning, where capabilities not currently supported by P4 are needed. These include more complex calculation, such as sparse computation and fused multiply-accumulate, data-intensive floating point operations, data reuse, and significant memory. The problem addressed here is that such a switch augmentation needs to support: a large amount of state, significant flexible compute capability, and ease of programming, all while maintaining full functionality, including ensuring high throughput, and demonstrating utility. In this work, we propose a programmable look-aside-type accelerator that can be embedded into, or attached to, existing communication switch pipelines and that is capable of processing packets at line-rate. The proposed in-switch accelerator is based on mixing an ISA (subset of RISC-V instructions) with dataflow graphs (found in CGRAs). To augment performance, vector instructions are also supported. To facilitate usability, we have developed a complete toolchain to compile user-provided C/C++ codes to appropriate back-end instructions for configuring the accelerator. While this approach is flexible enough to support various workloads, in this paper, we consider Graph Convolutional Networks (GCNs) as a case study. Experimental results show that this approach considerably improves the performance of distributed GCN applications.

Haghi, Pouya↗
DOE OSTI2012

High-performance analysis of filtered semantic graphs

High performance is a crucial consideration when executing a complex analytic query on a massive semantic graph. In a semantic graph, vertices and edges carry "attributes" of various types. Analytic queries on semantic graphs typically depend on the values of these attributes; thus, the computation must either view the graph through a filter that passes only those individual vertices and edges of interest, or else must first materialize a subgraph or subgraphs consisting of only the vertices and edges of interest. The filtered approach is superior due to its generality, ease of use, and memory efficiency, but may carry a performance cost. In the Knowledge Discovery Toolbox (KDT), a Python library for parallel graph computations, the user writes filters in a high-level language, but those filters result in relatively low performance due to the bottleneck of having to call into the Python interpreter for each edge. In this work, we use the Selective Embedded JIT Specialization (SEJITS) approach to automatically translate filters defined by programmers into a lower-level efficiency language, bypassing the upcall into Python. We evaluate our approach by comparing it with the high-performance C++ /MPI Combinatorial BLAS engine, and show that the productivity gained by using a high-level filtering language comes without sacrificing performance.

97 MATHEMATICS AND COMPUTING↗
NASA NTRSDate not supplied

Improving GES Disc Data Search and Discovery Through AI Metadata Augmentation

NASA’s Goddard Earth Science (GES) Data and Information Services Center (DISC) is one of twelve data centers in NASA's Science Mission Directorate (SMD), providing vital earth science data to a diverse user base. To enhance the discoverability of this data, GES DISC employs a keyword search system, which leverages scientific keywords embedded in dataset metadata. However, the evolving nature of scientific applications of our data necessitates regular review and augmentation of these keywords. To address this, we developed a service to automatically predict missing science keywords in the metadata. This service constructs a knowledge graph from the latest GES DISC metadata within NASA’s Common Metadata Repository (CMR). Using an open-source library, we trained a machine learning model to predict absent science keywords in the metadata. Our preliminary results indicate that the model has high levels of accuracy at predicting science keywords in the dataset metadata when exposed to data not included in its training. These predicted keywords were then evaluated by GES DISC data curation scientists and compared against other AI tools for metadata augmentation. We aim to enhance the overall usability and accessibility of NASA’s earth science data by implementing this tool in our data curation processes.

Kendall Gilbert↗
DOE OSTI2010

Learning planar ising models

Inference and learning of graphical models are both well-studied problems in statistics and machine learning that have found many applications in science and engineering. However, exact inference is intractable in general graphical models, which suggests the problem of seeking the best approximation to a collection of random variables within some tractable family of graphical models. In this paper, we focus our attention on the class of planar Ising models, for which inference is tractable using techniques of statistical physics [Kac and Ward; Kasteleyn]. Based on these techniques and recent methods for planarity testing and planar embedding [Chrobak and Payne], we propose a simple greedy algorithm for learning the best planar Ising model to approximate an arbitrary collection of binary random variables (possibly from sample data). Given the set of all pairwise correlations among variables, we select a planar graph and optimal planar Ising model defined on this graph to best approximate that set of correlations. We present the results of numerical experiments evaluating the performance of our algorithm.

36 MATERIALS SCIENCE↗
DOE OSTI2022

RanCompute: Computational Security in Embedded Devices via Random Input and Output Encodings

An embedded device in an insecure environment is subject to additional security risk through capture and reverse-engineering by a capable adversary. If this device contains a microchip performing sensitive computations, capture of the chip may leak functionality to an adversary. In this paper we propose a novel method in which we randomly encode the input operands and the outputs of a computation, thus not revealing the arithmetic operations being performed. The operations are sequenced in a graph representing the overall application. Once the initialization values are overwritten and lost, the results of these computations are indecipherable by the device performing the calculations as well as by any adversary. The result is transmitted back to a secure server which has stored the initialization values and so can decode the results which appear random to the adversary.

Embedded computing↗
NASA NTRS2017

GeoDash: Assisting Visual Image Interpretation in Collect Earth Online by Leveraging Big Data on Google Earth Engine

Collect Earth Online (CEO) is a free and open online implementation of the FAO Collect Earth system for collaboratively collecting environmental data through the visual interpretation of Earth observation imagery. The primary collection mechanism in CEO is human interpretation of land surface characteristics in imagery served via Web Map Services (WMS). However, interpreters may not have enough contextual information to classify samples by only viewing the imagery served via WMS, be they high resolution or otherwise. To assist in the interpretation and collection processes in CEO, SERVIR, a joint NASA-USAID initiative that brings Earth observations to improve environmental decision making in developing countries, developed the GeoDash system, an embedded and critical component of CEO. GeoDash leverages Google Earth Engine (GEE) by allowing users to set up custom browser-based widgets that pull from GEE's massive public data catalog. These widgets can be quick looks of other satellite imagery, time series graphs of environmental variables, and statistics panels of the same. Users can customize widgets with any of GEE's image collections, such as the historical Landsat collection with data available since the 1970s, select date ranges, image stretch parameters, graph characteristics, and create custom layouts, all on-the-fly to support plot interpretation in CEO. This presentation focuses on the implementation and potential applications, including the back-end links to GEE and the user interface with custom widget building. GeoDash takes large data volumes and condenses them into meaningful, relevant information for interpreters. While designed initially with national and global forest resource assessments in mind, the system will complement disaster assessments, agriculture management, project monitoring and evaluation, and more.

SERVI↗
NASA NTRS1990

Effects of source vs. interactive actuator assumptions on modelling of a smart structure

Embedded or internal actuators in a structure are being utilized to perform vibration attenuation, pointing maneuvers, damage control, and other adaptive tasks. The controls-structures-interaction (CSI) design process depends strongly on the coupled dynamic response of the structure and the actuators. A bond graph approach is used to guide this analytical study to uncover the effects of certain generic actuator types on the closed-loop, initial condition control of a single-mode structural model and an eighteen-state model of an active truss. So-called 'flow' and 'effort' source actuator types were studied and were shown to have significant differences in closed-loop response for ranges of initial conditions and system open-loop natural frequencies.

Robertshaw, Harry H.↗
DOE OSTI2025

Templates for Risk Informed Assurance with Curvature Embeddings (TRACE)

We investigate recovery of geometric structure from networks embedded in manifolds with spatially varying curvature, extending the constant-curvature framework of Lubold et al. (2023). Our work supports cascade risk assessment in critical infrastructure through the Templates for Risk-informed Assurance with Curvature Embeddings (TRACE) framework. Simulations on a bi-modal Gaussian surface show that constant-curvature methods yield weighted averages shaped by clique patterns, while hierarchical clustering identifies distinct regimes. Localized estimation, however, reveals boundary contamination in transitional regions. To address heterogeneity, we develop distance metrics for graphs with edge and node features, proving their metric validity, and validate them via deterministic graph generation from canonical tilings. We further propose a diffusion-based anomaly detection approach that treats networks as glued manifolds, using curvature discontinuities to detect structural anomalies. Employing the carré-du-champ operator and scalar curvature, we achieve robust anomaly discrimination, demonstrated on the Singapore Water Treatment (SWaT) dataset with joint network-traffic and sensor features. Integration with TRACE reveals how curvature shapes cascade dynamics: positive curvature impedes, while negative curvature accelerates propagation. This geometric perspective provides interpretable risk metrics and visualization tools for critical infrastructure managers. While full validation remains ongoing, our contributions establish a rigorous foundation for geometric analysis of network resilience and cascade vulnerability.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1991

Simulator for enhanced ATAMM multiprocessing

A simulator is introduced which follows the rules of the enhanced Algorithm to Architecture Mapping Model (ATAMM) multiprocessing strategy. ATAMM is a method for embedding an algorithm into a multiprocessing system in addition to providing system performance prediction capabilities. A discussion of the inner workings of the Architecture Design and Assessment System (ADAS) hosted simulator is introduced to illustrate how the simulator follows the ATAMM rule set. A sample 5-node algorithm graph is given as an example to illustrate: (1) entering of a graph into the simulator and how to run the graph using a graph entry tool; (2) how to analyze the data; and (3) a comparison of the simulation results with the predicted results from ATAMM.

Andrews, Asa M.↗
NASA NTRS2013

Flat Surface Damage Detection System (FSDDS)

The Flat Surface Damage Detection system (FSDDS} is a sensory system that is capable of detecting impact damages to surfaces utilizing a novel sensor system. This system will provide the ability to monitor the integrity of an inflatable habitat during in situ system health monitoring. The system consists of three main custom designed subsystems: the multi-layer sensing panel, the embedded monitoring system, and the graphical user interface (GUI). The GUI LABVIEW software uses a custom developed damage detection algorithm to determine the damage location based on the sequence of broken sensing lines. It estimates the damage size, the maximum depth, and plots the damage location on a graph. Successfully demonstrated as a stand alone technology during 2011 D-RATS. Software modification also allowed for communication with HDU avionics crew display which was demonstrated remotely (KSC to JSC} during 2012 integration testing. Integrated FSDDS system and stand alone multi-panel systems were demonstrated remotely and at JSC, Mission Operations Test using Space Network Research Federation (SNRF} network in 2012. FY13, FSDDS multi-panel integration with JSC and SNRF network Technology can allow for integration with other complementary damage detection systems.

Williams, Martha↗
DOE OSTI2021

A mathematical analysis of carbon fixing materials that grow, reinforce, and self-heal from atmospheric carbon dioxide

Carbon fixing materials are a new class of self-healing, self-reinforcing materials we have introduced that utilize ambient CO 2 to chemically add to an ever extending carbon backbone. This class of materials can utilize biological or non-biological photocatalysts and support a wide range of potential backbone chemistries. However, there is no analysis to date that describes their fundamental limits in terms of chemical kinetics and mass transfer. In this computational study, we employ a reaction engineering, and materials science analysis to answer basic questions about the maximum growth rate, photocatalytic requirements and limits of applicable materials. Our proposed mathematical framework envelops three main functions required for carbon fixing materials: (1) adsorption of CO 2 from air, (2) photocatalytic reduction of CO 2 into selected monomers, and (3) polymerization of CO 2 -derived monomers. First, by performing a Damköhler number analysis, we derive criteria for the cross over from kinetic control to mass transfer limited growth, setting upper limits on performance of a potential photocatalyst. Next, we analyze photocatalytic reduction of CO 2 to single carbon products, using known catalytic pathways and kinetic data. We identify formaldehyde as a C1 intermediate having unique potential for incorporation into the material backbone of carbon fixing materials. As an example, we find that a diamond-shaped reaction network graph for CO 2 reduction, passing through CO and HCOOH intermediates, accurately describes kinetic data for cobalt-promoted TiO 2 nanoparticles at room temperature and 1 atm CO 2 . Finally, as an applied case study, we consider and analyze the example of a carbon fixing poly(oxymethylene) system with embedded catalyst promoting the photocatalytic reduction of CO 2 to formaldehyde. The latter then trimerizes to a trioxane monomer which subsequently polymerizes to polyoxymethylene. This reaction engineering analysis introduces benchmarks for carbon fixing materials with respect to achievable rates of photocatalysis, adsorption, and polymerization. These results should prove valuable for the design, evaluation, and benchmarking of this emergent and new class of environmentally sustainable materials.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2017

NOUS: Construction and Querying of Dynamic Knowledge Graphs

The ability to construct domain specific knowledge graphs (KG) and perform question-answering or hypothesis generation is a trans- formative capability. Despite their value, automated construction of knowledge graphs remains an expensive technical challenge that is beyond the reach for most enterprises and academic institutions. We propose an end-to-end framework for developing custom knowl- edge graph driven analytics for arbitrary application domains. The uniqueness of our system lies A) in its combination of curated KGs along with knowledge extracted from unstructured text, B) support for advanced trending and explanatory questions on a dynamic KG, and C) the ability to answer queries where the answer is embedded across multiple data sources.

Choudhury, Sutanay↗
DOE OSTI2024

Dynamic Graph Sequence Data from Simulated Neutron Reflectometry Measurements

This dataset comprises dynamic graph sequences derived from simulated in-situ neutron reflectometry measurements, capturing the gradual evolution of a layer structure over time. Each graph sequence represents a synthetic sample, with node features detailing the scattering vector and corresponding reflectivity measurements, while adjacency matrices have corresponding reference material parameters attached as metadata. The dataset spans multiple sets, each with a different number of sequences, offering a comprehensive basis for training models that handle dynamic input sequences with embedded physics. This dataset is particularly suited for tackling inverse problems with hidden physical states that evolve over time, challenges that are typically difficult to address using conventional iterative fitting methods.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Predicting nutrition and environmental factors associated with female reproductive disorders using a knowledge graph and random forests

Female reproductive disorders (FRDs) are common health conditions that may present with significant symptoms. Diet and environment are potential areas for FRD interventions. We utilized a knowledge graph (KG) method to predict factors associated with common FRDs (for example, endometriosis, ovarian cyst, and uterine fibroids). We harmonized survey data from the Personalized Environment and Genes Study (PEGS) on internal and external environmental exposures and health conditions with biomedical ontology content. We merged the harmonized data and ontologies with supplemental nutrient and agricultural chemical data to create a KG. We analyzed the KG by embedding edges and applying a random forest for edge prediction to identify variables potentially associated with FRDs. We also conducted logistic regression analysis for comparison. Across 9765 PEGS respondents, the KG analysis resulted in 8535 significant or suggestive predicted links between FRDs and chemicals, phenotypes, and diseases. Amongst these links, 32 were exact matches when compared with the logistic regression results, including comorbidities, medications, foods, and occupational exposures. Mechanistic underpinnings of predicted links documented in the literature may support some of our findings. Our KG methods are useful for predicting possible associations in large, survey-based datasets with added information on directionality and magnitude of effect from logistic regression. These results should not be construed as causal but can support hypothesis generation. This investigation enabled the generation of hypotheses on a variety of potential links between FRDs and exposures. Future investigations should prospectively evaluate the variables hypothesized to impact FRDs.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2024

Development of message passing-based graph convolutional networks for classifying cancer pathology reports

Abstract Background Applying graph convolutional networks (GCN) to the classification of free-form natural language texts leveraged by graph-of-words features (TextGCN) was studied and confirmed to be an effective means of describing complex natural language texts. However, the text classification models based on the TextGCN possess weaknesses in terms of memory consumption and model dissemination and distribution. In this paper, we present a fast message passing network (FastMPN), implementing a GCN with message passing architecture that provides versatility and flexibility by allowing trainable node embedding and edge weights, helping the GCN model find the better solution. We applied the FastMPN model to the task of clinical information extraction from cancer pathology reports, extracting the following six properties: main site, subsite, laterality, histology, behavior, and grade. Results We evaluated the clinical task performance of the FastMPN models in terms of micro- and macro-averaged F1 scores. A comparison was performed with the multi-task convolutional neural network (MT-CNN) model. Results show that the FastMPN model is equivalent to or better than the MT-CNN. Conclusions Our implementation revealed that our FastMPN model, which is based on the PyTorch platform, can train a large corpus (667,290 training samples) with 202,373 unique words in less than 3 minutes per epoch using one NVIDIA V100 hardware accelerator. Our experiments demonstrated that using this implementation, the clinical task performance scores of information extraction related to tumors from cancer pathology reports were highly competitive.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2019

Evaluating Time Varying Connectivities and System Throughput in Opportunistic Networks for Smart Grid Applications

With increasing proliferation of smart phones, there is an opportunity to employ mobile ad hoc networks to connect to distributed energy assets located in remote areas. With embedded intelligence and edge computing capabilities, autonomous ‘edge control nodes’ can enable a decentralized energy nexus, without the need for on-demand communications. Authors have developed an opportunistic networking framework using Bluetooth Low Energy and a specialized mobile phone application that enables delay tolerant networking for the above framework. Here, this paper presents the analysis of time varying graph connectivity for such an opportunistic mobile ad hoc network. Dependence of connectivity on different network parameters such as radio characteristics, the mobility of data mules and parameters governing how connections are established are explored. Simulation results showing the variation of above trends have been presented.

Bluetooth↗
NASA NTRS1978

Predicting surface heat flux

Report presents technique involving single embedded thermocouple used to predict flux and temperature for high-or-low conductivity materials that have temperature-and-pressure dependent properties. Technique solves for heat rate and temperature at given surface at each time step, rather than for entire history. Newton-Raphson technique is used for temperature solutions; then quadratic fit is employed. Report contains representative graphs and tables.

Curry, D. M.↗
DOE OSTI2023

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

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

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗