Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “network embeddings”

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 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
NASA NTRS2006

Real Time Mars Approach Navigation Aided by the Mars Network

A NASA Mars technology project is described that is building a prototype embedded real time Mars approach navigation capability which can be hosted on the Mars Network's Electra transceiver. The paper motivates the reason for doing real time Mars approach navigation via a set of analyses demonstrating its utility for enabling Mars pin-point landing (less than 1-km landing error). The development approach, software design, and test results are discussed. Finally, the way forward towards a flight demonstration on the Mars Science Laboratory (MSL) is presented.

Mars Network↗
NASA NTRS2017

Classification of Wildfires from MODIS Data Using Neural Networks

Wildfires are destructive to both life and property, which necessitates an approach to quickly and autonomously detect these events from orbital observatories. This talk will introduce a neural network based approach for classifying wildfires in MODIS multispectral data, and will show how it could be applied to a constellation of low-cost CubeSats. The approach combines training a deep neural network on the ground using high performance consumer GPUs, with a highly optimized inference system running on a flight-proven embedded processor. Normally neural networks execute on hardware orders of magnitude more powerful than anything found in a space-based computer, therefore the inference system is designed to be performance even on the most modest of platforms. This implementation is able to be significantly more accurate than previous neural network implementations, while also approaching the accuracy of the state-of-the-art MODFIRE data products.

Artificial Intelligence↗
DOE OSTI2020

Multimodal Data Representation with Deep Learning for Extracting Cancer Characteristics from Clinical Text

This paper presents a multimodal data representation to improve the performance of deep learning models for extracting cancer key characteristics from unstructured text in pathology reports. Specifically, in addition to using the text as the input to deep learning models, we use concept unique identifiers (CUIs) as another source of information to the models. We analyze the performance of different text and CUI data representations, including word embeddings and bag of embeddings (BOE), with a convolutional neural network (CNN) and a fully connected multilayer perceptron neural network (MLP-NN). The high level document embeddings from text and CUI inputs are combined by concatenating them and then applying a classifier. The model is used for extracting cancer subsite and histology from pathology reports. These two classification tasks have a large number of labels, i.e. 317 for subsite and 556 for histology, with extreme class imbalance. We compare the performance of the developed DL models across the two tasks based on micro- and macro-F1 scores. The evaluation shows that a multi-channel DL model that utilizes text represented by word embeddings and CUIs represented by BOE outperforms other DL models. Also, this approach significantly improves the model performance on low prevalence classes.

Alawad, Mohammed↗
DOE OSTI2024

Smart pixel sensors: towards on-sensor filtering of pixel clusters with deep learning

Highly granular pixel detectors allow for increasingly precise measurements of charged particle tracks. Next-generation detectors require that pixel sizes will be further reduced, leading to unprecedented data rates exceeding those foreseen at the High- Luminosity Large Hadron Collider. Signal processing that handles data incoming at a rate of $\mathcal{O}$(40 MHz) and intelligently reduces the data within the pixelated region of the detector at rate will enhance physics performance at high luminosity and enable physics analyses that are not currently possible. Using the shape of charge clusters deposited in an array of small pixels, the physical properties of the traversing particle can be extracted with locally customized neural networks. In this first demonstration, we present a neural network that can be embedded into the on-sensor readout and filter out hits from low momentum tracks, reducing the detector's data volume by 57.1%–75.7%. The network is designed and simulated as a custom readout integrated circuit with 28 nm CMOS technology and is expected to operate at less than 300 μW with an area of less than 0.2 mm 2 . The temporal development of charge clusters is investigated to demonstrate possible future performance gains, and there is also a discussion of future algorithmic and technological improvements that could enhance efficiency, data reduction, and power per area.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2024

Smart pixel sensors Towards on-sensor filtering of pixel clusters with deep learning

High granularity silicon pixel sensors are at the heart of energy frontier particle physics collider experiments. At an collision rate of 40\,MHz, these detectors create massive amounts of data. Signal processing that handles data incoming at those rate and intelligently reduces the data within the pixelated region of the detector \textit{at rate} will enhance physics performance and enable physics analyses that are not currently possible. Using the shape of charge clusters deposited in an array of small pixels, the physical properties of the traversing particle can be extracted with locally customized neural networks. In this first work, we present a neural network that can be embedded into the on-sensor readout and filter out hits from low momentum tracks, reducing the detector's data volume by 54.4-75.4\%. The network is designed and simulated as a custom readout integrated circuit with 28\,nm CMOS technology and is expected to operate at less than 300\,$\mu W$ with an area of less than 0.2\,mm$^2$.

43 PARTICLE ACCELERATORS↗
DOE OSTI2025

GenomeFace v1.0

GenomeFace is meta-genome binning software. Metagenomic binning, the process of grouping DNA sequences into taxonomic units, is critical for understanding the functions, interactions, and evolutionary dynamics of microbial communities. We propose a deep learning approach to binning using two neural networks, one based on composition and another on environmental abundance, dynamically weighting the contribution of each based on characteristics of the input data. Trained on over 43,000 prokaryotic genomes, our network for composition-based binning is inspired by metric learning techniques used for facial recognition. Using a task-specific, multi-GPU accelerated algorithm to cluster the embeddings produced by our network, our binner leverages marker genes observed to be universally present in nearly all taxa to grade and select optimal clusters of sequences from a hierarchy of candidates. We evaluate our approach on four simulated datasets with known ground truth. Our linear time integration of marker genes recovers more near complete genomes than state of the art but computationally infeasible solutions using them, while being over an order of magnitude faster. Finally, we demonstrate the scalability and acuity of our approach by testing it on three of the largest metagenome assemblies ever performed. Compared to other binners, we produced 47%-183% more near complete genomes. From these datasets, we find over the genomes of over 3000 new candidate species which have never been previously cataloged, representing a potential 4% expansion of the known bacterial tree of life.

Lettich, Richard [Lawrence Berkeley National Labor↗
DOE OSTI2020

Thermodynamic Consistent Neural Networks for Learning Material Interfacial Mechanics

For multilayer materials in thin substrate systems, interfacial failure is one of the most challenges. The traction-separation relations (TSR) quantitatively describe the mechanical behavior of a material interface undergoing openings, which is critical to understand and predict interfacial failures under complex loadings. However, existing theoretical models have limitations on enough complexity and flexibility to well learn the real-world TSR from experimental observations. A neural network can fit well along with the loading paths but often fails to obey the laws of physics, due to a lack of experimental data and understanding of the hidden physical mechanism. In this paper, we propose a thermodynamic consistent neural network (TCNN) approach to build a data-driven model of the TSR with sparse experimental data. The TCNN leverages recent advances in physics-informed neural networks (PINN) that encode prior physical information into the loss function and efficiently train the neural networks using automatic differentiation. We investigate three thermodynamic consistent principles, i.e., positive energy dissipation, steepest energy dissipation gradient, and energy conservative loading path. All of them are mathematically formulated and embedded into a neural network model with a novel defined loss function. A real-world experiment demonstrates the superior performance of TCNN, and we find that TCNN provides an accurate prediction of the whole TSR surface and significantly reduces the violated prediction against the laws of physics.

Zhang, Jiaxin↗
DOE OSTI2023

A Deep Learning Pipeline for Optimizing Large-scale Phase Field Simulations

Phase field (PF) simulations are computationally expensive but remain a key analysis tool to understand the complex mechanisms of additive manufacturing (AM) processes. Each PF simulation-aided analysis requires thousands of node hours on leadership-class supercomputers. One of the main goals of these analyses is the study of microstructure evolution during the build process which begins with the onset of nucleation. Nucleation occurs under certain thermomechanical conditions which are not known a priori and many PF simulations are required to identify ranges of input thermo-mechanical parameters that can result in the onset of nucleation. Since many of the simulations do not result in nucleation, an analysis campaign often ends up wasting tremendous amounts of precious computing resources executing nucleation-absent simulations. The goal of this work is to design and train deep learning models to inform a PF simulation about the likelihood of the occurrence of nucleation in a future simulation time-step based on the state summary over a finite number of past time-steps of a running simulation. If the prediction determines that the running simulation is unlikely to reach nucleation in the allotted time, then its execution is stopped immediately ultimately resulting in vast reduction in wasted computations when accrued over all the PF simulations typically performed in a single or multiple analysis campaign(s). The paper presents the performance of a machine learning pipeline that uses a convolutional neural network (CNN) model to learn an embedding which is then used with a self-attention network to build a multi-task deep learning model to predict the likelihood of nucleation. The model also predicts the input parameters used in a simulation. Performance is compared with a baseline pipeline that uses an off-the-shelf LeNet-5 model to learn the initial embedding. Despite their smaller size, performance results indicate significant improvement in accuracy of the proposed models compared to the larger baseline models.

Kannan, Ramakrishnan {ramki}↗
DOE OSTI2022

Plant Cell Growth and Cell Wall Enlargement

Irreversible cell enlargement begins with cell wall loosening which induces wall stress relaxation, leading to cell water uptake and cell enlargement. Growing cell walls consist of a cohesive network of cellulose microfibrils embedded in hydrophilic pectins and cellulose-binding hemicelluloses. Models of the growing cell wall are provisional hypotheses about how these wall polymers interact to make a strong yet extensible wall. Recent results clarify how wall strength, plasticity and elasticity depend mostly on the stretching, straightening and sliding of cellulose microfibril networks in the wall. Passive sliding of cellulose microfibrils is facilitated by nonenzymic proteins named expansins while various enzymes modify pectins and hemicelluloses, altering their interactions with each other and with cellulose. Growth cessation is correlated with reduced expression of genes that promote wall loosening as well as changes in the direction of cellulose deposition and the structure of matrix polysaccharides, leading to a less extensible cell wall.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

cuAlign: Scalable Network Alignment on GPU Accelerators

Given two graphs, the objective of network alignment is to find the best one-to-one mapping of vertices in one graph (??) to vertices in the other (??), such that the number of overlaps is maximized. We say that edges(??, ??) ???and(??', ??') ??? are overlapped if ?? is mapped to ??' and ?? is mapped to??'. Network alignment is an important optimization problem with several applications in bioinformatics, computer vision and ontology matching. Since it is an NP-hard problem, efficient heuristics and scalable implementations are necessary. In this work, we introduce a new framework that combines the concepts of intra-network proximity using vertex embedding,Belief Propagation (BP) and approximate weighted matching, and provides qualitative improvements up to22%over state-of-the-art approaches. We also provide scalable implementations on GPU accelerators, demonstrating up to19×speedup for Belief Propagation and 3× speedup for approximate weighted matching relative to previous multithreaded implementation. A combination of combinatorial and algebraic kernels within the network alignment algorithm poses significant hurdles for parallelization. Load imbalance and irregular DRAM traffic limit achievable performance on GPUs. Our novel approach identifies and exploits unique structural proper-ties of the BP-based algorithm and employs code fusion to reduce data movement between different steps of the algorithm. Using a diverse set of inputs, we demonstrate qualitative improvements of our algorithms, and performance gains of our GPU-accelerated implementation. We believe that our work will enable algorithmic improvements and practical applications of network alignment.

Xiang, Lizhi↗
NASA NTRS1998

Thin Film Mediated Phase Change Phenomena: Crystallization, Evaporation and Wetting

We focus on two distinct materials science problems that arise in two distinct microgravity environments: In space and within the space of a polymeric network. In the former environment, we consider a near eutectic alloy film in contact with its vapor which, when evaporating on earth, will experience compositionally induced buoyancy driven convection. The latter will significantly influence the morphology of the crystallized end member. In the absence of gravity, the morphology will be dominated by molecular diffusion and Marangoni driven viscous flow, and we study these phenomena theoretically and experimentally. The second microgravity environment exists in liquids, gels, and other soft materials where the small mass of individual molecules makes the effect of gravity negligible next to the relatively strong forces of intermolecular collisions. In such materials, an essential question concerns how to relate the molecular dynamics to the bulk rheological behavior. Here, we observe experimentally the diffusive motion of a single molecule in a single polymer filament, embedded within a polymer network and find anomalous diffusive behavior.

Wettlaufer, John S.↗
DOE OSTI2023

Green Catalysts for Reprocessing Thermoset Polyurethanes

Polyurethane (PU) thermosets are usually landfilled at the end of their service lifetimes and cannot be recycled through conventional means. Although dibutyltin dilaurate (DBTDL) is an effective catalyst for reprocessing PU thermosets, organotins are immunotoxic and teratogenic, which is concerning for catalysts embedded within covalent adaptable networks (CANs). Here, we identify Zr(acac) 4 and Zr(tmhd) 4 as catalysts to reprocess PU CANs more sustainably. Thermoset PU foams containing Zr-based catalysts exhibit characteristic stress relaxation times between 6 and 200 s, similar or faster than DBTDL. These catalysts are capable of reprocessing a PU foam for four or five cycles. Dynamic mechanical thermal analysis indicates that zirconium-based catalysts preserve glass transition temperature and crosslink density between cycles and are promising catalysts for bulk reprocessing of thermoset PUs. Here, a solvent-free reprocessing method was developed by co-milling the PU foam and the Zr catalyst. Ultimately, these reprocessing methods using Zr-based catalysts will impart greater sustainability and circularity to PU plastics.

Catalysts↗
DOE OSTI2025

On the scale of heterogeneity in composite electrodes of batteries

An electrode in cylindrical or pouch cell batteries contains millions of active particles embedded in a conductive network. Battery performance, such as voltage, capacity, and cyclic efficiency, is a collective response of the particle network. We use optical microscopy to measure the local, heterogeneous state of charge of individual particles upon charging and discharging. The optical reflectivity is proportional to Li composition in the ternary oxide LiNi x Mn y Co z O 2 (NMC) cathode. Through clustering analysis, we determine the scale of heterogeneity where a representative volume in the composite electrode contains 100 to 1,000 particles. The heterogeneous activity in the particle network can be described by Weibull defect population at the particle interface with the conductive matrix.

batteries↗
DOE OSTI2025

AI-Powered Knowledge Graphs for Neuromorphic and Energy-Efficient Computing

The surge in scientific literature obscures breakthroughs and hinders the discovery of new research paths. We propose an artificial intelligence (AI) powered framework using large language models (LLMs) and knowledge graphs (KGs) to automate parts of scientific discovery, focusing on energy-efficient AI circuits. Our hybrid approach combines LLMs, structured data, and ontology-based reasoning to construct a comprehensive knowledge graph that integrates insights across computational neuroscience, spiking neuron models, learning rules, architectural motifs, and neuromorphic device technologies. This multi-domain representation enables the generation of hypotheses that connect biological function with implementable, energy-efficient hardware architectures. Using KG embeddings and graph neural networks, the framework generates hypotheses for novel circuits, validates them through optimization on exascale HPC systems, and with tools like SuperNeuro and Fugu, the most promising designs will be prototyped in hardware. This open-source system aims to accelerate discoveries and bridging neuroscience with hardware innovation, drive collaboration, and unlock new opportunities in low-power AI computing.

Gautam, Ashish [ORNL]↗
NASA NTRS1986

On the structure of parallelism in a highly concurrent PDE solver

A parallel multigrid algorithm for solving elliptic partial differential equations is developed and evaluated. A V-cycle multigrid method is altered to increase the degree of parallelism. A numerical analysis of the resulting concurrent-iteration multigrid algorithm is performed; its architectural implications are considered; highly parallel systems without shared memory are examined (including mesh-connected arrays, mesh-shuffle-connected systems, permutation networks, and direct VLSI embeddings); and the results of numerical experiments are presented in tables and graphs.

Gannon, D.↗
NASA NTRS2002

Embedded Web Technology: Applying World Wide Web Standards to Embedded Systems

Embedded Systems have traditionally been developed in a highly customized manner. The user interface hardware and software along with the interface to the embedded system are typically unique to the system for which they are built, resulting in extra cost to the system in terms of development time and maintenance effort. World Wide Web standards have been developed in the passed ten years with the goal of allowing servers and clients to intemperate seamlessly. The client and server systems can consist of differing hardware and software platforms but the World Wide Web standards allow them to interface without knowing about the details of system at the other end of the interface. Embedded Web Technology is the merging of Embedded Systems with the World Wide Web. Embedded Web Technology decreases the cost of developing and maintaining the user interface by allowing the user to interface to the embedded system through a web browser running on a standard personal computer. Embedded Web Technology can also be used to simplify an Embedded System's internal network.

Ponyik, Joseph G.↗
DOE OSTI2021

Clinical knowledge extraction via sparse embedding regression (KESER) with multi-center large scale electronic health record data

The increasing availability of electronic health record (EHR) systems has created enormous potential for translational research. However, it is difficult to know all the relevant codes related to a phenotype due to the large number of codes available. Traditional data mining approaches often require the use of patient-level data, which hinders the ability to share data across institutions. In this project, we demonstrate that multi-center large-scale code embeddings can be used to efficiently identify relevant features related to a disease of interest. We constructed large-scale code embeddings for a wide range of codified concepts from EHRs from two large medical centers. We developed knowledge extraction via sparse embedding regression (KESER) for feature selection and integrative network analysis. We evaluated the quality of the code embeddings and assessed the performance of KESER in feature selection for eight diseases. Besides, we developed an integrated clinical knowledge map combining embedding data from both institutions. The features selected by KESER were comprehensive compared to lists of codified data generated by domain experts. Features identified via KESER resulted in comparable performance to those built upon features selected manually or with patient-level data. The knowledge map created using an integrative analysis identified disease-disease and disease-drug pairs more accurately compared to those identified using single institution data. Analysis of code embeddings via KESER can effectively reveal clinical knowledge and infer relatedness among codified concepts. KESER bypasses the need for patient-level data in individual analyses providing a significant advance in enabling multi-center studies using EHR data.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2024

Optimization strategies for produced water networks with integrated desalination facilities

Optimal management and desalination of produced water is a major challenge for U.S. oil and gas development. Integrating rigorous desalination models into multi-period produced water network optimization problems presents several hurdles, which need to be tackled using advanced optimization strategies. Here, in this work, a novel multi-period produced water network formulation with separate solid and liquid flows is introduced to avoid singularities at zero flows. Rigorous steady state desalination models based on mechanical vapor recompression are embedded at the desalination sites in the network model. An integrated optimization formulation is developed to co-optimize the design of desalination units along with the operation of the network. Furthermore, a more robust approach based on the trust region filter method is developed to efficiently integrate complex desalination models into the multi-period planning problem. Both optimization approaches are demonstrated on a produced water network from the PARETO library (Drouven et al., 2022) using thermal desalination units. Our results show that while the TRF and integrated approaches have comparable solve times, the TRF approach has better performance reliability in terms of solver convergence. Furthermore, the optimal solution obtained by embedding rigorous models into the network is significantly different than when desalination costs are approximated using simple cost models, which motivates further research in this field.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗