Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “layered networks”

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 973 records · Page 54
All sourcesNASA NTRSDOE OSTI
NASA NTRS2010

Simultaneous Retrieval of Aerosol and Surface Optical Properties from Combined Airborne- and Ground-Based Direct and Diffuse Radiometric Measurements

This paper presents a new method for simultaneously retrieving aerosol and surface reflectance properties from combined airborne and ground-based direct and diffuse radiometric measurements. The method is based on the standard Aerosol Robotic Network (AERONET) method for retrieving aerosol size distribution, complex index of refraction, and single scattering albedo, but modified to retrieve aerosol properties in two layers, below and above the aircraft, and parameters on surface optical properties from combined datasets (Cloud Absorption Radiometer (CAR) and AERONET data). A key advantage of this method is the inversion of all available spectral and angular data at the same time, while accounting for the influence of noise in the inversion procedure using statistical optimization. The wide spectral (0.34-2.30 m) and angular range (180 ) of the CAR instrument, combined with observations from an AERONET sunphotometer, provide sufficient measurement constraints for characterizing aerosol and surface properties with minimal assumptions. The robustness of the method was tested on observations made during four different field campaigns: (a) the Southern African Regional Science Initiative 2000 over Mongu, Zambia, (b) the Intercontinental Transport Experiment-Phase B over Mexico City, Mexico (c) Cloud and Land Surface Interaction Campaign over the Atmospheric Radiation Measurement (ARM) Central Facility, Oklahoma, USA, and (d) the Arctic Research of the Composition of the Troposphere from Aircraft and Satellites (ARCTAS) over Elson Lagoon in Barrow, Alaska, USA. The four areas are dominated by different surface characteristics and aerosol types, and therefore provide good test cases for the new inversion method.

Gatebe, C. K.↗
NASA NTRS2012

The S-Web Model for the Sources of the Slow Solar Wind

Models for the origin of the slow solar wind must account for two seemingly contradictory observations: The slow wind has the composition of the closed-field corona, implying that it originates from the continuous opening and closing of flux at the boundary between open and closed field. On the other hand, the slow wind has large angular width, up to 60 degrees, suggesting that its source extends far from the open-closed boundary. We describe a model that can explain both observations. The key idea is that the source of the slow wind at the Sun is a network of narrow (possibly singular) open-field corridors that map to a web of separatrices (the S-Web) and quasi-separatrix layers in the heliosphere. We discuss the dynamics of the S-Web model and its implications for present observations and for the upcoming observations from Solar Orbiter and Solar Probe Plus.

Antiochos, Spiro K.↗
NASA NTRS2018

Towards Explainability of UAV-Based Convolutional Neural Networks for Object Classification

f autonomous systems using trust and trustworthiness is the focus of Autonomy Teaming and TRAjectories for Complex Trusted Operational Reliability (ATTRACTOR), a new NASA Convergent Aeronautical Solutions (CAS) Project. One critical research element of ATTRACTOR is explainability of the decision-making across relevant subsystems of an autonomous system. The ability to explain why an autonomous system makes a decision is needed to establish a basis of trustworthiness to safely complete a mission. Convolutional Neural Networks (CNNs) are popular visual object classifiers that have achieved high levels of classification performances without clear insight into the mechanisms of the internal layers and features. To explore the explainability of the internal components of CNNs, we reviewed three feature visualization methods in a layer-by-layer approach using aviation related images as inputs. Our approach to this is to analyze the key components of a classification event in order to generate component labels for features of the classified image at different layers of depths. For example, an airplane has wings, engines, and landing gear. These could possibly be identified somewhere in the hidden layers from the classification and these descriptive labels could be provided to a human or machine teammate while conducting a shared mission and to engender trust. Each descriptive feature may also be decomposed to a combination of primitives such as shapes and lines. We expect that knowing the combination of shapes and parts that create a classification will enable trust in the system and insight into creating better structures for the CNN.

Dolph, Chester V.↗
NASA NTRS2021

A Geodetic and Positioning Thematic Layer - Identifying tools to connect the GGRF and IGIF

Effective and sustainable modernization of a nation’s geodetic framework relies on the ability of the relevant organizations and other stakeholders to communicate, integrate, and align both their strategic objectives and operational planning with the United Nations Committee of Experts on Global Geospatial Information Management (UN GGIM) Sub-Committee on Geodesy’s (SCoG) roadmap for a Global Geodetic Reference Frame (GGRF) for Sustainable Development. In addition, to implement geodetic modernization initiatives through multiple government agencies, a holistic country action plan (CAP) for geospatial information management must incorporate pertinent geodetic outcomes and outputs. Presently, the CAP framework and principles used by nations is the UN GGIM Integrated Geospatial Information Framework (IGIF). From engagement with geospatial and survey communities across emerging nations in the Asia Pacific region, it is evident more assistance and coordination is necessary to articulate, integrate and connect geodetic organizational strategies with the requirements of the GGRF roadmap; the strategic pathways of the IGIF; and resourcing for a meaningful and relevant multi-faceted CAP. One of the supporting mechanisms for such planning or preparation, which representatives of the International Federation of Surveyors (FIG) Asia Pacific Capacity Development Network (AP CDN) and the UN SCoG Education, Training and Capacity Building (ETCB) working group are considering, is a policy framework and guide for a “Geodetic and Positioning Thematic Layer” (GPTL). Essentially, this “thematic layer”, in terms of the GGRF and IGIF, aims to provide a comprehensive understanding of, and a toolbox for, the “why, what, how, and who” of geodesy and positioning. This discussion paper will provide background and insights for a GPTL dedicated to recognizing, and aligning the geodetic capacity development needs with broader geospatial information management issues and applications. The paper will also outline a rigorous, participatory, and inclusive consultation process for the design and development of a thematic layer. Furthermore, as the intention of the authors is to prepare a forthcoming “white paper” that will concisely describe the issues of a GPTL and initiatives for an appropriate guide and/or policy framework, this paper will seek feedback on: the potential scientific, social, environmental and political benefits of modernizing geodetic infrastructure and systems; the challenges associated with the GGRF roadmap; leveraging the geodesy-relevant elements of each IGIF strategic pathway; the importance of collaborative efforts; and the capacity development needs and resources in relation to governance, technology and people.

SARIB, Rob↗
DOE OSTI2024

Integration of CeO 2 -Based Memristor with Vertically Aligned Nanocomposite Thin Film: Enabling Selective Conductive Filament Formation for High-Performance Electronic Synapses

The CeO 2 -based memristor has attracted significant attention due to its intrinsic resistive switching (RS) properties, large on/off ratio, and great plasticity, making it a promising candidate for artificial synapses. However, significant challenges such as high power consumption and poor device reliability hinder its broad application in neuromorphic microchips. To tackle these issues, in this work, we design a novel bilayer (BL) memristor by integrating a CeO 2 -based memristor with a Co-CeO 2 vertically aligned nanocomposite (VAN) layer and compare it with the single layer (SL) memristor. Preliminary electrical testing reveals that the BL memristor offers a reduced set/reset voltage (~67% lower), a higher on/off ratio (~5 × 10 2 ), enhanced device reliability, and improved device-to-device variation compared to the SL memristor. Insight from COMSOL simulation, coupled with microstructural analysis, provides a comprehensive elucidation on how the VAN layer facilitates the selective conductive filament (CF) formation. Subsequently, the plasticity of the BL memristor is evaluated through long-term potentiation/depression (LTP/LTD), paired-pulse facilitation (PPF), and spike-time-dependent plasticity (STDP). The spiking neural network (SNN) built upon the BL memristor achieves remarkable accuracy (~94%) after only 12 iterations, underscoring its potential for high-performance neural networks.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Emulator-Based Bayesian Calibration of the CISNET Colorectal Cancer Models

Purpose To calibrate Cancer Intervention and Surveillance Modeling Network (CISNET)'s SimCRC, MISCAN-Colon, and CRC-SPIN simulation models of the natural history colorectal cancer (CRC) with an emulator-based Bayesian algorithm and internally validate the model-predicted outcomes to calibration targets.Methods We used Latin hypercube sampling to sample up to 50,000 parameter sets for each CISNET-CRC model and generated the corresponding outputs. We trained multilayer perceptron artificial neural networks (ANNs) as emulators using the input and output samples for each CISNET-CRC model. We selected ANN structures with corresponding hyperparameters (i.e., number of hidden layers, nodes, activation functions, epochs, and optimizer) that minimize the predicted mean square error on the validation sample. We implemented the ANN emulators in a probabilistic programming language and calibrated the input parameters with Hamiltonian Monte Carlo-based algorithms to obtain the joint posterior distributions of the CISNET-CRC models' parameters. We internally validated each calibrated emulator by comparing the model-predicted posterior outputs against the calibration targets.Results The optimal ANN for SimCRC had 4 hidden layers and 360 hidden nodes, MISCAN-Colon had 4 hidden layers and 114 hidden nodes, and CRC-SPIN had 1 hidden layer and 140 hidden nodes. The total time for training and calibrating the emulators was 7.3, 4.0, and 0.66 h for SimCRC, MISCAN-Colon, and CRC-SPIN, respectively. The mean of the model-predicted outputs fell within the 95% confidence intervals of the calibration targets in 98 of 110 for SimCRC, 65 of 93 for MISCAN, and 31 of 41 targets for CRC-SPIN.Conclusions Using ANN emulators is a practical solution to reduce the computational burden and complexity for Bayesian calibration of individual-level simulation models used for policy analysis, such as the CISNET CRC models. In this work, we present a step-by-step guide to constructing emulators for calibrating 3 realistic CRC individual-level models using a Bayesian approach.

artificial neural networks↗
DOE OSTI2025

Coordinated Frequency Regulation in Grid-Forming Storage Network via Safety-Consensus

Inverter-based storages are poised to play a prominent role in future power grid with massive renewable generation. Grid-forming inverters (GFMs) are emerging as a dominant technology with synchronous generators (SG)-like characteristics through primary control loops. Advanced secondary-layer control schemes, e.g., consensus algorithms, allow GFM-interfaced storage units to participate in frequency regulations and restore nominal frequency following grid disturbances. However, it is imperative to ensure critical frequency safety limits are not violated while the grid transitions from pre- to post-disturbance operating point. This paper presents a novel safety-enforced consensus method, having three distinct objectives: safe transient frequency evolution, minimizing frequency deviation, and coordinated power sharing. The proposed technique is illustrated using a GFM-interfaced grid-wide storage network on the IEEE 68-bus system under multiple grid transient scenarios.

consensus control↗
NASA NTRS2004

An Aerosol Extinction-to-Backscatter Ratio Database Derived from the NASA Micro-Pulse Lidar Network: Applications for Space-based Lidar Observations

Backscatter lidar signals are a function of both backscatter and extinction. Hence, these lidar observations alone cannot separate the two quantities. The aerosol extinction-to-backscatter ratio, S, is the key parameter required to accurately retrieve extinction and optical depth from backscatter lidar observations of aerosol layers. S is commonly defined as 4*pi divided by the product of the single scatter albedo and the phase function at 180-degree scattering angle. Values of S for different aerosol types are not well known, and are even more difficult to determine when aerosols become mixed. Here we present a new lidar-sunphotometer S database derived from Observations of the NASA Micro-Pulse Lidar Network (MPLNET). MPLNET is a growing worldwide network of eye-safe backscatter lidars co-located with sunphotometers in the NASA Aerosol Robotic Network (AERONET). Values of S for different aerosol species and geographic regions will be presented. A framework for constructing an S look-up table will be shown. Look-up tables of S are needed to calculate aerosol extinction and optical depth from space-based lidar observations in the absence of co-located AOD data. Applications for using the new S look-up table to reprocess aerosol products from NASA's Geoscience Laser Altimeter System (GLAS) will be discussed.

Welton, Ellsworth J.↗
DOE OSTI2024

Controlled Spalling of 4H Silicon Carbide with Investigated Spin Coherence for Quantum Engineering Integration

We detail scientific and engineering advances which enable the controlled spalling and layer transfer of single crystal 4H silicon carbide (4H-SiC) from bulk substrates. 4HSiC’s properties, including high thermal conductivity and a wide bandgap, make it an ideal semiconductor for power electronics. Moreover, 4H-SiC is an excellent host of solid-state atomic defect qubits for quantum computing and quantum networking. Because 4H-SiC substrates are expensive (due to long growth times and limited yield), techniques for removal and transfer of bulk-quality films are desirable for substrate reuse and integration of the separated films. In this work, we utilize updated approaches for stressor layer thickness control and spalling crack initiation to demonstrate controlled spalling of 4H-SiC, the highest fracture toughness crystal spalled to date. We achieve coherent spin control of neutral divacancy (VV 0 ) qubit ensembles and measure a quasi-bulk spin T 2 of 79.7 μs in the spalled films.

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

Exact block encoding of imaginary time evolution with universal quantum neural networks

We develop a constructive approach to generate quantum neural networks capable of representing the exact thermal states of all many-body qubit Hamiltonians. The Trotter expansion of the imaginary time propagator is implemented through an exact block encoding by means of a unitary, restricted Boltzmann machine architecture. Marginalization over the hidden-layer neurons (auxiliary qubits) creates the nonunitary action on the visible layer. Then, we introduce a unitary deep Boltzmann machine architecture in which the hidden-layer qubits are allowed to couple laterally to other hidden qubits. We prove that this wave-function is closed under the action of the imaginary time propagator and, more generally, can represent the action of a universal set of quantum gate operations. We provide analytic expressions for the coefficients for both architectures, thus enabling exact network representations of thermal states without stochastic optimization of the network parameters. In the limit of large imaginary time, the yields the ground state of the system. The number of qubits grows linearly with the number of interactions and total imaginary time for a fixed interaction order. Both networks can be readily implemented on quantum hardware via midcircuit measurements of auxiliary qubits. If only one auxiliary qubit is measured and reset, the circuit depth scales linearly with imaginary time and number of interactions, while the width is constant. Alternatively, one can employ a number of auxiliary qubits linearly proportional to the number of interactions, and circuit depth grows linearly with imaginary time only. Every midcircuit measurement has a postselection success probability, and the overall success probability is equal to the product of the probabilities of the midcircuit measurements.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Understanding hydrogen electrocatalysis by probing the hydrogen-bond network of water at the electrified Pt–solution interface

Rational construction of the electrode–solution interface where electrochemical processes occur is of paramount importance in electrochemistry. Efforts to gain better control and understanding of the interface have been hindered by lack of probing methods. Here, in this study, we show that the hydrogen evolution and oxidation reactions (HER/HOR) catalysed by platinum in base can be promoted by introduction of N-methylimidazoles at the platinum–water interface. In situ spectroscopic characterization together with simulations indicate that the N-methylimidazoles facilitate diffusion of hydroxides across the interface by holding the second layer of water close to platinum surfaces, thereby promoting the HER/HOR. We thus propose that the HER/HOR kinetics of platinum in acid and base is governed by diffusion of protons and hydroxides, respectively, through the hydrogen-bond network of interfacial water by the Grotthuss mechanism. Moreover, we demonstrate a 40% performance improvement of an anion exchange membrane electrolyser by adding 1,2-dimethylimidazole into the alkali fed into its platinum cathode.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Tokamak edge localized mode onset prediction with deep neural network and pedestal turbulence

Abstract A neural network, BES-ELMnet, predicting a quasi-periodic disruptive eruption of the plasma energy and particles known as edge localized mode (ELM) onset is developed with observed pedestal turbulence from the beam emission spectroscopy system in DIII-D. BES-ELMnet has convolutional and fully-connected layers, taking two-dimensional plasma fluctuations with a temporal window of size 128 µ s and generating a scalar output which can be interpreted as a probability of the upcoming ELM onset. As approximately labeled inter-ELM broadband ( 15 kHz ⩽ f ⩽ 150 kHz ) fluctuations are given to the network, BES-ELMnet learns by itself ELM-related precursors arising before the onsets through supervised learning scheme. BES-ELMnet achieves the gradually increasing ELM onset probabilities between two consecutive ELMs during the inter-ELM phases and can forecast the first ELM onsets which occur after the high confinement mode transition. We further investigate the network generality in terms of the selected frequency band to ensure the use of BES-ELMnet for various operation regimes without changing the trained architecture. Therefore, our novel prediction method will enhance a proactive high confinement mode control of fusion-grade plasmas.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
NASA NTRSDate not supplied

Machine Learning Explainability and Transferability for Path Navigation

Deep neural networks are powerful tools for machine perception. Unfortunately their decisions are difficult to explain due to the complexity and size of the networks. Previously we have alleviated this issue by using the representational portion of a deep neural network and combining it with a k-nearest neighbor (KNN) classifier. Through inspection of the decisions made by the KNN, we can directly see the training data responsible for the decisions, allowing us to determine the quality of the overall decision and the quality of the representational layer of the deep NN. While the technique worked well, it requires tens of thousands of latent vectors to be stored for classification. In addition, it lacks the ability to show how parts of an image influence the classification decision. Here we address these issues by 1) Using a radial basis function network (RBFN) in place of the KNN allowing far fewer images to be used in deployment and 2) Using an auto encoder network for explainability. In addition to these techniques, we examine the effects of transfer learning to determine that results are robust. All results are tested on a domain where an unmanned aerial vehicle (UAV) navigates a forest trail through a single camera.

explainable machine learning↗
DOE OSTI2025

The design space of E(3)-equivariant atom-centred interatomic potentials

Abstract Molecular dynamics simulation is an important tool in computational materials science and chemistry, and in the past decade it has been revolutionized by machine learning. This rapid progress in machine learning interatomic potentials has produced a number of new architectures in just the past few years. Particularly notable among these are the atomic cluster expansion, which unified many of the earlier ideas around atom-density-based descriptors, and Neural Equivariant Interatomic Potentials (NequIP), a message-passing neural network with equivariant features that exhibited state-of-the-art accuracy at the time. Here we construct a mathematical framework that unifies these models: atomic cluster expansion is extended and recast as one layer of a multi-layer architecture, while the linearized version of NequIP is understood as a particular sparsification of a much larger polynomial model. Our framework also provides a practical tool for systematically probing different choices in this unified design space. An ablation study of NequIP, via a set of experiments looking at in- and out-of-domain accuracy and smooth extrapolation very far from the training data, sheds some light on which design choices are critical to achieving high accuracy. A much-simplified version of NequIP, which we call BOTnet (for body-ordered tensor network), has an interpretable architecture and maintains its accuracy on benchmark datasets.

Computer Science↗
DOE OSTI2023

Efficient multi-scale representation of visual objects using a biologically plausible spike-latency code and winner-take-all inhibition

Deep neural networks have surpassed human performance in key visual challenges such as object recognition, but require a large amount of energy, computation, and memory. In contrast, spiking neural networks (SNNs) have the potential to improve both the efficiency and biological plausibility of object recognition systems. Here we present a SNN model that uses spike-latency coding and winner-take-all inhibition (WTA-I) to efficiently represent visual stimuli using multi-scale parallel processing. Mimicking neuronal response properties in early visual cortex, images were preprocessed with three different spatial frequency (SF) channels, before they were fed to a layer of spiking neurons whose synaptic weights were updated using spike-timing-dependent-plasticity. We investigate how the quality of the represented objects changes under different SF bands and WTA-I schemes. We demonstrate that a network of 200 spiking neurons tuned to three SFs can efficiently represent objects with as little as 15 spikes per neuron. Furthermore, studying how core object recognition may be implemented using biologically plausible learning rules in SNNs may not only further our understanding of the brain, but also lead to novel and efficient artificial vision systems.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Electron tomography unravels new insights into fiber cell wall nanostructure; exploring 3D macromolecular biopolymeric nano-architecture of spruce fiber secondary walls

Lignocellulose biomass has a tremendous potential as renewable biomaterials for fostering the “bio-based society” and circular bioeconomy paradigm. It requires efficient use and breakdown of fiber cell walls containing mainly cellulose, hemicellulose and lignin biopolymers. Despite their great importance, there is an extensive debate on the true structure of fiber walls and knowledge on the macromolecular nano-organization is limited and remains elusive in 3D. We employed dual-axis electron tomography that allows visualization of previously unseen 3D macromolecular organization/biopolymeric nano-architecture of the secondary S2 layer of Norway spruce fiber wall. Unprecedented 3D nano-structural details with novel insights into cellulose microfibrils (~2 nm diameter), macrofibrils, nano-pore network and cell wall chemistry (volume %) across the S2 were explored and quantified including simulation of structure related permeability. Matrix polymer association with cellulose varied between microfibrils and macrofibrils with lignin directly associated with MFs. Simulated bio-nano-mechanical properties revealed stress distribution within the S2 and showed similar properties between the idealized 3D model and the native S2 (actual tomogram). Present work has great potential for significant advancements in lignocellulose research on nano-scale understanding of cell wall assembly/disassembly processes leading to more efficient industrial processes of functionalization, valorization and target modification technologies.

3-D reconstruction↗
DOE OSTI2022

Classification and Localization of Fracture-Hit Events in Low-Frequency Distributed Acoustic Sensing Strain Rate with Convolutional Neural Networks

Summary Distributed acoustic sensing (DAS) has been used in the oil and gas industry as an advanced technology for surveillance and diagnostics. Operators use DAS to monitor hydraulic fracturing activities, examine well stimulation efficacy, and estimate complex fracture system geometries. Particularly, low-frequency DAS can detect geomechanical events such as fracture hits because hydraulic fractures propagate and create strain rate variations in the rock. Analysis of DAS data today is mostly done post-job and subject to interpretation methods. However, the continuous and dense data stream generated live by DAS poses the opportunity for more efficient and accurate real-time data-driven analysis. The objective of this study is to develop a machine learning-based workflow that can identify and locate fracture-hit events in simulated strain rate responses correlated with low-frequency DAS data. In this paper, “fracture hit” refers to a hydraulic fracture originating from a stimulated well intersecting an offset well. We start with building a single fracture propagation model to produce strain rate patterns observed at a hypothetical monitoring well. This model is used to generate two sets of strain rate responses with one set containing fracture-hit events. The labeled synthetic data are then used to train a custom convolutional neural network (CNN) model for identifying the presence of fracture-hit events. The same model is trained again for locating the event with the output layer of the model replaced with linear units. We achieved near-perfect predictions for both event classification and localization. These promising results prove the feasibility of using CNN for real-time event detection from fiber-optic sensing data. Additionally, we use edge detection techniques to recognize fracture-hit event patterns in strain rate images. The fracture-hit location can be identified using recognized pixels in the image. The accuracy of edge detection-based location identification is also plausible, but edge detection is dependent on the assumption of pattern shape and image quality, hence it is less robust compared to CNN models. This comparison further supports the need for CNN applications in image-based real-time fiber-optic sensing event detection.

Engineering↗
DOE OSTI2024

Quantifying Variability and Controls of Riverine Dissolved Organic Carbon Exported to Arctic Coastal Margins of North America (Final Report)

This project involved implementation and application of a coupled permafrost hydrology and dissolved organic carbon process models to investigate how spatial and seasonal variations in terrestrial hydrology and soil freeze/thaw dynamics influence the mobilization, loading, and export of organic carbon to the stream network for selected arctic basins across northern Alaska and northwest Canada. The model simulations were constrained by detailed observations of in- stream chemistry, soil active layer profile moisture and temperature dynamics, streamflow, soil carbon inventories and satellite microwave remote sensing based assessments of surface soil freeze-thaw dynamics. We developed and applied the numerical modeling and data analysis, incorporating observed data for calibration and validation, in order to investigate the terrestrial hydrology, permafrost dynamics, and associated DOC production and loading to rivers across a region encompassing watersheds draining to the coast. The project produced six publications and three datasets archived in public repositories.

54 ENVIRONMENTAL SCIENCES↗