Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Deep Operator 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 1,297 records · Page 72
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Topology-Aware Reinforcement Learning for Voltage Control: Centralized and Decentralized Strategies

Volt-VAR control (VVC) methods based on deep reinforcement learning (DRL) can effectively control distribution grid voltage and minimize power loss by implementing corrective and preventive control measures on the reactive power output of inverter-based distributed energy resources (DERs). However, model-free DRL-based VVC approaches usually cannot capture the important topological feature of the power system since they use a fully-connected network (FCN) to deliver the action. Therefore, this paper proposes a graph convolutional network (GCN)-based DRL approach that can employ the topological information of the network to take better control action for regulating the voltage. Our implementation allows for both centralized and decentralized configurations, utilizing a single agent and multiple agents respectively. Although the centralized GCN-based DRL approach has its advantages of minimizing voltage fluctuation and power loss, it is not suitable for large scale power systems due to its challenges in terms of scalability, computation speed and potential single points of failure. Therefore, these problems can be resolved using the decentralized GCN-based DRL approach. Moreover, to ensure the safe operation of the model, our proposed approach incorporates an exponential barrier function while formulating the reward function for each agent. To validate performance of the proposed approaches, the proposed model is tested on modified IEEE test systems and the performances are measured in terms on voltage fluctuation reduction, minimization of power loss and computational speed. Finally, the results show that the proposed topology-aware approach outperforms the FCN-based DRL approach in terms of reducing voltage fluctuation and minimizing power loss of the network. Moreover, it is shown that the decentralized GCN-based DRL has faster computational speed than other approaches.

42 ENGINEERING↗
NASA NTRSDate not supplied

NASA’s Evolving Ka-Band Network Capabilities to Meet Mission Demand

Space missions are increasingly demanding higher data rates to support the growth in information-intensive mission operations. This growth is reflected in planned and operational missions from low Earth orbit, such as the upcoming NASA-Indian Space Research Organization (ISRO) Synthetic Aperture Radar (NISAR) and Plankton, Aerosol, Cloud and Ocean Ecosystem (PACE) missions, to the future Artemis lunar campaign, and the recently launched James Webb Space Telescope (JWST) orbiting at the Sun-Earth L2 Lagrange point. JWST was the first L2 mission to be defined as a high data rate mission transmitting at 28 Megabits per second (Mbps), or 270 Gigabits of science data per day. ISRO and PACE anticipate achieving data throughputs of 5-40 Terabits per day. These data rates exceed the capabilities of S-band and X-band frequency allocations and are a key driver for migrating to the 26 GHz Ka-band frequency allocation. The NASA Space Communications and Navigation (SCaN) program has been preparing the networks to support this demand by pursuing critical Ka-band infrastructure. The status of current and evolving network capability, including the Near Space Network’s Initiative for Ka-band Advancement (NIKA), and the Deep Space Network’s Lunar Exploration Upgrades (DLEU), as well as profiling mission usage of Ka-band services, are discussed in detail. The push toward Kaband, is not only an opportunity for increased performance, but alleviates current challenges with contentious and cluttered spectrum access in S- and X-band. The paper provides an overview of these advantages and advanced techniques that optimize its use before the transition to optical communications becomes an imperative. The challenges and potential mitigations for missions considering selection of Ka-band network services are also discussed.

Ka-band↗
DOE OSTI2024

Seismic Monitoring near Ithaca, New York, Reveals Nonuniform Distribution of Microseismicity in an Intraplate Region

Abstract Cornell University intends to use a deep direct-use geothermal system to heat its Ithaca, New York, campus. In preparation for this project, the Cornell Seismic Network has been monitoring the background seismicity in this intraplate region since 2019. From January 2020 to June 2023, 95 events were detected within 20 km of the proposed geothermal well site, with local magnitudes ranging from −1.02 to 0.56. None of these events appear in regional or national catalogs. Events locate in a narrow geographic band, with one-fourth exhibiting multimodal hypocentral probability peaks both near the surface and at 1–4 km depth. We relocate events with a joint hypocenter and 1D velocity model inversion, in addition to a fully nonlinear method, and then compare observations with synthetic waveforms. Together, these approaches provide strong evidence for >95% of events locating at the surface or within the 3-km-thick sedimentary sequence. We explore how anthropogenic activity and regional topographic stress may contribute to frequent surficial events. This information is critical for characterizing the background microseismicity for comparison during future geothermal operations. Ithaca’s geology of Paleozoic sediments overlying Precambrian crystalline basement is typical of many continental interiors, so these results also provide insight into intraplate microseismicity patterns.

Geochemistry & Geophysics↗
NASA NTRS2009

Ka-Band High-Rate Telemetry System Upgrade for the NASA Deep Space Network

The NASA Deep Space Network (DSN) has a new requirement to support high-data-rate Category A (Cat A) missions (within 2 million kilometers of Earth) with simultaneous S-band uplink, S-band downlink and Ka-band downlink. The S-band links are required for traditional TT&C (Telemetry, Tracking, and Command) support to the spacecraft, while the Ka-band link is intended for high-data-rate science returns. The new Ka-band system combines the use of proven DSN cryogenic designs, for low system temperature, and high data rate capability using commercial telemetry receivers. The initial Cat A support is required for the James Webb Space Telescope (JWST) in 2013 and possibly other missions. The upgrade has been implemented into 3 different 34-meter Beam Waveguide (BWG) antennas in the DSN, one at each of the complexes in Canberra (Australia), Goldstone (California) and Madrid (Spain). System test data is presented to show that the requirements were met and the DSN is ready for Cat A Ka-band operational support.

space communications↗
DOE OSTI2021

Prediction of DIII-D Pedestal Structure From Externally Controllable Parameters

The sharp increase of pressure at the edge of a high confinement mode (H-mode) plasma, the pedestal, strongly impacts overall plasma performance. Predicting the pedestal is a necessity to control and optimize tokamak operations. Here, an experimental data-driven machine learning (ML) approach is presented that predicts the pedestal heights and widths of electron density (n e ) and electron temperature (T e ) profiles as well as the separatrix ne from externally controllable parameters such as the plasma shape, heating method and power, and gas puff rate and integrated gas puff. The OMFIT framework was used with DIII-D data to efficiently, robustly, and automatically build a database of pedestal parameters to train machine learning models. Database creation was enabled by the search engine tool for DIII-D data, TokSearch, which parallelizes data fetching, enabling fast searches through basic signals of thousands of DIII-D shots and selection of relevant time intervals. Principal Component Analysis (PCA) separated the database into three clusters that represent classes of plasma shapes that are regularly used in DIII-D. The most important parameters for setting the pedestal structure were plasma current (I p ), toroidal magnetic field (B Φ ), neutral beam heating power (P NBI ) and shaping quantities. The Deep Jointly Informed Neural Networks (DJINN) algorithm was applied to identify suitable neural network (NN) architectures that appropriately capture the features of the pedestal database. Separate NNs were implemented for each pedestal parameter, and ensembling methods were used to improve the prediction accuracy and allowed estimation of the prediction uncertainty. The pedestal predictions of the test dataset lie within the measurement uncertainties of the pedestal parameters. The NN outperformed simple Linear Regression (LR) analysis, indicating non-linear dependencies in the pedestal structure. The presented achievements illustrate a promising path for future research, using feature extraction to infer experimental trends and thereby improve pedestal models as well as deploying NN for a fast pedestal prediction in DIII-D scenario development.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2023

A Theoretical Open Architecture Framework and Technology Stack for Digital Twins in Energy Sector Applications

Digital twin is often viewed as a technology that can assist engineers and researchers make data-driven system and network-level decisions. Across the scientific literature, digital twins have been consistently theorized as a strong solution to facilitate proactive discovery of system failures, system and network efficiency improvement, system and network operation optimization, among others. With their strong affinity to the industrial metaverse concept, digital twins have the potential to offer high-value propositions that are unique to the energy sector stakeholders to realize the true potential of physical and digital convergence and pertinent sustainability goals. Although the technology has been known for a long time in theory, its practical real-world applications have been so far limited, nevertheless with tremendous growth projections. In the energy sector, there have been theoretical and lab-level experimental analysis of digital twins but few of those experiments resulted in real-world deployments. There may be many contributing factors to any friction associated with real-world scalable deployment in the energy sector such as cost, regulatory, and compliance requirements, and measurable and comparable methods to evaluate performance and return on investment. Those factors can be potentially addressed if the digital twin applications are built on the foundations of a scalable and interoperable framework that can drive a digital twin application across the project lifecycle: from ideation to theoretical deep dive to proof of concept to large-scale experiment to real-world deployment at scale. This paper is an attempt to define a digital twin open architecture framework that comprises a digital twin technology stack (D-Arc) coupled with information flow, sequence, and object diagrams. Those artifacts can be used by energy sector engineers and researchers to use any digital twin platform to drive research and engineering. This paper also provides critical details related to cybersecurity aspects, data management processes, and relevant energy sector use cases.

Gourisetti, Sri, Nikhil Gupta (ORCID:0000000188778↗
NASA NTRS2008

NASA Tech Briefs, November 2008

Topics covered include: Digital Phase Meter for a Laser Heterodyne Interferometer; Vision System Measures Motions of Robot and External Objects; Advanced Precipitation Radar Antenna to Measure Rainfall From Space; Wide-Band Radar for Measuring Thickness of Sea Ice; Vertical Isolation for Photodiodes in CMOS Imagers; Wide-Band Microwave Receivers Using Photonic Processing; L-Band Transmit/Receive Module for Phase-Stable Array Antennas; Microwave Power Combiner/Switch Utilizing a Faraday Rotator; Compact Low-Loss Planar Magic-T; Using Pipelined XNOR Logic to Reduce SEU Risks in State Machines; Quasi-Optical Transmission Line for 94-GHz Radar; Next Generation Flight Controller Trainer System; Converting from DDOR SASF to APF; Converting from CVF to AAF; Documenting AUTOGEN and APGEN Model Files; Sequence History Update Tool; Extraction and Analysis of Display Data; MRO DKF Post-Processing Tool; Rig Diagnostic Tools; MRO Sequence Checking Tool; Science Activity Planner for the MER Mission; UAVSAR Flight-Planning System; Templates for Deposition of Microscopic Pointed Structures; Adjustable Membrane Mirrors Incorporating G-Elastomers; Hall-Effect Thruster Utilizing Bismuth as Propellant; High-Temperature Crystal-Growth Cartridge Tubes Made by VPS; Quench Crucibles Reinforced with Metal; Deep-Sea Hydrothermal-Vent Sampler; Mars Rocket Propulsion System; Two-Stage Passive Vibration Isolator; Improved Thermal Design of a Compression Mold; Enhanced Pseudo-Waypoint Guidance for Spacecraft Maneuvers; Altimetry Using GPS-Reflection/Occultation Interferometry; Thermally Driven Josephson Effect; Perturbation Effects on a Supercritical C7H16/N2 Mixing Layer; Gold Nanoparticle Labels Amplify Ellipsometric Signals; Phase Matching of Diverse Modes in a WGM Resonator; WGM Resonators for Terahertz-to-Optical Frequency Conversion; Determining Concentration of Nanoparticles from Ellipsometry; Microwave-to-Optical Conversion in WGM Resonators; Four-Pass Coupler for Laser-Diode-Pumped Solid-State Laser; Low-Resolution Raman-Spectroscopy Combustion Thermometry; Temperature Sensors Based on WGM Optical Resonators; Varying the Divergence of Multiple Parallel Laser Beams; Efficient Algorithm for Rectangular Spiral Search; Algorithm-Based Fault Tolerance Integrated with Replication; Targeting and Localization for Mars Rover Operations; Terrain-Adaptive Navigation Architecture; Self-Adjusting Hash Tables for Embedded Flight Applications; Schema for Spacecraft-Command Dictionary; Combined GMSK Communications and PN Ranging; System-Level Integration of Mass Memory; Network-Attached Solid-State Recorder Architecture; Method of Cross-Linking Aerogels Using a One-Pot Reaction Scheme; An Efficient Reachability Analysis Algorithm.

Source record↗
NASA NTRS2017

Multi-Objective Reinforcement Learning-Based Deep Neural Networks for Cognitive Space Communications

Future communication subsystems of space exploration missions can potentially benefit from software-defined radios (SDRs) controlled by machine learning algorithms. In this paper, we propose a novel hybrid radio resource allocation management control algorithm that integrates multi-objective reinforcement learning and deep artificial neural networks. The objective is to efficiently manage communications system resources by monitoring performance functions with common dependent variables that result in conflicting goals. The uncertainty in the performance of thousands of different possible combinations of radio parameters makes the trade-off between exploration and exploitation in reinforcement learning (RL) much more challenging for future critical space-based missions. Thus, the system should spend as little time as possible on exploring actions, and whenever it explores an action, it should perform at acceptable levels most of the time. The proposed approach enables on-line learning by interactions with the environment and restricts poor resource allocation performance through virtual environment exploration. Improvements in the multiobjective performance can be achieved via transmitter parameter adaptation on a packet-basis, with poorly predicted performance promptly resulting in rejected decisions. Simulations presented in this work considered the DVB-S2 standard adaptive transmitter parameters and additional ones expected to be present in future adaptive radio systems. Performance results are provided by analysis of the proposed hybrid algorithm when operating across a satellite communication channel from Earth to GEO orbit during clear sky conditions. The proposed approach constitutes part of the core cognitive engine proof-of-concept to be delivered to the NASA Glenn Research Center SCaN Testbed located onboard the International Space Station.

space archtiecture↗
NASA NTRS2017

Multi-Objective Reinforcement Learning-based Deep Neural Networks for Cognitive Space Communications

Future communication subsystems of space exploration missions can potentially benefit from software-defined radios (SDRs) controlled by machine learning algorithms. In this paper, we propose a novel hybrid radio resource allocation management control algorithm that integrates multi-objective reinforcement learning and deep artificial neural networks. The objective is to efficiently manage communications system resources by monitoring performance functions with common dependent variables that result in conflicting goals. The uncertainty in the performance of thousands of different possible combinations of radio parameters makes the trade-off between exploration and exploitation in reinforcement learning (RL) much more challenging for future critical space-based missions. Thus, the system should spend as little time as possible on exploring actions, and whenever it explores an action, it should perform at acceptable levels most of the time. The proposed approach enables on-line learning by interactions with the environment and restricts poor resource allocation performance through virtual environment exploration. Improvements in the multiobjective performance can be achieved via transmitter parameter adaptation on a packet-basis, with poorly predicted performance promptly resulting in rejected decisions. Simulations presented in this work considered the DVB-S2 standard adaptive transmitter parameters and additional ones expected to be present in future adaptive radio systems. Performance results are provided by analysis of the proposed hybrid algorithm when operating across a satellite communication channel from Earth to GEO orbit during clear sky conditions. The proposed approach constitutes part of the core cognitive engine proof-of-concept to be delivered to the NASA Glenn Research Center SCaN Testbed located onboard the International Space Station.

space archtiecture↗
DOE OSTI2025

Enhancing Automotive Intrusion Detection Through Multi-Modal Fusion: A CAN FD-LiDAR Approach

As vehicles become smarter and more autonomous, they increasingly depend on advanced sensors and communication technologies to operate securely. However, such growing dependence on technology—whether it’s CAN (Controller Area Network) for internal communication or LiDAR (Light Detection and Ranging) for sensing the world around them—also expands the attack surface for the types of cyber attacks. Traditional intrusion detection systems (IDS) typically monitor these systems in isolation, limiting their ability to detect sophisticated, crosssystem attacks. To address this, we propose a multi-modal fusion approach that combines real-world CAN FD signals (from the HCRL dataset) with LiDAR features (from the nuScenes dataset) to enhance attack detection. Our method employs a twostage ensemble approach. Calibrated XGBoost and LightGBM models initially process CAN FD (Fuzzing Data) and LiDAR data independently, detecting timing anomalies and space abnormalities. They are subsequently logarithmically combined with a logistic regression meta-model along with 17 engineered features capturing cross-modal behavior, prediction conflicts, and nonlinear interactions. This approach achieves an AUC of 0.87 and an F1-score of 0.82, surpassing single-modality baselines and early fusion methods, at merely 2 ms inference latency. Compared with deep learning competitors, it is 3 times more efficient, providing a lightweight, interpretable, and real time solution to automotive cybersecurity.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2019

Scale-Up of the Carbon Dioxide Removal by Ionic Liquid Sorbent (CDRILS) System

The Carbon Dioxide Removal by Ionic Liquid Sorbent (CDRILS) system is designed for efficient, safe and reliable carbon dioxide (CO2) removal from cabin air on long-duration missions to the Moon, deep space, and Mars. CDRILS integrates an ionic liquid sorbent with hollow fiber membrane contactors for rapid CO2 removal and recovery. The liquid-based system provides continuous CO2 delivery, which avoids complicated valve networks to switch between absorbing and desorbing beds and enables simpler integration to the Sabatier without the need for the CO2 Management System (CMS). Ionic liquids are particularly desirable as liquid absorbents for space applications since they are non-volatile, non-odorous, and have high oxidative stability. The hollow fiber membrane contactors offer both high contact area and rigorous containment between the gas and liquid phases in a microgravity environment. Scale-up of the CDRILS technology has presented a series of fascinating challenges, since the interaction between hollow fiber properties, ionic liquid properties and performance is complex. Properties measured with lab-scale hollow fiber contactors are used to estimate the performance of contactors that are similar in scale to flight-scale demonstrations. To accomplish this, component and system models have been built to relate the key scrubber and stripper design and operating variables with performance, and experiments directed to validate the models have been performed. System size, weight and power are determined by component selection, arrangement, and operating conditions. Reliability will be extremely important for any long-range mission and depends on the stability of the ionic liquids and hollow fiber contactors. We report on our continuing long term stability experiments for the ionic liquid and contactor materials and our investigation of the physical properties of additional ionic liquids.

Yates, Stephen F.↗
DOE OSTI2023

Frost prediction using machine learning and deep neural network models

This study describes accurate, computationally efficient models that can be implemented for practical use in predicting frost events for point-scale agricultural applications. Frost damage in agriculture is a costly burden to farmers and global food security alike. Timely prediction of frost events is important to reduce the cost of agricultural frost damage and traditional numerical weather forecasts are often inaccurate at the field-scale in complex terrain. In this paper, we developed machine learning (ML) algorithms for the prediction of such frost events near Alcalde, NM at the point-scale. ML algorithms investigated include deep neural network, convolution neural networks, and random forest models at lead-times of 6–48 h. Our results show promising accuracy (6-h prediction RMSE = 1.53–1.72°C) for use in frost and minimum temperature prediction applications. Seasonal differences in model predictions resulted in a slight negative bias during Spring and Summer months and a positive bias in Fall and Winter months. Additionally, we tested the model transferability by continuing training and testing using data from sensors at a nearby farm. We calculated the feature importance of the random forest models and were able to determine which parameters provided the models with the most useful information for predictions. We determined that soil temperature is a key parameter in longer term predictions (>24 h), while other temperature related parameters provide the majority of information for shorter term predictions. The model error compared favorable to previous ML based frost studies and outperformed the physically based High Resolution Rapid Refresh forecasting system making our ML-models attractive for deployment toward real-time monitoring of frost events and damage at commercial farming operations.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2018

Command and Control Software Development

As NASA’s role in spaceflight operations change, so too does its design priorities. NASA’s flagship venture, the Space Launch System (SLS), is being created primarily to explore deep space. While commercial partners conduct low Earth orbit resupplies, tests, and even transportation of astronauts, NASA can divert more resources to more exciting projects - going back to the moon, or onwards to Mars. In the short term, this goal manifests in the upcoming Exploration Mission-1 (EM-1) test of the SLS, slated for as early as 2019. SLS, with the Orion capsule, will travel farther than any human-rated spacecraft has gone before. As the most powerful launch vehicle ever created, SLS requires many new innovations to ensure mission success. One such technology is the launch control software, which is the focus of this internship. The SLS launch control software is composed of many functions, all of which require rigorous testing to meet the standard of life-critical code. To facilitate easier testing, the first project I undertook was to customize the open-source tool Wireshark to the software team’s needs. Wireshark is a network protocol analyzer that can take in information about custom information packets. The launch control software will have several protocols that are custom to NASA. I ensured that all necessary component files were the correct file type and in the correct structure for Wireshark to compile. Having allowed Wireshark access to understand custom NASA data packets, testers of the launch control software will be able to find anomalies easier.

Wang, Zhengdong↗
NASA NTRS1998

RIACS

The Research Institute for Advanced Computer Science (RIACS) was established by the Universities Space Research Association (USRA) at the NASA Ames Research Center (ARC) on June 6, 1983. RIACS is privately operated by USRA, a consortium of universities that serves as a bridge between NASA and the academic community. Under a five-year co-operative agreement with NASA, research at RIACS is focused on areas that are strategically enabling to the Ames Research Center's role as NASA's Center of Excellence for Information Technology. Research is carried out by a staff of full-time scientist,augmented by visitors, students, post doctoral candidates and visiting university faculty. The primary mission of RIACS is charted to carry out research and development in computer science. This work is devoted in the main to tasks that are strategically enabling with respect to NASA's bold mission in space exploration and aeronautics. There are three foci for this work: Automated Reasoning. Human-Centered Computing. and High Performance Computing and Networking. RIACS has the additional goal of broadening the base of researcher in these areas of importance to the nation's space and aeronautics enterprises. Through its visiting scientist program, RIACS facilitates the participation of university-based researchers, including both faculty and students, in the research activities of NASA and RIACS. RIACS researchers work in close collaboration with NASA computer scientists on projects such as the Remote Agent Experiment on Deep Space One mission, and Super-Resolution Surface Modeling.

Moore, Robert C.↗
DOE OSTI2024

Complex Structure of Molten FLiBe (2 Li F – Be F 2 ) Examined by Experimental Neutron Scattering, X-Ray Scattering, and Deep-Neural-Network Based Molecular Dynamics

The use of molten salts as coolants, fuels, and tritium breeding blankets in the next generation of fission and fusion nuclear reactors benefits from furthering the characterization of the molecular structure of molten halide salts, paving the way to predictive capability of the chemical and thermophysical properties of molten salts. Due to its neutronic, chemical, and thermochemical properties, 2 Li F - Be F 2 is a candidate molten salt for several fusion- and fission-reactor designs. We performed neutron and x-ray total-scattering measurements to determine the atomic structure of liquid 2 Li F - Be F 2 . We also performed and neural-network molecular-dynamics simulations to predict the structure obtained by neutron- and x-ray-diffraction experiments. The use of machine learning provides improvements to the efficiency in predicting the structure at a longer length scales than is achievable with simulations at significantly lower computational expense while retaining near accuracy. We found that the NNMD simulations accurately predicted the Be F 4 2 − oligomer formations seen in the experimental first-structure-factor peak. Our combination of high-resolution measurements with large-scale molecular dynamics provided an avenue to explore and experimentally verify the intermediate-range ordering beyond the first-nearest neighbor that has posed too many experimental and computational challenges in previous works. With a deeper understanding of the salt structure and ion ordering, the evolution of salt chemistry over the lifetime of a reactor can be better predicted, which is crucial to the licensing and operation of advanced fission and fusion reactors that employ molten salts. To this end, this work will serve as a reference for future studies of salt structure and macroscopic properties with and without the addition of solutes. Published by the American Physical Society 2024

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2021

A domain wall-magnetic tunnel junction artificial synapse with notched geometry for accurate and efficient training of deep neural networks

Inspired by the parallelism and efficiency of the brain, several candidates for artificial synapse devices have been developed for neuromorphic computing, yet a nonlinear and asymmetric synaptic response curve precludes their use for backpropagation, the foundation of modern supervised learning. Spintronic devices—which benefit from high endurance, low power consumption, low latency, and CMOS compatibility—are a promising technology for memory, and domain-wall magnetic tunnel junction (DW-MTJ) devices have been shown to implement synaptic functions such as long-term potentiation and spike-timing dependent plasticity. In this work, we propose a notched DW-MTJ synapse as a candidate for supervised learning. Using micromagnetic simulations at room temperature, we show that notched synapses ensure the non-volatility of the synaptic weight and allow for highly linear, symmetric, and reproducible weight updates using either spin transfer torque (STT) or spin–orbit torque (SOT) mechanisms of DW propagation. We use lookup tables constructed from micromagnetics simulations to model the training of neural networks built with DW-MTJ synapses on both the MNIST and Fashion-MNIST image classification tasks. Accounting for thermal noise and realistic process variations, the DW-MTJ devices achieve classification accuracy close to ideal floating-point updates using both STT and SOT devices at room temperature and at 400 K. Our work establishes the basis for a magnetic artificial synapse that can eventually lead to hardware neural networks with fully spintronic matrix operations implementing machine learning.

42 ENGINEERING↗
DOE OSTI2021

Charged Particle Tracking via Edge-Classifying Interaction Networks

Recent work has demonstrated that geometric deep learning methods such as graph neural networks (GNNs) are well suited to address a variety of reconstruction problems in high-energy particle physics. In particular, particle tracking data are naturally represented as a graph by identifying silicon tracker hits as nodes and particle trajectories as edges, given a set of hypothesized edges, edge-classifying GNNs identify those corresponding to real particle trajectories. In this work, we adapt the physics-motivated interaction network (IN) GNN toward the problem of particle tracking in pileup conditions similar to those expected at the high-luminosity Large Hadron Collider. Assuming idealized hit filtering at various particle momenta thresholds, we demonstrate the IN’s excellent edge-classification accuracy and tracking efficiency through a suite of measurements at each stage of GNN-based tracking: graph construction, edge classification, and track building. The proposed IN architecture is substantially smaller than previously studied GNN tracking architectures; this is particularly promising as a reduction in size is critical for enabling GNN-based tracking in constrained computing environments. Furthermore, the IN may be represented as either a set of explicit matrix operations or a message passing GNN. Efforts are underway to accelerate each representation via heterogeneous computing resources towards both high-level and low-latency triggering applications.

accelerator physics↗
DOE OSTI2022

Hardware-accelerated inference for real-time gravitational-wave astronomy

The field of transient astronomy has seen a revolution with the first gravitational-wave detections and the arrival of multi-messenger observations they enabled. Transformed by the first detection of binary black hole and binary neutron star mergers, computational demands in gravitational-wave astronomy are expected to grow by at least a factor of two over the next five years as the global network of kilometer-scale interferometers are brought to design sensitivity. With the increase in detector sensitivity, real-time delivery of gravitational-wave alerts will become increasingly important as an enabler of multi-messenger followup. In this work, we report a novel implementation and deployment of deep learning inference for real-time gravitational-wave data denoising and astrophysical source identification. This is accomplished using a generic Inference-as-a-Service model that is capable of adapting to the future needs of gravitational-wave data analysis. Overall, our implementation allows seamless incorporation of hardware accelerators and also enables the use of commercial or private (dedicated) as-a-service computing. Based on our results, we propose a paradigm shift in low-latency and offline computing in gravitational-wave astronomy. Such a shift can address key challenges in peak-usage, scalability and reliability, and provide a data analysis platform particularly optimized for deep learning applications. The achieved sub-millisecond scale latency will also be relevant for any machine learning-based real-time control systems that may be invoked in the operation of near-future and next generation ground-based laser interferometers, as well as the front-end collection, distribution and processing of data from such instruments.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗