Search NASA⌕ Search

SEARCH · Search NASA

Results for “Deep Operator Network”

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 991 records · Page 55
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Trustworthy Physics-Informed Deep Learning for Predictive Scientific Computing

This project has developed powerful trustworthy physics-informed deep learning (TPiDL) models and methods to fundamentally enhance the scale and power of computational modeling in the scientific and engineering domains. Deep learning (DL) has radically advanced the state-of-the-art in machine learning, computer vision, natural language processing, and also scientific computing. Nevertheless, progress has been driven almost entirely by empirical observations, hacks, and tricks. Under the support of this project, the graph operator learning tools and advanced trustworthy physical informed neural networks have been developed. In addition, stochastic gradient replica-exchange Markov Chain Monte Carlo (MCMC) sampling algorithms have been designed to quantify the uncertainties and speed up the training of large-scale neural networks.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1977

Mu-2 ranging

The Mu-II Dual-Channel Sequential Ranging System designed as a model for future Deep Space Network ranging equipment is described. A list of design objectives is followed by a theoretical explanation of the digital demodulation techniques first employed in this machine. Hardware and software implementation are discussed, together with the details relating to the construction of the device. Two appendixes are included relating to the programming and operation of this equipment to yield the maximum scientific data.

Martin, W. L.↗
NASA NTRS2022

A Deep Learning Approach to Fast Radiative Transfer

Due to the sheer volume of data, leveraging satellite instrument observations effectively in a data assimilation context for numerical weather prediction or for remote sensing requires a radiative transfer model as an observation operator that is both fast and accurate at the same time. Physics-based line-by-line radiative transfer (RT) models fulfil the requirement for accuracy, but are too slow and too costly in computational terms for operational applications. Therefore, fast methods were developed to be able to perform fast RT calculations using techniques such as spectral sampling or pre-computed look-up tables. The operational fast models currently calculate the absorption and scattering coefficients from the pre-computed regression coefficients and atmospheric state and cloud profiles. As a novel solution to this problem, this work investigates a deep learning approach to replace the regression coefficients in the fast RT models. A selection of hidden-layer neural network configurations is trained against atmospheric transmittance profile data computed by an accurate line-by-line model and their performance is evaluated and their advantages and disadvantages are discussed.

Machine learning↗
NASA NTRSDate not supplied

Dense Feature Tracking of Atmospheric Winds with Deep Optical Flow

Atmospheric winds are a key physical phenomenon impacting natural hazards, energy transport, ocean currents, large-scale circulation, and ecosystem fluxes. Observing winds is a complex process and presents a large gap in NASA’s Earth Observation System. Atmospheric motion vectors (AMVs) aim to fill this gap by making numerical estimates of cloud movement between sequences of multi-spectral satellite images, tracking clouds and water vapor. Recent imaging hardware and software advancements have enabled the use of numerical optical flow techniques to produce accurate and dense vector fields outperforming traditional methods. This work presents WindFlow as the first machine learning based system for feature tracking atmospheric motion using optical flow. Due to the lack of large-scale satellite-based observations, we leverage high-resolution numerical simulations from NASA's GEOS-5 Nature Run to perform supervised learning and transfer to satellite images. We demonstrate that our approach using deep learning based optical flow scales to ultra-high-resolution images of size 2881x5760 with less than 1 m/s bias and 2.5 m/s average error. Four network and learning architectures are compared and it is found that recurrent all-pairs field transforms (RAFT) produces the lowest errors on all metrics for wind speed and direction. Results on held out numerical outputs shows RAFT's good performance in each of the spatial, temporal, and physical dimensions. A comparison between WindFlow and an operational AMV product against rawinsonde observations show that RAFT transfers across simulations and thermal infrared satellite observations. This work shows that machine learning based optical flow is an efficient approach to generating robust feature tracking for AMVs consistently over large regions.

Atmospheric winds↗
NASA NTRS1987

Results of using the global positioning system to maintain the time and frequency synchronization in the Deep Space Network

There are two hydrogen maser clocks located at each signal processing center (SPC) in the DSN. Close coordination of the time and frequency of the SPC clocks is needed to navigate spacecraft to the outer planets. A recent example was the Voyager spacecraft's encounter with Uranus in January 1986. The clocks were adjusted with the goal of minimizing time and frequency offsets between the SPCs at encounter. How time and frequency at each SPC is estimated using data acquired from the Global Positioning System Timing Receivers operating on the NBS-BIH (National Bureau of Standards-Bureau International de l'Heure) tracking schedule is described. These data are combined with other available timing receiver data to calculate the time offset estimates. The adjustment of the clocks is described. It was determined that long range hydrogen maser drift is quite predictable and adjustable within limits. This enables one to minimize time and frequency differences between the three SPCs for many months by matching the drift rates of the three standards. Data acquisition and processing techniques using a Kalman filter to make estimates of time and frequency offsets between the clocks at the SPCs and UTC(NBS) (Coordinated Universal Time realized at NBS) are described.

Clements, P. A.↗
DOE OSTI2019

Generative Adversarial Network for Synthetic Time Series Data Generation in Smart Grids

The availability of fine grained time series data is a pre-requisite for research in smart-grids. While data for transmission systems is relatively easily obtainable, issues related to data collection, security and privacy hinder the widespread public availability/accessibility of such datasets at the distribution system level. This has prevented the larger research community from effectively applying sophisticated machine learning algorithms to significantly improve the distribution-level accuracy of predictions and increase the efficiency of grid operations. Synthetic dataset generation has proven to be a promising solution for addressing data availability issues in various domains such as computer vision, natural language processing and medicine. However, its exploration in the smart grid context remains unsatisfactory. Previous works have tried to generate synthetic datasets by modeling the underlying system dynamics: an approach which is difficult, time consuming, error prone and often times infeasible in many problems. In this work, we propose a novel data-driven approach to synthetic dataset generation by utilizing deep generative adversarial networks (GAN) to learn the conditional probability distribution of essential features in the real dataset and generate samples based on the learned distribution. To evaluate our synthetically generated dataset, we measure the maximum mean discrepancy (MMD) between real and synthetic datasets as probability distributions, and show that their sampling distance converges. To further validate our synthetic dataset, we perform common smart grid tasks such as k-means clustering and short-term prediction on both datasets. Experimental results show the efficacy of our synthetic dataset approach: the real and synthetic datasets are indistinguishable by solely examining the output of these tasks.

14 SOLAR ENERGY↗
NASA NTRS1996

The Mars Microprobe Mission: A Unique Solution for Network Science

The second deep-space advanced technology validation mission in NASA's New Millenium Program will demonstrate planetary microprobe technologies. Two microporobes, each consisting of a very low-mass aeroshell and penetrator system, are planned to be launched in January 1999 and arrive at at Mars in December 1999... This paper will summarize the engineering techniques that will be implemented to provide safe landing and operation of the Mars microprobe in its unique environment. This paper will also summarize some key mission and system design trades, as well as discuss some of the technologies being developed.

microprobes↗
NASA NTRS2011

Interplanetary Overlay Network Bundle Protocol Implementation

The Interplanetary Overlay Network (ION) system's BP package, an implementation of the Delay-Tolerant Networking (DTN) Bundle Protocol (BP) and supporting services, has been specifically designed to be suitable for use on deep-space robotic vehicles. Although the ION BP implementation is unique in its use of zero-copy objects for high performance, and in its use of resource-sensitive rate control, it is fully interoperable with other implementations of the BP specification (Internet RFC 5050). The ION BP implementation is built using the same software infrastructure that underlies the implementation of the CCSDS (Consultative Committee for Space Data Systems) File Delivery Protocol (CFDP) built into the flight software of Deep Impact. It is designed to minimize resource consumption, while maximizing operational robustness. For example, no dynamic allocation of system memory is required. Like all the other ION packages, ION's BP implementation is designed to port readily between Linux and Solaris (for easy development and for ground system operations) and VxWorks (for flight systems operations). The exact same source code is exercised in both environments. Initially included in the ION BP implementations are the following: libraries of functions used in constructing bundle forwarders and convergence-layer (CL) input and output adapters; a simple prototype bundle forwarder and associated CL adapters designed to run over an IPbased local area network; administrative tools for managing a simple DTN infrastructure built from these components; a background daemon process that silently destroys bundles whose time-to-live intervals have expired; a library of functions exposed to applications, enabling them to issue and receive data encapsulated in DTN bundles; and some simple applications that can be used for system checkout and benchmarking.

Burleigh, Scott C.↗
DOE OSTI2021

Detecting False Data Injection Attacks in Smart Grids: A Semi-Supervised Deep Learning Approach

The dependence on advanced information and communication technology increases the vulnerability in smart grids under cyber-attacks. Recent research on unobservable false data injection attacks (FDIAs) reveals the high risk of secure system operation, since these attacks can bypass current bad data detection mechanisms. To mitigate this risk, this paper proposes a data-driven learning-based algorithm for detecting unobservable FDIAs in distribution systems. We use autoencoders for efficient dimension reduction and feature extraction of measurement datasets. Further, we integrate the autoencoders into an advanced generative adversarial network (GAN) framework, which successfully detects anomalies under FDIAs by capturing the unconformity between abnormal and secure measurements. Also, considering that the datasets collected from practical power systems are partially labeled due to expensive labeling costs and missing labels, the proposed method only requires a few labeled measurement data in addition to unlabeled data for training. Numerical simulations in three-phase unbalanced IEEE 13-bus and 123-bus distribution systems validate the detection accuracy and efficiency of this method.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2012

Development of the Optical Communications Telescope Laboratory: A Laser Communications Relay Demonstration Ground Station

The Laser Communications Relay Demonstration (LCRD) project will demonstrate high bandwidth space to ground bi-directional optical communications links between a geosynchronous satellite and two LCRD optical ground stations located in the southwestern United States. The project plans to operate for two years with a possible extension to five. Objectives of the demonstration include the development of operational strategies to prototype optical link and relay services for the next generation tracking and data relay satellites. Key technologies to be demonstrated include adaptive optics to correct for clear air turbulence-induced wave front aberrations on the downlink, and advanced networking concepts for assured and automated data delivery. Expanded link availability will be demonstrated by supporting operations at small sun-Earth-probe angles. Planned optical modulation formats support future concepts of near-Earth satellite user services to a maximum of 1.244 Gb/s differential phase shift keying modulation and pulse position modulations formats for deep space links at data rates up to 311 Mb/s. Atmospheric monitoring instruments that will characterize the optical channel during the link include a sun photometer to measure atmospheric transmittance, a solar scintillometer, and a cloud camera to measure the line of sight cloud cover. This paper describes the planned development of the JPL optical ground station.

optical commuication↗
NASA NTRSDate not supplied

NASA’s Efforts to Pursue Commercial Communications Services for Missions in Near Space

The National Aeronautics and Space Administration (NASA) Space Communications and Navigation (SCaN) Program enables high speed, robust, secure, and cost-effective space communications and navigation services to current and future science and exploration missions. Consistent with National Space Policy, NASA is seeking commercial services for all its future near-Earth requirements by incorporating additional direct to Earth (DTE) providers and introducing commercial satellite relay communications (SATCOM) vendors as NASA’s Tracking and Data Relay Satellites (TDRS) begin to decline. Through the progression of these efforts, SCaN is also integrating commercial services in the cislunar domain. The overarching objective is to satisfy the demands from the mission community – both in terms of capacity and capability – in a robust, reliable, and cost-effective way, leveraging the strong and growing commercial space sector. For near earth space relay, six SATCOM vendors were awarded Funded Space Act Agreements in June of 2022 to demonstrate the ability to serve near-Earth missions with space-based communication relay services. All six vendors are working through their committed milestones with end-to-end service demonstrations tacking place throughout the mid-2020’s. The failure of TDRS Flight-9 (F9) in late 2022 prompted an increased tempo of mission engagement to identify driving user needs that commercial SATCOM can meet in the near-term. NASA has set a course to accelerate a decision to terminate offering TDRS services to new missions and is developing a plan to execute validation and risk reduction efforts with early adopter “pathfinder” missions, paving the way to operational services. As the Artemis Program matures and builds on the successful Artemis I flight in November-December of 2022, the definition of the supporting communications and navigation architecture has further been refined. Although NASA government assets will continue to play a key role in provision of services, such as through the Deep Space Network, SCaN is pursuing commercial services offerings to expand ground network capability and implement lunar relay services. In February of 2023, SCaN released solicitation for services that include DTE services to missions near-Earth and in cislunar space, as well as lunar relay services. Further, SCaN is seeking opportunities to integrate commercial capability into lunar surface communications infrastructure. NASA is also advocating for standards that promote interoperability and strategic technology investments in the commercial sector. This paper addresses the recent progress and future plans in the near-Earth space and lunar regimes, discusses the unified approach for industry engagement, and highlights both the common and unique challenges of commercialization efforts in the two regimes.

commercial services↗
DOE OSTI2018

Novel deep learning methods for track reconstruction

For the past year, the HEP.TrkX project has been investigating machine learning solutions to LHC particle track reconstruction problems. A variety of models were studied that drew inspiration from computer vision applications and operated on an image-like representation of tracking detector data. While these approaches have shown some promise, image-based methods face challenges in scaling up to realistic HL-LHC data due to high dimensionality and sparsity. In contrast, models that can operate on the spacepoint representation of track measurements ("hits") can exploit the structure of the data to solve tasks efficiently. In this paper we will show two sets of new deep learning models for reconstructing tracks using space-point data arranged as sequences or connected graphs. In the first set of models, Recurrent Neural Networks (RNNs) are used to extrapolate, build, and evaluate track candidates akin to Kalman Filter algorithms. Such models can express their own uncertainty when trained with an appropriate likelihood loss function. The second set of models use Graph Neural Networks (GNNs) for the tasks of hit classification and segment classification. These models read a graph of connected hits and compute features on the nodes and edges. They adaptively learn which hit connections are important and which are spurious. The models are scaleable with simple architecture and relatively few parameters. Results for all models will be presented on ACTS generic detector simulated data.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2021

Fully Convolutional Spatio-Temporal Models for Representation Learning in Plasma Science

We have trained a fully convolutional spatio-temporal model for fast and accurate representation learning in the challenging exemplar application area of fusion energy plasma science. The onset of major disruptions is a critically important fusion energy science issue that must be resolved for advanced tokamak plasmas such as the $25B burning plasma international thermonuclear experimental reactor (ITER) experiment. While a variety of statistical methods have been used to address the problem of tokamak disruption prediction and control, recent approaches based on deep learning have proven particularly compelling. In the present paper, we introduce further improvements to the fusion recurrent neural network (FRNN) software suite, which delivered cross-machine disruption predictions with unprecedented accuracy using a large database of experimental signals from two major tokamaks. Up to now, FRNN was based on the long short-term memory (LSTM) variant of recurrent neural networks to leverage the temporal information in the data. Here, we implement and apply the "temporal convolutional neural network (TCN)" architecture to the time-dependent input signals. Furthermore, this allows highly optimized convolution operations to carry the majority of the computational load of training, thus enabling a reduction in training time, and the effective use of high-performance computing resources for hyperparameter tuning. At the same time, the TCN-based architecture achieves better predictive performance when compared with the LSTM architecture for various tasks for a representative fusion database.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2025

Comprehensive assessment of deep reinforcement learning approaches for economic dispatch in nuclear-driven microgrids

As the electrical grid integrates more variable renewable energy sources such as wind and solar, the demand for distributed and flexible systems to address this increased variability becomes critical. Nuclear-driven microgrids provide a promising solution by offering stable generation to complement intermittent renewables, ensuring grid reliability and operating efficiency. This paper proposes a recurrent deep reinforcement learning framework for optimal economic dispatch in a nuclear-powered microgrid integrating renewable energy sources, small modular reactors, battery storage systems, and balance-of-plant dynamics. A three-agent control architecture is developed, where demand and renewable energy agents act as forecasters, and a reinforcement learning-based dispatch agent performs real-time energy allocation. A nonlinear programming formulation is first used to generate an optimal baseline for benchmarking. The proposed dispatch controller, based on Proximal Policy Optimization enhanced with Long Short-Term Memory networks, exploits temporal correlations in system dynamics by taking advantage of the time series used as inputs to improve policy robustness under uncertainty. Comparative analysis against established deep reinforcement learning methods, including Proximal Policy Optimization with a feedforward architecture, Soft Actor-Critic, and Twin Delayed Deep Deterministic Policy Gradient, demonstrates superior performance. Numerical results indicate that the proposed controller achieves a 0.39% cost reduction relative to the nonlinear programming benchmark and outperforms other learning-based methods by generating additional revenue of up to 0.35%. All reinforcement learning controllers compute dispatch actions in less than 0.3 s, resulting in a computational speedup of more than three orders of magnitude over the nonlinear programming baseline. The findings of this paper highlight their applicability for real-time operation and control in nuclear-integrated microgrids under volatile operating conditions.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS2011

Licklider Transmission Protocol Implementation

This software is an implementation of the Licklider Transmission Protocol (LTP), a communications protocol intended to support the Bundle Protocol in Delay-Tolerant Network (DTN) operations. LTP is designed to provide retransmission-based reliability over links characterized by extremely long message round-trip times and/or frequent interruptions in connectivity. Communication in interplanetary space is the most prominent example of this sort of environment, and LTP is principally aimed at supporting long-haul reliable transmission over deep-space RF links. Like any reliable transport service employing ARQ (Automatic Repeat re-Quests), LTP is stateful. In order to assure the reception of a block of data it has sent, LTP must retain for possible retransmission all portions of that block which might not have been received yet. In order to do so, it must keep track of which portions of the block are known to have been received so far, and which are not, together with any additional information needed for purposes of retransmitting part, or all, of the block. Long round-trip times mean substantial delay between the transmission of a block of data and the reception of an acknowledgement from the block s destination, signaling arrival of the block. If LTP postponed transmission of additional blocks of data until it received acknowledgement of the arrival of all prior blocks, valuable opportunities to use what little deep space transmission bandwidth is available would be forever lost. For this reason, LTP is based in part on a notion of massive state retention. Any number of requested transmission conversations (sessions) may be concurrently in flight at various displacements along the link between two LTP engines, and the LTP engines must necessarily retain transmission status and retransmission resources for all of them. Moreover, if any of the data of a given block are lost en route, it will be necessary to retain the state of that transmission during an additional round trip while the lost data are retransmitted; even multiple retransmission cycles may be necessary. LTP's possible multiplicity of sessions per association makes it necessary for each segment of application data to include an additional demultiplexing token: a session ID that uniquely identifies the session in which the segment was issued and, implicitly, the block of data being conveyed by this session. This software comprises a prototype implementation developed by Johns Hopkins University APL in cooperation with JPL, together with adaptations that improve the robustness, correctness, and operability of that implementation.

Burleigh, Scott C.↗
NASA NTRS2017

Cassini Spacecraft Strategy for Recovering from a Complete Loss-Of-Signal Condition

Unlike other faults where the space craft’s automated Fault Protection (FP) routines can be relied upon to provide a carrier signal and telemetered data to the ground-based Spacecraft Operations Flight Support (SOFS) team to facilitate vehicle acquisition, diagnosis, and fault recovery, a complete Loss-of-Spacecraft-Signal (LOS) condition will yield no information at all to help re-acquire the vehicle and resolve the fault. For any FP response activation, the spacecraft’s downlink signal must be acquired via the Deep Space Network (DSN) on the expected (post-fault) Radio Frequency Subsystem (RFS) device configuration commanded by the FP; data that will not be attainable in the case of a complete LOS condition since there is no signal available for the ground station to lock onto. In the case of the Cassini Mission-to-Saturn spacecraft, numerous fault possibilities exist that can cause a LOS condition. Activations of the onboard RFS-related FP can reconfigure the post-fault RFS states, impeding the ground team’s ability to acquire the spacecraft’s downlink signal

Morgan, Paula S.↗
DOE OSTI2018

GoldenEye: stream-based network packet inspection using GPUs

High-performance packet analysis systems have attracted great interest as tools to deal with security concerns in high-speed networks. Recently, researchers have utilized GPUs to improve packet processing performance. However, most existing work has been targeted at per-packet analysis level. Flow-centric operations have been challenging for GPUs because they require sequential operations and large buffers for flow reassembly. In this work, we present the GoldenEye GPU Packet Processing System (GoldenEye), a deep packet inspection (DPI) system that tracks out-of-order TCP packets and provides streambased signature matching. When a batch of packets arrives, GoldenEye sorts packets into flow-reassembled streams and normalizes retransmission through a GPU-implemented reordering module. For signatures that straddle batch boundaries, GoldenEye couples a small set of metadata with a functionallyequivalent minimal regular expression retrieval algorithm to connect the partial matches. Results show that GoldenEye can reassemble tens of millions of packets/sec and conduct stateful DPI operations on TCP streams at multi-ten Gbit/sec rates.

97 MATHEMATICS AND COMPUTING↗
NASA NTRSDate not supplied

Advances in High-rate Delay Tolerant Networking On-board the International Space Station

The High-rate Delay Tolerant Networking (HDTN) project at the NASA John H. Glenn Research Center (GRC) is developing a performance optimized Delay Tolerant Networking (DTN) implementation which is able to provide reliable multigigabit per second automated network communications for near-Earth and deep space missions. To that end, this paper provides an overview of the testing and integration efforts culminating in a high-rate DTN demonstration onboard the International Space Station (ISS). Over several years, the HDTN team has performed a series of end-to-end tests between the Software Development and Integration Laboratory (SDIL) at the Lyndon B. Johnson Space Center (JSC) and Marshall Space Flight Center’s Huntsville Operations Support Center (HOSC). The testing has focused on a realistic emulation of the ISS Ku-band RF link, which operates at a maximum of 500 Mbps downlink with a 600 ms round-trip time. In this environment, the HDTN onboard gateway has been tested for interoperability with ISS payload nodes and the DTN ground gateway, store and forward capability, reliable transport using the Licklider Transmission Protocol (LTP), and successful recovery from unexpected loss of signal. In addition to integration testing, HDTN has developed a series of software engineering practices to ensure the stability and maturity of the implementation. As the result, HDTN has successfully demonstrated high-rate DTN services onboard the ISS. This paper concludes with a summary of preliminary flight testing results from the Integrated LCRD LEO User Modem and Amplifier Terminal networking experiments.

Delay tolerant networking↗