Results for “Deep Operator Networks” — Page 55

NASA NTRS1990

An 8.4-GHz dual-maser front-end system for Parkes reimplementation

An 8.4-GHz front-end system consisting of a feedhorn, a waveguide feed assembly, dual masers, and downconverters was reimplemented at Parkes as part of the Parkes Canberra Telemetry Array for the Voyager Neptune encounter. The front-end system was originally assembled by the European Space Agency and installed on the Parkes antenna for the Giotto project. It was also used on a time-sharing basis by the Deep Space Network as part of the Parkes Canberra Telemetry Array to enhance the data return from the Voyager Uranus encounter. At the conclusion of these projects in 1986, part of the system was then shipped to JPL on loan for reimplementation at Parkes for the Voyager Neptune encounter. New design and implementation required to make the system operable at Parkes included new microwave front-end control cabinets, closed-cycle refrigeration monitor system, noise-adding radiometer system, front-end controller assembly, X81 local oscillator multiplier, and refurbishment of the original dual 8.4-GHz traveling-wave masers and waveguide feed system. The front-end system met all requirements during the encounter and was disassembled in October 1989 and returned to JPL.

Trowbridge, D. L.↗

NASA NTRS2014

Is Model-Based Development a Favorable Approach for Complex and Safety-Critical Computer Systems on Commercial Aircraft?

A system is safety-critical if its failure can endanger human life or cause significant damage to property or the environment. State-of-the-art computer systems on commercial aircraft are highly complex, software-intensive, functionally integrated, and network-centric systems of systems. Ensuring that such systems are safe and comply with existing safety regulations is costly and time-consuming as the level of rigor in the development process, especially the validation and verification activities, is determined by considerations of system complexity and safety criticality. A significant degree of care and deep insight into the operational principles of these systems is required to ensure adequate coverage of all design implications relevant to system safety. Model-based development methodologies, methods, tools, and techniques facilitate collaboration and enable the use of common design artifacts among groups dealing with different aspects of the development of a system. This paper examines the application of model-based development to complex and safety-critical aircraft computer systems. Benefits and detriments are identified and an overall assessment of the approach is given.

Torres-Pomales, Wilfredo↗

NASA NTRSDate not supplied

Small Spacecraft Sample Return to Support Gateway and Lunar Science

The Lunar Gateway is a planned orbital outpost to support Lunar surface, Cislunar, and deep space exploration activities. NASA, together with international and commercial partners, are providing various capabilities, infrastructure, and services to build the Lunar economy. As Gateway capabilities and transportation logistics evolve, utilization is expected to increase, providing ample science, technology demonstration, and commercial development opportunities. Elements of the transportation network supporting Lunar activities are primarily focused on the outbound segment, which include Commercial Lunar Payload Services (CLPS), Human Landing System (HLS), Deep Space Logistics (DSL), and the SLS/Orion crew transportation system. Initially, the only Earth return segment will be provided via Orion. However, infrequent mission cadence (once every 12 months), limited payload return mass (100 kg), and operational constraints suggest that additional sample return logistics capability will be needed. Sustaining long-term presence at the Moon will likely require innovative approaches for frequent and affordable payload return. NASA Ames Research Center and the DSL team at Kennedy Space Center (which provides the Gateway Logistics Services missions) have investigated the development of a small spacecraft-based sample return capability to complement Orion. The goal of the first mission is to demonstrate the capability as a part of an early DSL mission, and provide up to 10 kg of scientific sample return from the Gateway. The mission concept envisions the progressive addition of sample return capabilities, including returning temperature- and acceleration-sensitive payloads, and evolution into a commercially provided service, similar to existing ISS payload return logistics. An overview of payload science and technology use cases and small spacecraft mission concepts will be presented to engage scientists, payload developers and mission planners who are considering Lunar exploration activities that will require the return of high-value samples from the Gateway and/or the lunar surface.

Alan Cassell↗

NASA NTRSDate not supplied

Small Spacecraft Sample Return Mission Concept to Support Gateway and Lunar Science

The Lunar Gateway is a planned orbital outpost to support Lunar surface, Cislunar, and deep space exploration activities. NASA, together with international and commercial partners, are providing various capabilities, infrastructure, and services to build the Lunar economy. As Gateway capabilities and transportation logistics evolve, utilization is expected to increase, providing ample science, technology demonstration, and commercial development opportunities. Elements of the transportation network supporting Lunar activities are primarily focused on the outbound segment, which include Commercial Lunar Payload Services (CLPS), Human Landing System (HLS), Deep Space Logistics (DSL), and the SLS/Orion crew transportation system. Initially, the only Earth return segment will be provided via Orion. However, infrequent mission cadence (once every 12 months), limited payload return mass (100 kg), and operational constraints suggest that additional sample return logistics capability will be needed. Sustaining long-term presence at the Moon will likely require innovative approaches for frequent and affordable payload return. NASA Ames Research Center and the DSL team at Kennedy Space Center (which provides the Gateway Logistics Services missions) have investigated the development of a small spacecraft-based sample return capability to complement Orion. The goal of the first mission is to demonstrate the capability as a part of an early DSL mission, and provide up to 10 kg of scientific sample return from the Gateway. The mission concept envisions the progressive addition of sample return capabilities, including returning temperature- and acceleration-sensitive payloads, and evolution into a commercially provided service, similar to existing ISS payload return logistics. An overview of payload science and technology use cases and small spacecraft mission concepts will be presented to engage scientists, payload developers and mission planners who are considering Lunar exploration activities that will require the return of high-value samples from the Gateway and/or the lunar surface.

Small Spacecraft↗

NASA NTRSDate not supplied

Small Spacecraft Sample Return Mission Concept to Support Gateway and Lunar Science

The Lunar Gateway is a planned orbital outpost to support Lunar surface, Cislunar, and deep space exploration activities. NASA, together with international and commercial partners, are providing various capabilities, infrastructure, and services to build the Lunar economy. As Gateway capabilities and transportation logistics evolve, utilization is expected to increase, providing ample science, technology demonstration, and commercial development opportunities. Elements of the transportation network supporting Lunar activities are primarily focused on the outbound segment, which include Commercial Lunar Payload Services (CLPS), Human Landing System (HLS), Deep Space Logistics (DSL), and the SLS/Orion crew transportation system. Initially, the only Earth return segment will be provided via Orion. However, infrequent mission cadence (once every 12 months), limited payload return mass (100 kg), and operational constraints suggest that additional sample return logistics capability will be needed. Sustaining long-term presence at the Moon will likely require innovative approaches for frequent and affordable payload return. NASA Ames Research Center and the DSL team at Kennedy Space Center (which provides the Gateway Logistics Services missions) have investigated the development of a small spacecraft-based sample return capability to complement Orion. The goal of the first mission is to demonstrate the capability as a part of an early DSL mission, and provide up to 10 kg of scientific sample return from the Gateway. The mission concept envisions the progressive addition of sample return capabilities, including returning temperature- and acceleration-sensitive payloads, and evolution into a commercially provided service, similar to existing ISS payload return logistics. An overview of payload science and technology use cases and small spacecraft mission concepts will be presented to engage scientists, payload developers and mission planners who are considering Lunar exploration activities that will require the return of high-value samples from the Gateway and/or the lunar surface.

Alan Cassell↗

NASA NTRSDate not supplied

Enabling Interoperability in Earth System Digital Twins (ESDT): Integrating Observations, Models, and AI for Actionable Insights Through NASA'S Intelligent Systems Technology Program

NASA’s Intelligent Systems Technology Program (IST) is driving a paradigm shift in Earth science through the development of Earth System Digital Twins (ESDT). These integrated information systems create a dynamic "digital replica" of the Earth by harmonizing continuous, multi-source observations with high-fidelity models and state-of-the-art artificial intelligence (AI) that enable “What now?”, “What next?”, and “What if?” scenario building. These scenarios are reflected in NASA IST’s series of ESDTs, from the Coastal Zone Digital Twin that integrates complex data on the current state of the Chesapeake Bay to the Terrestrial Environmental Rapid-Replication and Assimilation Hydrometeorological (TerraHydro) AI-based ESDT that forecasts water movement across Earth’s surface, to the Agriculture Land Information System (AgLIS) which can be used to assess optimal planting dates and crop yield estimates. By bridging the gap between vast data archives and actionable insights, these projects enable a system-of-systems approach to understanding complex, interacting Earth processes. This poster will highlight recent innovations and future directions from NASA’s ESDT initiatives: Continuous Data Assimilation & Multi-Source Fusion. A core requirement of the ESDT work is the transition from static models to dynamic "living" replicas. This involves creating frameworks for the continual assimilation of near-real-time data from uncoordinated, heterogeneous sources, including satellite observations and airborne assets, and ground-based Internet of Things (IoT) sensors. These systems link design, operational status, and environmental data, ensuring the digital twin accurately reflects the current state of the physical Earth system. High-Fidelity Hybrid Modeling & Computational Acceleration to enable interactive "what-if" explorations, programs are moving beyond traditional, slow physical solvers by developing fast surrogate machine learning models and Deep Generative Models (DGMs). These hybrid approaches use neural networks to emulate complex physics, such as cloud feedback or ocean dynamics, at a fraction of the original computing cost, often leveraging advanced hardware like Graphics Processing Units (GPUs) to achieve the necessary scale. Federated Ecosystems & Interoperable Frameworks rather than building isolated tools, NASA IST is moving toward federated ESDTs and reusable analytic collaborative frameworks. This theme focuses on interoperability standards and common ontologies that allow specialized digital twins to interact and share data. This system-of-systems architecture supports multi-discipline investigations, such as analyzing how upstream watershed changes impact downstream urban flooding or how wildfire emissions affect regional air quality. By leveraging these advancements, ESDTs empower researchers and decision-makers to conduct real-time analysis and run complex hypothetical scenarios, ultimately improving our understanding of Earth’s evolving systems and informing critical real-world applications.

Earth System↗

DOE OSTI2022

Lessons Learned for Rapid Decarbonization Of Power Sectors: Key Messages for Energy Ministers

This report covers key lessons learned for the rapid decarbonization of power systems, emphasizing best practices in planning, building, and operating power systems. This report is the result of a collaborative effort among various Clean Energy Ministerial (CEM) workstreams and partner initiatives: 21st Century Power Partnership (21CPP); Carbon Capture, Utilization and Storage (CCUS); Global Power System Transformation Consortium (G-PST), a partner to CEM; Industrial Deep Decarbonization Initiative (IDDI); International Energy Agency Digital Demand-Driven Electricity Networks Initiative (IEA 3DEN), a partner to CEM; International Smart Grid Action Network (ISGAN); Long Term Scenarios for the Energy Transition (LTES); Nuclear Innovation: Clean Energy Future (NICE Future); Super-Efficient Equipment and Appliance Deployment (SEAD). The contents are not intended to be comprehensive of all power sector topics, and there may be overlap between content in each section due to the nature of this first-of-its-kind collaborative effort to deliver unified messaging on power sector decarbonization to energy ministers. This work is intended to complement other work at the Clean Energy Ministerial and offers options for consideration, not specific policy recommendations.

21CPP↗

NASA NTRS2018

Ground System Development at the Morehead State University for Interplanetary Smallsat Missions

As more small satellites are used for interplanetary research and exploration, more ground antennas with sufficiently large aperture are needed to support the increased demand in deep space communication. The 21-m ground antenna at the Morehead State University in Kentucky, United States is under development to upgrade its telemetry, tracking and command capability at X-band. The system architecture is based on a hybrid design that combines commercially available products with specialized equipment developed for the National Aeronautic and Aerospace Administration’s Deep Space Network. This architecture produces a low-cost and geographically diverse system, connecting elements at the Morehead State University and those of the DSN at the Jet Propulsion Laboratory in Pasadena, California. The architecture makes Morehead antenna appears as one of the DSN nodes, albeit with a different performance metrics due to difference in aperture size. Its operation is geared for automation, with automated data retrieval of information needed for configuring the ground station for spacecraft tracking. An incremental testing approach is used to verify system capabilities as various components are deployed into the system.

Kruth, Jeff↗

NASA NTRS2011

Orbit Determination and Navigation Software Testing for the Mars Reconnaissance Orbiter

During the extended science phase of the Mars Reconnaissance Orbiter's lifecycle, the operational duties pertaining to navigation primarily involve orbit determination. The orbit determination process utilizes radiometric tracking data and is used for the prediction and reconstruction of MRO's trajectories. Predictions are done twice per week for ephemeris updates on-board the spacecraft and for planning purposes. Orbit Trim Maneuvers (OTM-s) are also designed using the predicted trajectory. Reconstructions, which incorporate a batch estimator, provide precise information about the spacecraft state to be synchronized with scientific measurements. These tasks were conducted regularly to validate the results obtained by the MRO Navigation Team. Additionally, the team is in the process of converting to newer versions of the navigation software and operating system. The capability to model multiple densities in the Martian atmosphere is also being implemented. However, testing outputs among these different configurations was necessary to ensure compliance to a satisfactory degree.

Deep Space Network↗

DOE OSTI2022

Machine-Learning of Nonlocal Kernels for Anomalous Subsurface Transport from Breakthrough Curves

Anomalous behavior is ubiquitous in subsurface solute transport due to the presence of high degrees of heterogeneity at different scales in the media. Although fractional models have been extensively used to describe the anomalous transport in various subsurface applications, their application is hindered by computational challenges. Simpler nonlocal models characterized by integrable kernels and finite interaction length represent a computationally feasible alternative to fractional models; yet, the informed choice of their kernel functions still remains an open problem. We propose a general data-driven framework for the discovery of optimal kernels on the basis of very small and sparse data sets in the context of anomalous subsurface transport. Using spatially sparse breakthrough curves recovered from fine-scale particle-density simulations, we learn the best coarse-scale nonlocal model using a nonlocal operator regression technique. Predictions of the breakthrough curves obtained using the optimal nonlocal model show good agreement with fine-scale simulation results even at locations and time intervals different from the ones used to train the kernel, confirming the excellent generalization properties of the proposed algorithm. A comparison with trained classical models and with black-box deep neural networks confirms the superiority of the predictive capability of the proposed model.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1996

Ka-band monopulse antenna-pointing systems analysis and simulation

NASA 's Deep Space Network (DSN) has been using both 70-m and 34-m reflector antennas to communicate with spacecraft at S-band (2.3 GHz) and X-band (8.45 GHz). To improve the quality of telecommunication and to meet future mission requirements, JPL has been developing 34-m Ka-band (32-GHz) beam waveguide antennas. Presently, antenna pointing operates in either the open-loop mode with blind pointing using navigation predicts or the closed-loop mode with conical scan (conscan). Pointing accuracy under normal conscan operating conditions is in the neighborhood of 5 mdeg. This is acceptable at S- and X-bands, but not enough at Ka-band. Due to the narrow beamwidth at Ka-band, it is important to improve pointing accuracy significantly (approximately 2 mdeg). Monopulse antenna tracking is one scheme being developed to meet the stringent pointing-accuracy requirement at Ka-band. Other advantages of monopulse tracking include low sensitivity to signal amplitude fluctuations as well as single-pulse processing for acquisition and tracking. This article presents system modeling, signal processing, simulation, and implementation of Ka-band monopulse tracking feed for antennas in NASA/DSN ground stations.

Lo, V. Y.↗

NASA NTRS1996

Ka-Band Monopulse Antenna-Pointing Systems Analysis and Simulation

NASA's Deep Space Network (DSN) has been using both 70-m and 34-m reflector antennas to communicate with spacecraft at S-band (2.3 GHz) and X-band (8.45 GHz). To improve the quality of telecommunication and to meet future mission requirements, JPL has been developing 34-m Ka-band (32-GHz) beamwave guide antennas. Presently, antenna pointing operates in either the open-loop mode with blind pointing using navigation predicts or the closed-loop mode with conical scan (conscan). Pointing accuracy under normal conscan operating conditions is in the neighborhood of 5 mdeg. This is acceptable at S- and X-bands, but not enough at Ka-band. Due to the narrow beamwidth at Ka-band, it is important to improve pointing accuracy significantly (approx. 2 mdeg). Monopulse antenna tracking is one scheme being developed to meet the stringent pointing-accuracy requirement at Ka-band. Other advantages of monopulse tracking include low sensitivity to signal amplitude fluctuations as well as single-pulse processing for acquisition and tracking. This article presents system modeling, signal processing, simulation, and implementation of Ka-band monopulse tracking feed for antennas in NASA/DSN ground stations.

Lo, V. Y.↗

NASA NTRS1983

Adaptation of a software development methodology to the implementation of a large-scale data acquisition and control system

A progress report is presented on a program to upgrade the existing NASA Deep Space Network in terms of a redesigned computer-controlled data acquisition system for channelling tracking, telemetry, and command data between a California-based control center and three signal processing centers in Australia, California, and Spain. The methodology for the improvements is oriented towards single subsystem development with consideration for a multi-system and multi-subsystem network of operational software. Details of the existing hardware configurations and data transmission links are provided. The program methodology includes data flow design, interface design and coordination, incremental capability availability, increased inter-subsystem developmental synthesis and testing, system and network level synthesis and testing, and system verification and validation. The software has been implemented thus far to a 65 percent completion level, and the methodology being used to effect the changes, which will permit enhanced tracking and communication with spacecraft, has been concluded to feature effective techniques.

Madrid, G. A.↗

NASA NTRS1987

Environmental projects. Volume 3: Environmental compliance audit

The Goldstone Deep Space Communications Complex is part of NASA's Deep Space Network, one of the world's largest and most sensitive scientific telecommunications and radio navigation networks. Activities at Goldstone are carried out in support of six large parabolic dish antennas. In support of the national goal of the preservation of the environment and the protection of human health and safety, NASA, JPL and Goldstone have adopted a position that their operating installations shall maintain a high level of compliance with Federal, state, and local laws governing the management of hazardous substances, abestos, and underground storage tanks. A JPL version of a document prepared as an environmental audit of Goldstone operations is presented. Both general and specific items of noncompliance at Goldstone are identified and recommendations are provided for corrective actions.

Source record↗

NASA NTRS1993

An OSI architecture for the deep space network

The flexibility and robustness of a monitor and control system are a direct result of the underlying inter-processor communications architecture. A new architecture for monitor & Control at the Deep Space Network Communications Complexes has been developed based on the Open System Interconnection (OSI) standards. The suitability of OSI standards for DSN M&C has been proven in the laboratory. The laboratory success has resulted in choosing an OSI-based architecture for DSS-13 M&C. DSS-13 is the DSN experimental station and is not part of the 'operational' DSN; it's role is to provide an environment to test new communications concepts can be tested and conduct unique science experiments. Therefore, DSS-13 must be robust enough to support operational activities, while also being flexible enough to enable experimentation. This paper describes the M&C architecture developed for DSS-13 and the results from system and operational testing.

Heuser, W. Randy↗

NASA NTRS2003

Time Analyzer for Time Synchronization and Monitor of the Deep Space Network

A software package has been developed to measure, monitor, and archive the performance of timing signals distributed in the NASA Deep Space Network. Timing signals are generated from a central master clock and distributed to over 100 users at distances up to 30 kilometers. The time offset due to internal distribution delays and time jitter with respect to the central master clock are critical for successful spacecraft navigation, radio science, and very long baseline interferometry (VLBI) applications. The instrument controller and operator interface software is written in LabView and runs on the Linux operating system. The software controls a commercial multiplexer to switch 120 separate timing signals to measure offset and jitter with a time-interval counter referenced to the master clock. The offset of each channel is displayed in histogram form, and "out of specification" alarms are sent to a central complex monitor and control system. At any time, the measurement cycle of 120 signals can be interrupted for diagnostic tests on an individual channel. The instrument also routinely monitors and archives the long-term stability of all frequency standards or any other 1-pps source compared against the master clock. All data is stored and made available for

Cole, Steven↗

NASA NTRSDate not supplied

Runway Sign Classifier: A DAL C Certifiable Machine Learning System

In recent years, the remarkable progress of Machine Learning (ML) technologies within the domain of Artificial Intelligence (AI) systems has presented unprecedented opportunities for the aviation industry, paving the way for further advancements in automation, including the potential for single pilot or fully autonomous operation of large commercial airplanes. However, ML technology faces major incompatibilities with existing airborne certification standards, such as ML model traceability and explainability issues or the inadequacy of traditional coverage metrics. Certification of ML-based airborne systems using current standards is problematic due to these challenges. This paper presents a case study of an airborne system utilizing a Deep Neural Network (DNN) for airport sign detection and classification. Building upon our previous work, which demonstrates compliance with Design Assurance Level (DAL) ”D”, we upgrade the system to meet the more stringent requirements of Design Assurance Level ”C”. To achieve DAL C, we employ an established architectural mitigation technique involving two redundant and dissimilar Deep Neural Networks. The application of novel ML-specific data management techniques further enhances this approach. This work is intended to illustrate how the certification challenges of ML-based systems can be addressed for medium criticality airborne applications.

Flight Software↗

DOE OSTI2021

IoT Intrusion Detection Taxonomy, Reference Architecture, and Analyses

This paper surveys the deep learning (DL) approaches for intrusion-detection systems (IDSs) in Internet of Things (IoT) and the associated datasets toward identifying gaps, weaknesses, and a neutral reference architecture. A comparative study of IDSs is provided, with a review of anomaly-based IDSs on DL approaches, which include supervised, unsupervised, and hybrid methods. All techniques in these three categories have essentially been used in IoT environments. To date, only a few have been used in the anomaly-based IDS for IoT. For each of these anomaly-based IDSs, the implementation of the four categories of feature(s) extraction, classification, prediction, and regression were evaluated. We studied important performance metrics and benchmark detection rates, including the requisite efficiency of the various methods. Four machine learning algorithms were evaluated for classification purposes: Logistic Regression (LR), Support Vector Machine (SVM), Decision Tree (DT), and an Artificial Neural Network (ANN). Therefore, we compared each via the Receiver Operating Characteristic (ROC) curve. The study model exhibits promising outcomes for all classes of attacks. The scope of our analysis examines attacks targeting the IoT ecosystem using empirically based, simulation-generated datasets (namely the Bot-IoT and the IoTID20 datasets).

97 MATHEMATICS AND COMPUTING↗