SEARCH · Search NASA

Results for “Transfer Learning”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 181 records · Page 10

All sources NASA NTRS DOE OSTI

NASA NTRS2003

ASK Magazine

Welcome to the Academy of Program and Project Leadership (APPL) and ASK Magazine. APPL helps NASA managers and project teams accomplish today's missions and meet tomorrow's challenges by providing performance enhancement services and tools, supporting career development programs, sponsoring knowledge sharing events and publications, and creating opportunities for project management collaboration with universities, professional associations, industry partners and other government agencies. ASK Magazine grew out of APPL's Knowledge Sharing Initiative. The stories that appear in ASK are written by the 'best of the best' project managers, primarily from NASA, but also from other government agencies and industry. These stories contain genuine nuggets of knowledge and wisdom that are transferable across projects. Who better than a project manager to help another project manager address a critical issue on a project? Big projects, smaLl projects-they're ali here in ASK. Stories in this issue include: Earthly Considerations on Mars, Getting Politically Active, Stumping for the Project, Grins & Giggles: The Launch Pad to High Performance, Transfer Wisdom Workshops: Coming to a NASA Center Near You, Project Management: The Television Show, Lessons Learned Again and Again and Again, Implementation Reviews, ASK Talks with Dr. Michael Hecht, and What Is This Fourth Dimension?.

Laufer, Alexander↗

NASA NTRSDate not supplied

SWIPE: Spectral Water Inversion Processor and Emulator

Degradation of Earth’s inland water resources due to anthropogenic perturbations and climate anomalies at both local and global scales continues to place human health at substantial risk. There is now a growing necessity to develop pragmatic approaches that allow timely and effective extrapolation of local processes, to spatially resolved global products, and to promote operational and sustainable resource policy management. This presentation will be discussing the progress made developing SWIPE: Spectral Water Inversion Processor and Emulator. SWIPE is a platform for advanced modeling of coastal and inland aquatic habitats. The goal is create a comprehensive and cohesive system to leverage recent advancements in computation and machine learning to develop a synthetic training ground for sensitivity studies and algorithm development. The four principal facets of SWIPE include: 1. Advanced two-layer coated sphere bio-optical modeling and GPU radiative transfer modeling, 2. Big Data involving massive synthetic spectral libraries of optical properties of various global aquatic particles, surface reflectance, and top-of-atmosphere reflectance, all at hyperspectral resolution leveraging high-end computing systems at NASA Ames Research Center, 3. Deep Learning for algorithm development for water quality inversion of concentrations of common biogeophysical variables as well as optics, full uncertainty characterization by water type, and forward emulation, and lastly, 4. Image Processing for application of developed retrieval algorithms for both hyperspectral and multispectral sensors with experimental corrections for global adjacency, noise, sunglint, and benthic reflectance. This presentation will demonstrate the Equivalent Algal Populations (EAP) two-layer coated sphere scattering model which has been used develop spectral libraries of hyperspectral inherent optical properties of roughly 80 species of phytoplankton, covering 15 different classes and nine taxonomic functional types. The EAP model was also used to derive spectral properties of 10 different non-algal particle functional types. Examples of how the SMART-G (Speed-up Monte-carlo Advanced Radiative Transfer using GPU) radiative transfer code is used to model optically complex aquatic signals will be presented and discussed in the context of creating a massive synthetic database which can leverage the full power of next generation machine learning techniques and high end computing for water quality inversion. We will discuss our active investigation in things like appropriate model architectures, dimensionality reduction techniques such as PCA and autoencoders, uncertainty quantification and abstaining, and which variables actually benefit most from hyperspectral information versus multispectral resolution. We are also curious about questions relating to cost/benefit analysis in terms of computation resources, neural network complexity, and data volumes. Answers to these questions will hopefully elaborate on cost efficiency for potential future sensor design considerations.

SWIPE↗

NASA NTRS1994

The Network Operations Control Center upgrade task: Lessons learned

This article synthesizes and describes the lessons learned from the Network Operations Control Center (NOCC) upgrade project, from the requirements phase through development and test and transfer. At the outset, the NOCC upgrade was being performed simultaneously with two other interfacing and dependent upgrades at the Signal Processing Center (SPC) and Ground Communications Facility (GCF), thereby adding a significant measure of complexity to the management and overall coordination of the development and transfer-to-operations (DTO) effort. Like other success stories, this project carried with it the traditional elements of top management support and exceptional dedication of cognizant personnel. Additionally, there were several NOCC-specific reasons for success, such as end-to-end system engineering, adoption of open-system architecture, thorough requirements management, and use of appropriate off-the-shelf technologies. On the other hand, there were several difficulties, such as ill-defined external interfaces, transition issues caused by new communications protocols, ambivalent use of two sets of policies and standards, and mistailoring of the new JPL management standard (due to the lack of practical guidelines). This article highlights the key lessons learned, as a means of constructive suggestions for the benefit of future projects.

Sherif, J. S.↗

NASA NTRS2010

Flight Dynamics and GN&C for Spacecraft Servicing Missions

Future human exploration missions and commercial opportunities will be enabled through In-space assembly and satellite servicing. Several recent efforts have developed technologies and capabilities to support these exciting future missions, including advances in flight dynamics and Guidance, Navigation and Control. The Space Shuttle has demonstrated significant capabilities for crewed servicing of the Hubble Space Telescope (HST) and assembly of the International Space Station (ISS). Following the Columbia disaster NASA made significant progress in developing a robotic mission to service the HST. The DARPA Orbital Express mission demonstrated automated rendezvous and capture, In-space propellant transfer, and commodity replacement. This paper will provide a summary of the recent technology developments and lessons learned, and provide a focus for potential future missions.

Naasz, Bo↗

NASA NTRS2018

Preventing Premature Death in the M&S Lifecycle: Lessons Learned from Resurrection and Modernization of a Space System Contamination Model

Models and simulations (M&S) are often developed to meet specific needs and unique requirements for a particular situation. Once the M&S is implemented for a specific case and questions are answered, the M&S may go dormant until a similar need arises again at a later time, perhaps months to years later. Possible modification of the M&S may be required, and issues may arise if the M&S is not well documented, captured, or available. This can severely limit the useful life of the M&S and hinder future development or enhancements. This situation occurred with an M&S tool that had been developed to determine the impact to space system performance due to the presence of molecular contaminant films accumulating on key spacecraft surfaces. The challenges and issues encountered when resurrecting, executing, and modernizing the tool will be presented as a case study. To stay ahead of tomorrow’s challenges, resources to create M&S tools must be utilized efficiently. Lessons learned from this case study will aid M&S developers and users in planning for proper maintenance, transfer, and capture of key M&S tools and knowledge to avoid increased cost, increased development time, and wasted resources for projects relying on M&S.

Seasly, Elaine↗

NASA NTRS1992

Artificial neural network implementation of a near-ideal error prediction controller

A theory has been developed at the University of Virginia which explains the effects of including an ideal predictor in the forward loop of a linear error-sampled system. It has been shown that the presence of this ideal predictor tends to stabilize the class of systems considered. A prediction controller is merely a system which anticipates a signal or part of a signal before it actually occurs. It is understood that an exact prediction controller is physically unrealizable. However, in systems where the input tends to be repetitive or limited, (i.e., not random) near ideal prediction is possible. In order for the controller to act as a stability compensator, the predictor must be designed in a way that allows it to learn the expected error response of the system. In this way, an unstable system will become stable by including the predicted error in the system transfer function. Previous and current prediction controller include pattern recognition developments and fast-time simulation which are applicable to the analysis of linear sampled data type systems. The use of pattern recognition techniques, along with a template matching scheme, has been proposed as one realizable type of near-ideal prediction. Since many, if not most, systems are repeatedly subjected to similar inputs, it was proposed that an adaptive mechanism be used to 'learn' the correct predicted error response. Once the system has learned the response of all the expected inputs, it is necessary only to recognize the type of input with a template matching mechanism and then to use the correct predicted error to drive the system. Suggested here is an alternate approach to the realization of a near-ideal error prediction controller, one designed using Neural Networks. Neural Networks are good at recognizing patterns such as system responses, and the back-propagation architecture makes use of a template matching scheme. In using this type of error prediction, it is assumed that the system error responses be known for a particular input and modeled plant. These responses are used in the error prediction controller. An analysis was done on the general dynamic behavior that results from including a digital error predictor in a control loop and these were compared to those including the near-ideal Neural Network error predictor. This analysis was done for a second and third order system.

Mcvey, Eugene S.↗

NASA NTRS2000

Probing Below the Surface of Mars

In this activity, students will record and graph temperature data to learn about NASA's Mars Microprobe Mission, Deep Space 2, and how the properties of a material affect the transfer of heat.

Deep Space 2 Mars Microprobes classroom experiment↗

NASA NTRS2005

Flying SATS Higher Volume Operations: Training, Lessons Learned, and Pilots' Experiences

Developments in aviation, including new surveillance technologies and quicker, more economical small aircraft, have been identified as driving factors in a potential expansion of the use of non-towered, non-radar airports. The Small Aircraft Transportation System (SATS) project has developed the Higher Volume Operations (HVO) concept that enables pilots to safely arrive and depart these airports in instrument conditions at an increased rate as compared to today's procedures. This is achieved by transferring some traffic management tasks to centralized, ground-based automation, while assigning others to participating pilots aided by on-board tools. This paper describes strategies and lessons learned while training pilots to fly these innovative operations. Pilot approaches to using the experimental displays and dynamic altering systems during training are discussed. Potential operational benefits as well as pit-falls and frustrations expressed by subjects while learning to fly these new procedures are presented. Generally, pilots were comfortable with the procedures and the training process, and expressed interest in its near-term implementation.

Conway, Sheila↗

NASA NTRS2013

Flight Planning Branch NASA Co-op Tour

This semester I worked with the Flight Planning Branch at the NASA Johnson Space Center. I learned about the different aspects of flight planning for the International Space Station as well as the software that is used internally and ISSLive! which is used to help educate the public on the space program. I had the opportunity to do on the job training in the Mission Control Center with the planning team. I transferred old timeline records from the planning team's old software to the new software in order to preserve the data for the future when the software is retired. I learned about the operations of the International Space Station, the importance of good communication between the different parts of the planning team, and enrolled in professional development classes as well as technical classes to learn about the space station.

Marr, Aja M.↗

NASA NTRS1996

DGPS with NASA's ACTS

The U.S. Army Topographic Engineering Center, concerned about frequency license problems inherent with operating data-ready radios to support differential GPS (DGPS), learned of an experiment program the National Aeronautics and Space Administration (NASA) was sponsoring with its prototype digital satellite - the Advanced Communications Technology Satellite (ACTS). ACTS was designed to evaluate many new, untested technologies for eventual transfer to U.S. telecommunications and related industries. The new technologies promised greater data transmission rates and significantly reduced transmission latency. recognizing these benefits, the Topographic Engineering Center designed a DGPS experiment using an ACTS datalink with baselines of 200 kilometers and longer to learn what positional accuracy was possible with leading-edge satellite telecommunications technology.

Dendy, Roger↗

NASA NTRSDate not supplied

DEVELOP’s Approach to Experiential Learning

The NASA DEVELOP Program addresses environmental decision making needs and geoscience workforce development through 10-week feasibility studies that apply Earth observations to environmental issues at hand. The program builds capacity to use geospatial information in both its participants (students, recent graduates, early career professionals, and transitioning career professionals) and partner organizations (federal agencies, state & local governments, non-profits, and private industry). This is accomplished through a structured project execution model that provides opportunities for participants to have autonomy, learn “on the job,” and gain new skillsets for working with remote sensing data. A pipeline of leadership positions enhances opportunities for individuals engaged in the program to get hands-on experience conducting data analyses, communicating their work, leading technical projects, and building their knowledge bank of Earth-observing satellite capabilities. These skillsets and knowledge are then transferred to partners through the projects. This panel contribution will introduce the DEVELOP model, highlight experiences of participants, and share the program’s insights into good practices for effective experiential learning.

Capacity Building↗

NASA NTRS2014

JSC Search System Usability Case Study

The advanced nature of "search" has facilitated the movement from keyword match to the delivery of every conceivable information topic from career, commerce, entertainment, learning... the list is infinite. At NASA Johnson Space Center (JSC ) the Search interface is an important means of knowledge transfer. By indexing multiple sources between directorates and organizations, the system's potential is culture changing in that through search, knowledge of the unique accomplishments in engineering and science can be seamlessly passed between generations. This paper reports the findings of an initial survey, the first of a four part study to help determine user sentiment on the intranet, or local (JSC) enterprise search environment as well as the larger NASA enterprise. The survey is a means through which end users provide direction on the development and transfer of knowledge by way of the search experience. The ideal is to identify what is working and what needs to be improved from the users' vantage point by documenting: (1) Where users are satisfied/dissatisfied (2) Perceived value of interface components (3) Gaps which cause any disappointment in search experience. The near term goal is it to inform JSC search in order to improve users' ability to utilize existing services and infrastructure to perform tasks with a shortened life cycle. Continuing steps include an agency based focus with modified questions to accomplish a similar purpose

Meza, David↗

NASA NTRS2012

Why Games Work and the Science of Learning

In 2010, the Navy formally added the Damage Control Trainer (DCT) to the recruit training program at Great Lakes, Illinois. Despite the incredibly dense training schedule at the Navy's boot camp, the instructors were willing to set aside two hours of time for recruits to play a game. Why? Because it worked. Even with just one hour of play, research showed that recruits gained a 50-80% improvement in performance that transferred to Battle Stations 21 (B821), the Navy's capstone training event. This paper explores why games makes these kinds of results possible. It argues that the things that are known to improve learning are almost exactly the same reasons why games work: the time-honored laws of learning. It concludes that the traditional gulf between instructional design and game design is really an issue of perspective, rather than fundamentals.

Murphy, Curtiss↗

NASA NTRS2020

Deep Learning Models for Planetary Seismicity Detection

Research in planetary seismology is fundamentally constrained by a lack of data. Seismo-logical science products of future missions can typically only be informed by theoretical signal/noise characteristics of the environment or likely Earth-analogues. Although objectives can be re-assessed after some initial data-collection upon lander arrival, transfer of high-resolution data back to Earth is costly on lander power usage. Over the last several years, development of GPU computing techniques and open-source high-level APIs have led to rapid advances in deep learning within the fields of computer vision, natural language processing, and collaborative filtering. These techniques are actively being adapted in seismology for a variety of tasks, including: earthquake detection, seismic phase discrimination, and ground-motion prediction. Until the recent detection of mars quakes during the Mars InSight mission, the only other measurements of seismicity recorded outside of Earth was on the Moon during the Apollo missions between 1969 to 1977. These unique data sets have been periodically revisited using new seismological methods, including ambient noise interferometry and Hidden Markov Models. Our objective is to develop a deep learning seismic detector and use it to catalog moonquakes from the Apollo 17 Lunar Seismic Profiling Experiment (LSPE) and compare the results with those obtained by other methods. Additionally, we will assess the accuracy tradeoff between using a training set of lunar data and one composed of Earth seismicity. In this document, we present preliminary results using a prototype classifier trained on a small set of earthquakes that was able to obtain detections for LSPE moonquakes with a greater accuracy than a recent study using Hidden Markov Models.

Civilini, F.↗

NASA NTRS2024

EdgeCortix SAKURA-I Machine-Learning, PCIe Accelerator SEE Heavy Ion Test Report

To enable autonomy in space, machine-learning and computer vision applications become invaluable for sensor processing. However, these algorithms are computationally complex and unfeasible for many embedded central processing units (CPUs) and usually require external coprocessors, such as graphics processing units (GPUs) or accelerators specific to the application, including application specific integrated circuits (ASICs). In power-constrained systems, GPUs tend to consume more power than is acceptable (>40W), so lower-power accelerators have shown promise to provide the performance needed under spacecraft constraints. For radiation engineers, developing methodologies that can properly test CPUs, GPUs, and accelerators, and enable comparisons between them remains a necessary complication to solve as the devices become more complex. The methodology in this test aims to be a start in developing a baseline single-event effect (SEE) test for client-device machine learning accelerators. This category of devices do not host their own operating system. This testing campaign is a continuation of a previous 200 MeV proton test performed in January 2024. This report covers two heavy ion tests of the SAKURA-I card: one in April 2024, and one in June 2024. Additional data was needed after the April test due to ion-range issues experienced at higher linear-energy transfers (LETs). These range issues are described in more detail in Section 8. This experiment characterizes SEEs and data error susceptibility of the EdgeCortix SAKURA-I machine-learning accelerator under heavy ions. The device was monitored for single event upsets (SEUs) and single event functional interrupts (SEFIs) at the Lawrence Berkeley National Laboratory’s 88-inch cyclotron. The SAKURA-I board accelerates machine-learning inference applications on a host computer through a PCIex16 connection. For the purposes of devising an end to end automated analysis workflow for this experiment, the YOLO-V5 and SSD300 objection-detection models, and the ResNet-50, EfficientNet, and MobileNetV2 image classification models were used as a representative suite of analytical machine-learning models.

Seth S Roffe↗

NASA NTRS2000

Separation Control at Flight Reynolds Numbers: Lessons Learned and Future Directions

Active separation control, using periodic excitation, was studied experimentally at high Reynolds numbers. The effects of compressibility, mild sweep, location o excitation slot and steady momentum transfer on the efficacy of the method were identified. Tests conducted at chord Reynolds numbers as high as 40 x 10(exp 6) demonstrated that active control using oscillatory flow excitation can effectively delay flow separation from and reattach separated flow to aerodynamic surfaces at flight conditions. The effective frequencies generate one to four vortices over the controlled region at all times, regardless of the Reynolds number. The vortices are initially amplified by the separated shear-layer, and after initiating reattachment, the strength of the vortices decay as they are convected downstream. Large amplitude, low frequency vortices break down to smaller ones upon introduction at the excitation slot. The effects of steady mass transfer were compared to those of periodic excitation. It was found that steady blowing is significantly inferior to periodic excitation in terms o performance benefits and that the response to steady blowing is abrupt, and therefore undesirable from a control point of view. Steady suction and periodic excitation are comparable in effectiveness and both exhibit a gradual response to changes in the magnitude of the control input. The combination of weak steady suction and periodic excitation is extremely effective while the addition of steady blowing could be detrimental. Compressibility effects are weak as long as separation is not caused by a shock-wave/boundary-layer interaction The undesirable effects of the shock-induced separation could be alleviated by the introduction of periodic excitation upstream of the shock wave, inside the region of supersonic flow. The effects of mild sweep were also studied and periodic excitation was found to be very effective in reattaching three-dimensional separated flow. Scaling laws that correlate 2D and 3D controlled flows were tested and verified. Several performance benefits could be gained by applying the method to existing configurations, but it is expected that the full potential of the method can only be realized through the design of new configurations. A comprehensive, fully turbulent, database was generated in order to guide the development, and enable validation, of candidate unsteady CFD design tools.

Seifert, Avi↗

NASA NTRS2000

Separation Control at Flight Reynolds Numbers: Lessons Learned and Future Directions

Active separation control, using periodic excitation, was studied experimentally at high Reynolds numbers. The effects of compressibility, mild sweep, location of excitation slot and steady momentum transfer on the efficacy of the method were identified. Tests conducted at chord Reynolds numbers as high as 40 x 10(exp 6) demonstrated that active control using oscillatory flow excitation can effectively delay flow separation from, and reattach separated flow to aerodynamic surfaces at flight conditions. The effective frequencies generate one to four vortices over the controlled region at all times, regardless of the Reynolds number. The vortices are initially amplified by the separated shear-layer, and after initiating reattachment, the strength of the vortices decay as they are convected downstream. Large amplitude, low frequency vortices break down to smaller ones upon introduction at the excitation slot. The effects of steady mass transfer were compared to those of periodic excitation. It was found that steady blowing is significantly inferior to periodic excitation in terms of performance benefits and that the response to steady blowing is abrupt, and therefore undesirable from a control point of view. Steady suction and periodic excitation are comparable in effectiveness and both exhibit a gradual response to changes in the magnitude of the control input. The combination of weak steady suction and periodic excitation is extremely effective while the addition of steady blowing could be detrimental. Compressibility effects are weak as long as separation is not caused by a shock-wave/boundary-layer interaction. The undesirable effects of the shock-induced separation could be alleviated by the introduction of periodic excitation upstream of the shock wave, inside the region of supersonic flow. The effects of mild sweep were also studied and periodic excitation was found to be very effective in reattaching three-dimensional separated flow. Scaling laws that correlate 2D and 3D controlled flows were tested and verified. Several performance benefits could be gained by applying the method to existing configurations, but it is expected that the full potential of the method can only be realized through the design of new configurations. A comprehensive, fully turbulent, database was generated in order to guide the development, and enable validation, of candidate unsteady CFD design tools.

Pack, LaTunia G.↗

NASA NTRS2004

Cloud-Vegetation Radiative Interaction: What Can We Learn from it about Cloud Optical Properties?

Because of their radiative interactions, the vegetation canopy and the atmosphere are coupled together; each serves as a boundary condition to the radative transfer equations in the adjacent medium. To better understand radiative processes in these media we need an accurate description of their interactions. This presentation outlines a technique needed to describe interactions between vegetation and clouds and exploits it to retrieve cloud optical depth from ground-based radiance measurements. measurements of zenith radiance in the RED and NIR spectral regions. In addition to an algebraic combinations of spectral radiances such as Normalized Difference Cloud Index (NDCI) that can result in poor retrievals due to its insensitivity to cloud fraction, both RED and NIR radiances as points on the "RED vs. NIR" plane are proposed to be used for retrieval. The proposed method is applied to a multi-channel sunphotometer (as a part of AERONET) measurements at the ARM site in Oklahoma. In addition to cloud optical depth, the new method also infers a "radiatively effective" cloud fraction.

Marshak, Alexander↗