SEARCH · Search NASA

Results for “GROUND EFFECT MACHINE”

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 109 records · Page 6

All sources NASA NTRS DOE OSTI

NASA NTRSDate not supplied

High School Citizen Scientists Use AI/ML to Predict Intra-Ocular Pressure From Gene Expression Data for Spaceflown Mice

Artificial Intelligence (AI) and Machine Learning (ML) have increasingly become pivotal in biological and biomedical research, largely due to the culture of open data sharing and its associated benefits. The methodologies inherent in AI/ML are particularly adept at identifying and forecasting biological phenotypes from the vast amounts of data generated by next-generation sequencing technologies. These techniques offer substantial promise for advancing research in space biosciences and for the development of automated systems for monitoring space health. Nevertheless, there are crucial aspects to consider when training, validating, and testing machine learning models in both biological research and clinical contexts. It is essential that Open Science principles, including data sharing and the availability of open-source code, are complemented by high-quality, publicly accessible training resources. These resources should focus on best practices and include modules based on real-world scientific cases and data to ensure that future AI/ML practitioners gain practical experience with genuine problems. Addressing this knowledge gap, we have designed, developed, and delivered both interactive and self-paced training programs for citizen scientists worldwide, enabling them to utilize AI/ML for space biology research. This initiative was made possible through generous funding from a Transformation to Open Science Training grant. The interactive training sessions, conducted this summer, utilized AI/ML techniques to analyze data from the Open Science Data Repository, specifically targeting the effects of spaceflight on ocular structure and function. The dataset OSD-583, from the Rodent Research 9 mission, provides experimental data detailing the ocular responses of mice subjected to a 35-day spaceflight, compared with ground control counterparts. Using OSD-583 as observational data, our summer training participants applied AI/ML methods to predict intraocular pressure from RNA-seq data and identify the genes most predictive of the observed responses. Further analysis through pathway enrichment and gene set enrichment revealed that these genes are involved in molecular and cellular processes contributing to retinal degeneration.

James Casaletto↗

NASA NTRS2016

Post-Flight Assessment of Avcoat Thermal Protection System for the Exploration Flight Test-1

On December 5, 2014 NASA conducted the first flight test of its next generation human-class Orion spacecraft. The flight was called the Exploration Flight Test -1 (EFT-1) which lasted for 4 hours and culminated into a re-entry trajectory at 9 km/s. This flight test of the 5-meter Orion Crew Module demonstrated various sub-systems including the Avcoat ablative thermal protection system (TPS) on the heat shield. The Avcoat TPS had been developed from the Apollo-era recipe with a few key modifications. The engineering for thermal sizing was supported by modeling, analysis, and ground tests in arc jet facilities. This paper will describe a postlfight analysis plan and present results from post-recovery inspections, data analysis from embedded sensors, TPS sample extraction and characterization in the laboratory. After the recovery of the vehicle, a full photographic survey and surface scans of the TPS were performed. The recovered vehicle showed physical evidence of flow disturbances, varying degrees of surface roughness, and excessive recession downstream of compression pads. The TPS recession was measured at more than 200 locations of interest on the Avcoat surface. The heat shield was then processed for sample extraction prior to TPS removal using the 7-Axis Milling machine at Marshall Space Flight Center. Around 182 rectangular TPS samples were extracted for subsequent analysis and investigation. The final paper will also present results of sample analysis. The planned investigation includes sidewall imaging, followed by image analysis to characterize TPS response by quantifying different layers in the char and pyrolysis zones. A full postmortem of the instrumentation and sensor ports will also be performed to confirm no adverse effects due to the sensors themselves. A subset of the samples will undergo structural testing and perform detailed characterization of any cracks and integrity of gore seams. Finally, the material will be characterized with layer-by-layer density measurements and SEM investigations to evaluate material morphology at microstructural level including identification of elements and compounds.

Aerothermodynamics↗

NASA NTRS2013

Design and Development of Functionally Effective Human-Machine Interfaces for Firing Room Displays

This project involves creating software for support equipment used on the Space l aunch System (SLS). The goal is to create applications and displays that will be used to remotely operate equipment from the firing room and will continue to support the SLS launch vehicle to the extent of its program. These displays include design practices that help to convey information effectively, such as minimizing distractions at normal operating state and displaying intentional distractions during a warning or alarm state. The general practice for creating an operator display is to reduce the detail of unimportant aspects of the display and promote focus on data and dynamic information. These practices include using minimalist design, using muted tones for background colors, using a standard font at a readable text size, displaying alarms visible for Immediate attention, grouping data logically, and displaying data appropriately varying on the type of data. Users of these displays are more likely to stay focused on operating for longer periods by using design practices that reduce eye strain and fatigue. Effective operator displays will improve safety by reducing human errors during operation, which will help prevent catastrophic accidents. This report entails the details of my work on developing remote displays for the Hypergolics ground system. Before developing a prototype display, the design and requirements of the system are outlined and compiled into a document. Then each subsystem has schematic representations drawn tha.t meet the specifications detailed in the document. The schematics are then used as the outline to create display representations of each subsystem. Each display is first tested individually. Then the displays are integrated with a prototype of the master system, and they are tested in a simulated environment then retested in the real environment. Extensive testing is important to ensure the displays function reliably as intended.

Cho, Henry↗

NASA NTRSDate not supplied

A Distributed Simulation-to-Flight Framework to Support Investigating Trust/Trustworthiness in Multi-Agent Systems

As autonomous systems continue to grow both in use and complexity, the necessity for robust and extensible simulation-to-flight methods is paramount for establishing an effective architecture for autonomous systems. A fundamental objective of the ATTRACTOR (Autonomy Teaming and TRAjectories for Complex Trusted Operational Reliability) project was to design and develop a distributed mixed-reality simulation environment to begin establishing a basis for certification of autonomous systems via research into trust and trustworthiness. In this paper, we present an autonomous systems architecture and development framework paired with a persistent distributed modeling and simulation environment for test and evaluation of autonomous systems. The Autonomous Entity Operations Network (AEON) framework enables autonomous system development with an easily extensible collection of libraries and plug-n-play nodes facilitated by the Data Distribution Service (DDS) communication protocol standard. The Baseline Environment for Autonomous Modeling (BEAM) simulation environment is a distributed mixed-reality Unity™-based environment built around the same DDS communication paradigm allowing for easy integration with AEON-based autonomous applications. They were designed under ATTRACTOR in order to measure and establish trustworthiness and trust in single- and multi-agent human-machine systems whether these machines are fixed-wing general aviation, rotary-wing Unmanned Aerial Vehicles (UAVs), ground rovers, or even spacecraft. Together AEON and BEAM enable sim-to-flight with minimal configuration changes. By using AEON and BEAM, source code that runs in simulation ports directly to hardware and has successfully flown in the lab and in the National Airspace System (NAS) at NASA LaRC many times over the lifetime of ATTRACTOR.

Benjamin N Kelley↗

NASA NTRSDate not supplied

A Distributed Simulation-to-Flight Framework to Support Investigating Trust/Trustworthiness in Multi-Agent Systems

Benjamin N Kelley↗

NASA NTRS2006

LDCM Grid Prototype (LGP)

The LGP successfully demonstrated that grid technology could be used to create a collaboration among research scientists, their science development machines, and distributed data to create a science production system in a nationally distributed environment. Grid technology provides a low cost and effective method of enabling production of science products by the science community. To demonstrate this, the LGP partnered with NASA GSFC scientists and used their existing science algorithms to generate virtual Landsat-like data products using distributed data resources. LGP created 48 output composite scenes with 4 input scenes each for a total of 192 scienes processed in parallel. The demonstration took 12 hours, which beat the requirement by almost 50 percent, well within the LDCM requirement to process 250 scenes per day. The LGP project also showed the successful use of workflow tools to automate the processing. Investing in this technology has led to funding for a ROSES ACCESS proposal. The proposal intends to enable an expert science user to produce products from a number of similar distributed instrument data sets using the Land Cover Change Community-based Processing and Analysis System (LC-ComPS) Toolbox. The LC-ComPS Toolbox is a collection of science algorithms that enable the generation of data with ground resolution on the order of Landsat-class instruments.

Weinstein, Beth↗

NASA NTRS2019

Testing a Neural Network Accelerator on a High-Altitude Balloon

The cognitive communications project has been working to re d machine learning approaches to support their deployment and sustained use in space environments. It has historically been difficult to implement such techniques on space platforms, however, due to the computational requirements they levy onto general-purpose avionics hardware. While technologies exist to accelerate the computation of aspects of neural networks, such platforms have not historically been deployed in space environments. Given that testing payloads in such environments can be both cost- and time-prohibitive, high-altitude balloons can be used as a way to approximate a space environment at a much lower cost, thus providing a cost-effective way in which to test newer approaches to hardware acceleration for artificial intelligence which may be deployed onto spacecraft more directly. This paper describes a successful test of a commercial off- the-shelf neural network accelerator on a high-altitude balloon. It begins by explaining our selection criteria when evaluating different commercial neural network acceleration techniques: primary considerations include size, weight, and power (SWaP) as well as ease of integration. Next, the paper describes the development and implementation of an experimental flight test platform: flight and ground components are discussed. Afterward, the paper discusses the experimental payload itself: this includes the experimental procedure as well as the specific image and method used for testing. Finally, the paper concludes with an evaluation of both the experimental device tested at altitude as well as the flight test framework itself, identifying how the existing platform can be used to continue tes g commercial off-the-shelf (COTS) solutions for acceleration.

Clark, Gilbert↗

NASA NTRS2018

Assimilation of Multi-Frequency, Multi-Polarization Passive Microwave Brightness Temperature Observations in North America over Snow-Covered Regions Using Support Vector Machines

Accurately estimating the mass of water within a snowpack (a.k.a. snow water equivalent, or SWE) across regional or continental scales is a challenge. In order to overcome some of the limitations in traditional SWE retrieval algorithms or radiative transfer-based snow emission models, this study explores the use of a support vector machine (SVM) to merge an advanced land surface model within a radiance emission (i.e., brightness temperature) assimilation framework. The goal of direct radiance assimilation is preferable as it avoids inconsistencies in the use of ancillary data between the assimilation system and the independently-generated geophysical retrieval. The impact of assimilating multiple observations simultaneously at different frequency and polarization combinations is then evaluated via comparisons to state-of-the-art SWE and snow depth products as well as available ground-based measurements across North America for the years 2002 through 2011. It is found that assimilation-derived estimates (relative to estimates without assimilation) tend to better agree with state-of-the-art snow products. In addition, an overall improvement in goodness-of-fit statistics for snow estimates is achieved via assimilation when compared against ground-based snow measurements. In addition, these improvements in snow are shown to translate into improvements in streamflow predictions. Specifically, 11 out of the 13 major snow-dominated basins investigated have improved cumulative runoff estimates versus ground-based discharge measurements compared to the no-assimilation scenario. It is proven that a SVM can serve as an efficient and effective observation operator for a snow mass analysis within a radiance assimilation system.

Xue, Yuan↗

NASA NTRS1998

A Very High Resolution Mid Infrared Spectrograph for SOFIA

The purpose of this project was to study the design of a high resolution mid-infrared spectrograph for the SOFIA airborne observatory. The primary motivation for the construction and use of such an instrument is the study of vibrational transitions of molecules in molecular clouds, circumstellar inflows and outflows, and planetary atmospheres, which are blocked from ground-based observations by absorption by the Earth's atmosphere. The instrument design studied is a cross-dispersed grating spectrograph with several modes of operation giving spectral resolving powers of approximately 4000, 20,000, and 100,000. In the two lower resolution modes a single grating is used in a long-slit spectrograph. At high resolution that grating serves as the cross-disperser for a 1-m long echelon, a very coarsely and steeply ruled grating, diamond-machined in aluminum. Several design study tasks were carried out: 1. An optical and mechanical design was developed. It differed from the preliminary design by using a reflecting focal reducer in the fore-optics and by rearranging the echelon and cross-dispersing chambers to improve the efficiency of the long-slit modes. 2. A finite-element analysis of the dewar and echelon support structures was done. It led us to change the echelon support to improve its rigidity. 3. Further information was obtained which convinced us that Hyperfine Inc. was capable of diamond-machining the echelon. 4. Several possible vendors of readout electronics and software were identified. It was decided that it is more cost-effective to purchase these items rather than developing them ourselves. 5. Observing and calibration procedures were studied. we did not identify significant changes needed from procedures used previously. 6. Possible expansions of instrument capabilities, including wavelength coverage, were studied. It appears unlikely that the echelon will perform well at wavelengths shortward of 5 microns, but the spectral coverage could be extended longward of 28 microns with the use of an Si:Sb detector. No patentable inventions were made during this study. Based on this design study, a proposal was submitted to construct the instrument. It was chosen as one of the first-light instruments for SOFIA.

Lacy, John H.↗

NASA NTRS2022

Multi-Variate LSTM Prediction of Alaska Magnetometer Chain Utilizing a Coupled Model Approach

During periods of rapidly changing geomagnetic conditions electric fields form within the Earth’s surface and induce currents known as geomagnetically induced currents(GICs), which interact with unprotected electrical systems our society relies on. In this study, we train multi-variate Long-Short Term Memory neural networks to predict magnitude of north-south component of the geomagnetic field (|BN|) at multiple ground magnetometer stations across Alaska provided by the SuperMAG database with a future goal of predicting geomagnetic field disturbances. Each neural network is driven by solar wind and interplanetary magnetic field inputs from the NASA OMNI database spanning from 2000–2015 and is fine tuned for each station to maximize the effectiveness in predicting |BN|. The neural networks are then compared against multivariate linear regression models driven with the same inputs at each station using Heidke skill scores with thresholds at the 50, 75, 85, and 99 percentiles for |BN|. The neural network models show significant increases over the linear regression models for |BN| thresholds. We also calculate the Heidke skill scores for d|BN|/dt by deriving d|BN|/dt from |BN| predictions. However, neural network models do not show clear outperformance compared to the linear regression models. To retain the sign information and thus predict BN instead of |BN|, a secondary so-called polarity model is utilized. The polarity model is run in tandem with the neural networks predicting geomagnetic field in a coupled model approach and results in a high correlation between predicted and observed values for all stations. We find this model a promising starting point for a machine learned geomagnetic field model to be expanded upon through increased output time history and fast turnaround times.

Matthew Blandin↗

NASA NTRSDate not supplied

A Distributed Simulation-to-Flight Framework to Support Investigating Trust/Trustworthiness in Multi-Agent Systems

As autonomous systems continue to grow both in use and complexity, the necessity for robust and extensible simulation-to-flight frameworks is paramount for establishing an effective architecture for autonomous systems. Hardware test flights are time-consuming and cost prohibitive during early system design and development. Simulation environments can be useful tools to accelerate algorithm development and testing. However, transitions from simulation to flight (sim-to-flight) can be challenging, unless systems are designed with this transition in mind and with the necessary capabilities built into the architecture and framework. One of the objectives of Autonomy Teaming and TRAjectories for Complex Trusted Operational Reliability (ATTRACTOR) was to design and develop a distributed mixed-reality simulation environment to begin establishing a basis for certification of autonomous systems via research into trust and trustworthiness. ATTRACTOR’s objective was to construct computational concepts of trustworthiness and justifiable trust in multi-agent autonomous teams, to inform future certification of safety-critical and time-critical autonomous systems in aviation. In this paper, we present an autonomous systems architecture and development framework paired with a persistent distributed modeling and simulation (ModSim) environment for test and evaluation of autonomous systems. They were designed under ATTRACTOR in order to measure and establish trustworthiness and trust in single-and multi-agent human-machine systems whether these machines are fixed-wing general aviation, rotary-wing Unmanned Aerial Vehicles (UAVs), ground rovers, or even spacecraft. The Autonomous Entity Operational Network (AEON) framework enables autonomous system development with an easily extensible collection of libraries and plug-n-play nodes facilitated by the Data Distribution Service (DDS) communication protocol standard. The Baseline Environment for Autonomous Modeling (BEAM) simulation environment is a distributed mixed-reality Unity™-based environment built around the same DDS communication paradigm allowing for easy integration with AEON-based autonomous applications, enabling sim-to-flight with minimal configuration changes. Using AEON and BEAM, source code that runs in simulation ports directly to hardware and has successfully flown in the National Airspace System (NAS) at NASA LaRC many times over the lifetime of ATTRACTOR.

Benjamin N Kelley↗

NASA NTRS2023

CLASS Observation of Polarized Cloud Emission at Millimeter Wavelengths

The dynamic atmosphere imposes challenges to ground-based cosmic microwave background observation, especially for measurements on large angular scales. The hydrometeors in the atmosphere, mostly in the form of clouds, scatter the ambient thermal radiation and are known to be the main linearly polarized source in the atmosphere. This scattering-induced polarization is significantly enhanced for ice clouds due to the alignment of ice crystals under gravity, which are also the most common clouds seen at the millimeter-astronomy sites at high altitudes. This work presents a multifrequency study of cloud polarization observed by the Cosmology Large Angular Scale Surveyor experiment on Cerro Toco in the Atacama Desert of northern Chile, from 2016–2022, at the frequency bands centered around 40, 90, 150, and 220 GHz. Using a machine-learning-assisted cloud classifier, we made connections between the transient polarized emission found in all four frequencies with the clouds imaged by monitoring cameras at the observing site. The polarization angles of the cloud events are found to be mostly 90° from the local meridian, which is consistent with the presence of horizontally aligned ice crystals. The90 and 150 GHz polarization data are consistent with a power law with a spectral index of 3.90±0.06, while an excess/deficit of polarization amplitude is found at 40/220 GHz compared with a Rayleigh scattering spectrum. These results are consistent with Rayleigh-scattering-dominated cloud polarization, with possible effects from supercooled water absorption and/or Mie scattering from a population of large cloud particles that contribute to the220 GHz polarization.

Earth's clouds↗

NASA NTRS2010

The Importance of HRA in Human Space Flight: Understanding the Risks

Human performance is critical to crew safety during space missions. Humans interact with hardware and software during ground processing, normal flight, and in response to events. Human interactions with hardware and software can cause Loss of Crew and/or Vehicle (LOCV) through improper actions, or may prevent LOCV through recovery and control actions. Humans have the ability to deal with complex situations and system interactions beyond the capability of machines. Human Reliability Analysis (HRA) is a method used to qualitatively and quantitatively assess the occurrence of human failures that affect availability and reliability of complex systems. Modeling human actions with their corresponding failure probabilities in a Probabilistic Risk Assessment (PRA) provides a more complete picture of system risks and risk contributions. A high-quality HRA can provide valuable information on potential areas for improvement, including training, procedures, human interfaces design, and the need for automation. Modeling human error has always been a challenge in part because performance data is not always readily available. For spaceflight, the challenge is amplified not only because of the small number of participants and limited amount of performance data available, but also due to the lack of definition of the unique factors influencing human performance in space. These factors, called performance shaping factors in HRA terminology, are used in HRA techniques to modify basic human error probabilities in order to capture the context of an analyzed task. Many of the human error modeling techniques were developed within the context of nuclear power plants and therefore the methodologies do not address spaceflight factors such as the effects of microgravity and longer duration missions. This presentation will describe the types of human error risks which have shown up as risk drivers in the Shuttle PRA which may be applicable to commercial space flight. As with other large PRAs of complex machines, human error in the Shuttle PRA proved to be an important contributor (~12 percent) to LOCV. An existing HRA technique was adapted for use in the Shuttle PRA, but additional guidance and improvements are needed to make the HRA task in space-related PRAs easier and more accurate. Therefore, this presentation will also outline plans for expanding current HRA methodology to more explicitly cover spaceflight performance shaping factors.

Hamlin, Teri↗

NASA NTRS2021

A Machine Learning Approach to Objective Identification of Dust in Satellite Imagery

Airborne dust has broad adverse effects on human activity, including aviation, human health, and agriculture. Remote sensing observations are used to detect dust and aerosols in the atmosphere using long established techniques. False color Red-Green-Blue (RGB) imagery using band differences sensitive to dust absorption (Dust RGB) is currently used operationally to assist forecasters and decision-makers in identifying dust at night, but there are still limitations, subjectivity, and nuances to image interpretation making night-time dust identification difficult even for experts. This study applies machine learning to the problem of night-time dust detection with a simple random forest (RF) model using Geostationary Operational Environmental Satellite-16 (GOES-16) Advanced Baseline Imager (ABI) infrared imagery, band differences sensitive to dust absorption, and Dust RGB color components as inputs to the model. The RF model achieves an Area-Under-Curve (AUC) of 0.97 with a standard deviation of 0.04 for dust cases. For images with dust present, the model correctly labels 85% of dust pixels and 99.96% of no-dust pixels for all dust images in the validation data set. The addition of a single null case to the training data set drastically reduces error in labeling no-dust pixels as dust from 45% to 14.5%. Application of the machine learning model to the April 13–14, 2019 dust event demonstrates the ability of the model to identify dust during night-time hours when visual dust detection is limited by the cooling ground surface characteristics.

dust↗

NASA NTRS2017

Ablation and Heating During Atmospheric Entry and Its Effect on Airburst Risk

Large meteoroids and asteroids entering the atmosphere endure tremendous heating from the shock heated air, and thereby lose a significant fraction of their mass during atmospheric entry a process known as ablation. The predicted evolution of the asteroids mass as it passes through the atmosphere can affect both the predicted energy deposition profile relevant to an airburst event, or the residual mass that strikes the ground in the case of an impact event. This presentation is divided roughly into two parts. In the first part, an overview of traditional models for heat transfer and ablation that are historically used in the meteor physics community is presented, and the validity in the asteroid entry regime discussed. Sensitivity analyses performed using the recently developed Fragment-Cloud Model (FCM) will be presented which show illustrate the range of sizes and entry parameters for which the predicted asteroid threat is most sensitive to the models for ablation and heat transfer. The second part of the presentation shall focus on recent work done under NASAs Asteroid Threat Assessment Project (ATAP) to develop new models for heat transfer and ablation using high-fidelity numerical simulation in concert with state-of-the-art experiments. Coupled computational fluid dynamics (CFD)radiation transport simulations preformed using the state-of-the-art entry modeling tools at NASA show that, for large meteoroids and asteroids, there can significant attenuation of the heat transfer to the surface (95 in some cases) by the products of ablation. In addition to the heat transfer, new models for the material response and ablation of asteroidal material have been developed [cite]. In the current work, we present finding from recent novel experiments performed in the arc jet facility at NASA Ames, which allows us to, in part, simulate the extreme environment experienced by the asteroid during entry. Briefly, the experimental set-up was comprised of a 1.5 conical article of machined H5 chondrite, which was exposed to a high-enthalpy flow resulting in approximately 4 kWcm2 of heating to the surface. A still frame capture from high-speed video taken during this experiment can be seen in Figure 1. In this figure, we can observe some of the major mechanisms for meteoroid ablation, such as melt flow, spallation (mechanical removal of material), and vaporization. Major findings from this, and other experiments will be discussed, as well progress on utilizing the data from the experiments to inform and develop improved models for ablation.

Asteroids↗

NASA NTRS2010

Observing System Simulation Experiment (OSSE) for the HyspIRI Spectrometer Mission

The OSSE software provides an integrated end-to-end environment to simulate an Earth observing system by iteratively running a distributed modeling workflow based on the HyspIRI Mission, including atmospheric radiative transfer, surface albedo effects, detection, and retrieval for agile exploration of the mission design space. The software enables an Observing System Simulation Experiment (OSSE) and can be used for design trade space exploration of science return for proposed instruments by modeling the whole ground truth, sensing, and retrieval chain and to assess retrieval accuracy for a particular instrument and algorithm design. The OSSE in fra struc ture is extensible to future National Research Council (NRC) Decadal Survey concept missions where integrated modeling can improve the fidelity of coupled science and engineering analyses for systematic analysis and science return studies. This software has a distributed architecture that gives it a distinct advantage over other similar efforts. The workflow modeling components are typically legacy computer programs implemented in a variety of programming languages, including MATLAB, Excel, and FORTRAN. Integration of these diverse components is difficult and time-consuming. In order to hide this complexity, each modeling component is wrapped as a Web Service, and each component is able to pass analysis parameterizations, such as reflectance or radiance spectra, on to the next component downstream in the service workflow chain. In this way, the interface to each modeling component becomes uniform and the entire end-to-end workflow can be run using any existing or custom workflow processing engine. The architecture lets users extend workflows as new modeling components become available, chain together the components using any existing or custom workflow processing engine, and distribute them across any Internet-accessible Web Service endpoints. The workflow components can be hosted on any Internet-accessible machine. This has the advantages that the computations can be distributed to make best use of the available computing resources, and each workflow component can be hosted and maintained by their respective domain experts.

Turmon, Michael J.↗

NASA NTRS2008

Jet Propulsion Laboratory: Annual Report 2007

Many milestones are celebrated in the business of space exploration, but one of them that arrived this year has particular meaning for us. Half a century ago, on January 31, 1958, the Jet Propulsion Laboratory was responsible for creating America's first satellite, Explorer 1, and joined with the Army to launch it into orbit. That makes 2007 the 50th year we have been sending robotic craft from Earth to explore space. No other event before or since has had such a profound effect on JPL's basic identity, setting it on the path to become the world's leader in robotic solar system exploration. It is not lost on historians that Explorer 1, besides being America's first satellite, was also the first spacecraft from any country to deliver scientific results in its case, the discovery of the Van Allen Radiation Belts that surround Earth. Science, of course, has been the prime motivator for all the dozens of missions that we have lofted into space in the half-century since then. JPL has sent spacecraft to every planet in the solar system from Mercury to Neptune, some of them very sophisticated machines. But in one way or another, they all owe their heritage to the 31-pound bullet-shaped probe JPL shot into space in 1958. Although we have ranged far and wide across the solar system, we have a very strong contingent of satellites and instruments dedicated, like Explorer, to the environment of our home planet. JPL missions have been providing much of the data to establish the facts of global warming - most especially, the melting of ice sheets in Greenland and Antarctica. During the past year, JPL and our parent organization, the California Institute of Technology, have created a task force to focus the special capabilities of the Laboratory and campus on ways to better understand the physics of global change. While Earth is a chaotic and dynamic system capable of large natural variations, evidence is mounting that human activities are playing an increasingly important role. A central piece of this effort is a search for novel energy sources to replace fossil fuels, the combustion of which adds carbon dioxide to our atmosphere. All of this is supported by our worldwide Deep Space Network, which provides the communication link between spacecraft and the ground. In addition, missions are infused with technologies developed by researchers working on projects for non-NASA sponsors as well as on pure research.

Jet Propulsion Laboratory (JPL)↗

NASA NTRSDate not supplied

Onboard Hyperspectral Image Classification via Transfer Learning for Communication-Limited Spacecraft

Employing deep-learning and artificial-intelligence (AI) techniques onboard spacecraft can dramatically improve priority data selection to ensure more effective use of the available downlink. However, deployment of effective deep-learning models requires significant training on the ground, which may not be feasible, due to limited data available in an unexplored environment. Therefore, this research explores building robust classification models for onboard data processing where training data is highly limited using transfer-learning techniques. In this paper, we focus on the use case of hyperspectral imaging for remote sensing, a domain where the high dimensionality of the data from the sensor can rapidly saturate the downlink bandwidth. With this bottleneck, there is an impending need to autonomously and robustly classify data onboard to optimize downlink of high-impact measurements, thus maximizing the scientific utility per bit transmitted to the ground. This paper examines the use of deep neural networks onboard for hyperspectral image classification in a communication-limited scenario to analyze how the models perform with limited training data. The use of transfer learning can ameliorate the issue of poor generalization by transferring features learned from training on a large source dataset for one classification task to the target classification task with limited training data. For two deep-learning models from literature, we compare the accuracy of the models trained using transfer learning to models trained from scratch using a random weight initialization with varying amounts of training data. We demonstrate the feasibility and performance of running inference of the deep-learning models on representative flight-like hardware.

Advanced Avionics, Machine Learning, Data Processi↗