Results for “remote training” — Page 13

NASA NTRSDate not supplied

Applications of MERRA-2 data for avian migration, biomass burning, and dusty atmospheric rivers

Three different applications of MERRA-2 data are presented. 1) Using radar data, we introduced a new concept for spatial patterns of bird migration across the contiguous U.S. This approach allowed us to use MERRA-2 data and learn that remote forcing in the tropical Pacific—through a chain of processes including atmospheric Rossby wave trains— controls the climatic conditions, associated with bird migration in North America. 2) We showed that emissions from biomass burning in the Congo Basin are partly controlled by the low-level winds, which are in turn associated with the intensity of the subtropical high in the Indian Ocean. Using back-trajectory analysis, we found that these emissions combined with their transport mechanism explain the interannual variability of black carbon in West Africa. 3) Our analysis showed that atmospheric rivers in the Middle East contribute to both heavy flood and dust transport within their corridor. We also found that warm advection and rain-on-snow effect of dusty atmospheric rivers further enhance the chance of flood through rapid snowmelt processes.

Amin Dezfuli↗

NASA NTRSDate not supplied

Applications of MERRA-2 Data for Avian Migration, Biomass Burning, and Dusty Atmospheric Rivers

Three different applications of MERRA-2 data are presented. 1) Using radar data, we introduced a new concept for spatial patterns of bird migration across the contiguous U.S. This approach allowed us to use MERRA-2 data and learn that remote forcing in the tropical Pacific—through a chain of processes including atmospheric Rossby wave trains— controls the climatic conditions, associated with bird migration in North America. 2) We showed that emissions from biomass burning in the Congo Basin are partly controlled by the low-level winds, which are in turn associated with the intensity of the subtropical high in the Indian Ocean. Using back-trajectory analysis, we found that these emissions combined with their transport mechanism explain the interannual variability of black carbon in West Africa. 3) Our analysis showed that atmospheric rivers in the Middle East contribute to both heavy flood and dust transport within their corridor. We also found that warm advection and rain-on-snow effect of dusty atmospheric rivers further enhance the chance of flood through rapid snowmelt processes.

Amin Dezfuli↗

NASA NTRS2002

Development and Flight Testing of an Adaptive Vehicle Health-Monitoring Architecture

On going development and testing of an adaptable vehicle health-monitoring architecture is presented. The architecture is being developed for a fleet of vehicles. It has three operational levels: one or more remote data acquisition units located throughout the vehicle; a command and control unit located within the vehicle, and, a terminal collection unit to collect analysis results from all vehicles. Each level is capable of performing autonomous analysis with a trained expert system. The expert system is parameterized, which makes it adaptable to be trained to both a user's subject reasoning and existing quantitative analytic tools. Communication between all levels is done with wireless radio frequency interfaces. The remote data acquisition unit has an eight channel programmable digital interface that allows the user discretion for choosing type of sensors; number of sensors, sensor sampling rate and sampling duration for each sensor. The architecture provides framework for a tributary analysis. All measurements at the lowest operational level are reduced to provide analysis results necessary to gauge changes from established baselines. These are then collected at the next level to identify any global trends or common features from the prior level. This process is repeated until the results are reduced at the highest operational level. In the framework, only analysis results are forwarded to the next level to reduce telemetry congestion. The system's remote data acquisition hardware and non-analysis software have been flight tested on the NASA Langley B757's main landing gear. The flight tests were performed to validate the following: the wireless radio frequency communication capabilities of the system, the hardware design, command and control; software operation and, data acquisition, storage and retrieval.

Woodard, Stanley E.↗

NASA NTRS1975

International Conference on Remote Emergency Medical Services

An emergency medical system is characterized. Applications of NASA technology in biomedical telecommunication and bioinstrumentation are explored. The training and effectiveness of paramedics, technicians, nurses, and physicians are evaluated as applied to emergency situations and the operations of trauma centers. Civilian and military aeromedical evacuation is discussed.

Source record↗

NASA NTRS1975

Remote sensing of water quality in reservoirs and lakes in semi-arid climates

Overlake measurements using aerial cameras (remote sensing) combined with water truth collected from boats most economically provided wide-band photographs rather than precise spectra. With use of false color infrared film (400-950 nm), the reflected spectral signatures seen from hundreds to thousands of meters above the lake merged to produce various color tones. Such colors were easily and inexpensively obtained and could be recognized by lake management personnel without any prior training. The characteristic spectral signatures of various algal types were also recognizable in part by the color tone produced by remote sensing.

Anderson, H. M.↗

NASA NTRS2010

Design and Testing of a Prototype Lunar or Planetary Surface Landing Research Vehicle (LPSLRV)

This handbook describes a two-semester senior design course sponsored by the NASA Office of Education, the Exploration Systems Mission Directorate (ESMD), and the NASA Space Grant Consortium. The course was developed and implemented by the Mechanical and Aerospace Engineering Department (MAE) at Utah State University. The course final outcome is a packaged senior design course that can be readily incorporated into the instructional curriculum at universities across the country. The course materials adhere to the standards of the Accreditation Board for Engineering and Technology (ABET), and is constructed to be relevant to key research areas identified by ESMD. The design project challenged students to apply systems engineering concepts to define research and training requirements for a terrestrial-based lunar landing simulator. This project developed a flying prototype for a Lunar or Planetary Surface Landing Research Vehicle (LPSRV). Per NASA specifications the concept accounts for reduced lunar gravity, and allows the terminal stage of lunar descent to be flown either by remote pilot or autonomously. This free-flying platform was designed to be sufficiently-flexible to allow both sensor evaluation and pilot training. This handbook outlines the course materials, describes the systems engineering processes developed to facilitate design fabrication, integration, and testing. This handbook presents sufficient details of the final design configuration to allow an independent group to reproduce the design. The design evolution and details regarding the verification testing used to characterize the system are presented in a separate project final design report. Details of the experimental apparatus used for system characterization may be found in Appendix F, G, and I of that report. A brief summary of the ground testing and systems verification is also included in Appendix A of this report. Details of the flight tests will be documented in a separate flight test report. This flight test report serves as a complement to the course handbook presented here. This project was extremely ambitious, and achieving all of the design and test objectives was a daunting task. The schedule ran slightly longer than a single academic year with the complete design closure not occurring until early April. Integration and verification testing spilled over into late May and the first flight did not occur until mid to late June. The academic year at Utah State University ended on May 8, 2010. Following the end of the academic year, testing and integration was performed by the faculty advisor, paid research assistants, and volunteer student help

Murphy, Gloria A.↗

NASA NTRS2003

A Fast Implementation of the ISOCLUS Algorithm

Unsupervised clustering is a fundamental tool in numerous image processing and remote sensing applications. For example, unsupervised clustering is often used to obtain vegetation maps of an area of interest. This approach is useful when reliable training data are either scarce or expensive, and when relatively little a priori information about the data is available. Unsupervised clustering methods play a significant role in the pursuit of unsupervised classification. One of the most popular and widely used clustering schemes for remote sensing applications is the ISOCLUS algorithm, which is based on the ISODATA method. The algorithm is given a set of n data points (or samples) in d-dimensional space, an integer k indicating the initial number of clusters, and a number of additional parameters. The general goal is to compute a set of cluster centers in d-space. Although there is no specific optimization criterion, the algorithm is similar in spirit to the well known k-means clustering method in which the objective is to minimize the average squared distance of each point to its nearest center, called the average distortion. One significant feature of ISOCLUS over k-means is that clusters may be merged or split, and so the final number of clusters may be different from the number k supplied as part of the input. This algorithm will be described in later in this paper. The ISOCLUS algorithm can run very slowly, particularly on large data sets. Given its wide use in remote sensing, its efficient computation is an important goal. We have developed a fast implementation of the ISOCLUS algorithm. Our improvement is based on a recent acceleration to the k-means algorithm, the filtering algorithm, by Kanungo et al.. They showed that, by storing the data in a kd-tree, it was possible to significantly reduce the running time of k-means. We have adapted this method for the ISOCLUS algorithm. For technical reasons, which are explained later, it is necessary to make a minor modification to the ISOCLUS specification. We provide empirical evidence, on both synthetic and Landsat image data sets, that our algorithm's performance is essentially the same as that of ISOCLUS, but with significantly lower running times. We show that our algorithm runs from 3 to 30 times faster than a straightforward implementation of ISOCLUS. Our adaptation of the filtering algorithm involves the efficient computation of a number of cluster statistics that are needed for ISOCLUS, but not for k-means.

Memarsadeghi, Nargess↗

NASA NTRS1993

A review and analysis of neural networks for classification of remotely sensed multispectral imagery

A literature survey and analysis of the use of neural networks for the classification of remotely sensed multispectral imagery is presented. As part of a brief mathematical review, the backpropagation algorithm, which is the most common method of training multi-layer networks, is discussed with an emphasis on its application to pattern recognition. The analysis is divided into five aspects of neural network classification: (1) input data preprocessing, structure, and encoding; (2) output encoding and extraction of classes; (3) network architecture, (4) training algorithms; and (5) comparisons to conventional classifiers. The advantages of the neural network method over traditional classifiers are its non-parametric nature, arbitrary decision boundary capabilities, easy adaptation to different types of data and input structures, fuzzy output values that can enhance classification, and good generalization for use with multiple images. The disadvantages of the method are slow training time, inconsistent results due to random initial weights, and the requirement of obscure initialization values (e.g., learning rate and hidden layer size). Possible techniques for ameliorating these problems are discussed. It is concluded that, although the neural network method has several unique capabilities, it will become a useful tool in remote sensing only if it is made faster, more predictable, and easier to use.

Paola, Justin D.↗

NASA NTRS1983

Application of the Hardman methodology to the Army Remotely Piloted Vehicle (RPV)

The application of the HARDMAN Methodology to the Remotely Piloted Vehicle (RPV) is described. The methodology was used to analyze the manpower, personnel, and training (MPT) requirements of the proposed RPV system design for a number of operating scenarios. The RPV system is defined as consisting of the equipment, personnel, and operational procedures needed to perform five basic artillery missions: reconnaissance, target acquisition, artillery adjustment, target designation and damage assessment. The RPV design evaluated includes an air vehicle (AV), a modular integrated communications and navigation system (MICNS), a ground control station (GCS), a launch subsystem (LS), a recovery subsystem (RS), and a number of ground support requirements. The HARDMAN Methodology is an integrated set of data base management techniques and analytic tools, designed to provide timely and fully documented assessments of the human resource requirements associated with an emerging system's design.

Source record↗

NASA NTRS2007

Window Observational Research Facility (WORF)

This viewgraph document concerns the Window Observational Research Facility (WORF) Rack, a unique facility designed for use with the US Lab Destiny Module window. WORF will provide valuable resources for Earth Science payloads along with serving the purpose of protecting the lab window. The facility can be used for remote sensing instrumentation test and validation in a shirt sleeve environment. WORF will also provide a training platform for crewmembers to do orbital observations of other planetary bodies. WORF payloads will be able to conduct terrestrial studies utilizing the data collected from utilizing WORF and the lab window.

Pelfrey, Joseph↗

NASA NTRS1998

Development of a Portable, Ground-Based Ozone Lidar Instrument for Tropospheric Ozone Research and Educational Training

The objective of this project is to develop a portable, eye-safe, ground-based ozone lidar instrument specialized for ozone differential absorption lidar (DIAL) measurements in the troposphere. This prototype instrument is intended to operate at remote field sites and to serve as the basic unit for monitoring projects requiring multi-instrument networks, such as that discussed in the science plan for the Global Tropospheric Ozone Project (GTOP). This instrument will be based at HU for student training in lidar technology as well as atmospheric ozone data analysis and interpretation. It will be also available for off-site measurement campaigns and will serve as a test bed for further instrument development. Later development beyond this grant to extend the scientific usefulness of the instrument may include incorporation of an aerosol channel and upgrading the laser to make stratospheric ozone measurements. Undergraduate and graduate students have been and will be active participants in this research effort.

Chyba, Thomas↗

NASA NTRS1993

Application of neural network to remote sensing of soil moisture using theoretical polarimetric backscattering coefficients

This paper investigates the potential application of neural network to inversion of soil moisture using polarimetric remote sensing data. The neural network used for the inversion of soil parameters is multi-layer perceptron trained with the back-propagation algorithm. The training data include the polarimetric backscattering coefficients obtained from theoretical surface scattering models together with an assumed nominal range of soil parameters which are comprised of the soil permittivity and surface roughness parameters. Soil permittivity is calculated from the soil moisture and the assumed soil texture based on an empirical formula at C-, L-, and P-bands. The rough surface parameters for the soil surface, which is described by the Gaussian random process, are the root-mean-square (rms) height and correlation length. For the rough surface scattering, small perturbation method is used for the L-band frequency, and Kirchhoff approximation is used for the C-band frequency to obtain the corresponding backscattering coefficients. During the training, the backscattering coefficients are the inputs to the neural net and the output from the net are compared with the desired soil parameters to adjust the interconnecting weights. The process is repeated for each input-output data entry and then for the entire training data until convergence is reached. After training, the backscattering coefficients are applied to the trained neural net to retrieve the soil parameters which are compared with the desired soil parameters to verify the effectiveness of this technique. Several cases are examined. First, for simplicity, the correlation length and rms height of the soil surface are fixed while soil moisture is varied. Soil moisture obtained using the neural networks with either L-band or C-band backscattering coefficients for the HH and VV polarizations as inputs is in good agreement with the desired soil moisture. The neural net output matches the desired output for the soil moisture range of 16 to 60 percent for the C-band case. The next case investigated is to vary both soil moisture and rms height while keeping the correlation length fixed. For this case, C-band backscattering coefficients are not sufficient for retrieving two parameters because the Kirchhoff approximation gives the same HH and VV backscattering coefficients. Therefore, the backscattering coefficients at two different frequency bands are necessary to find both the soil moisture and rms height. Finally, the neural nets are also applied to simultaneously invert soil moisture, rms height, and correlation length. Overall, the soil moisture retrieved from the neural network agrees very well with the desired soil moisture. This suggests that the neural network shows potential for retrieval of soil parameters from remote sensing data.

Wang, L.↗

NASA NTRS1975

ERIPS: Earth Resource Interactive Processing System

The ERIPS is an interactive computer system used in the analysis of remotely sensed data. It consists of a set of software programs which are executed on an IBM System/360 Model 75J computer under the direction of a trained analyst. The software was a derivative of the Purdue LARSYS program and has evolved to include an extensive pattern recognition system and a number of manipulative, preprocessing routines which prepare the imagery for the pattern recognition application. The original purpose of the system was to analyze remotely sensed data, to develop and perfect techniques to process the data, and to determine the feasibility of applying the data to significant earth resources problems. The System developed into a production system. Error recovery and multi-jobbing capabilities were added to the system.

Quinn, M. J.↗

NASA NTRS2017

Medical Support for ISS Crewmember Training in Star City, Russia

Medical support of spaceflight training operations across international lines is a unique circumstance with potential applications to other aerospace medicine support scenarios. KBRwyle's Star City Medical Support Group (SCMSG) has fulfilled this role since the Mir-Shuttle era, with extensive experience and updates to share with the greater AsMA community. OVERVIEW: The current Soyuz training flow for assigned ISS crewmembers takes place in Star City, Russia. Soyuz training flow involves numerous activities that pose potential physical and occupational risks to crewmembers, including centrifuge runs and pressurized suit simulations at ambient and hypobaric pressures. In addition, Star City is a relatively remote location in a host nation with variable access to reliable, Western-standard medical care. For these reasons, NASA's Human Health & Performance contract allocates full-time physician support to assigned ISS crewmembers training in Star City. The Star City physician also treats minor injuries and illnesses as needed for both long- and short-term NASA support personnel traveling in the area, while working to develop and maintain relationships with local health care resources in the event of more serious medical issues that cannot be treated on-site. The specifics of this unique scope of practice will be discussed. SIGNIFICANCE: ISS crewmembers training in Star City are at potential physical and occupational risk of trauma or dysbarism during nominal Soyuz training flow, requiring medical support from an on-duty aerospace medicine specialist. This support maintains human health and performance by preserving crewmember safety and well-being for mission success; sharing information regarding this operational model may contribute to advances in other areas of international, military, and civilian operational aerospace medicine.

Chough, Natacha↗

NASA NTRS2017

Medical Support for ISS Crewmember Training in Star City, Russia

Medical support of spaceflight training operations across international lines is a unique circumstance with potential applications to other aerospace medicine support scenarios. KBRwyle's Star City Medical Support Group (SCMSG) has fulfilled this role since the Mir-Shuttle era, with extensive experience and updates to share with the greater AsMA community. OVERVIEW: The current Soyuz training flow for assigned ISS crewmembers takes place in Star City, Russia. Soyuz training flow involves numerous activities that pose potential physical and occupational risks to crewmembers, including centrifuge runs and pressurized suit simulations at ambient and hypobaric pressures. In addition, Star City is a relatively remote location in a host nation with variable access to reliable, Western-standard medical care. For these reasons, NASA's Human Health & Performance contract allocates full-time physician support to assigned ISS crewmembers training in Star City. The Star City physician also treats minor injuries and illnesses as needed for both long- and short-term NASA support personnel traveling in the area, while working to develop and maintain relationships with local health care resources in the event of more serious medical issues that cannot be treated on-site. The specifics of this unique scope of practice will be discussed. SIGNIFICANCE: ISS crewmembers training in Star City are at potential physical and occupational risk of trauma or dysbarism during nominal Soyuz training flow, requiring medical support from an on-duty aerospace medicine specialist. This support maintains human health and performance by preserving crewmember safety and well-being for mission success; sharing information regarding this operational model may contribute to advances in other areas of international, military, and civilian operational aerospace medicine.

Chough, Natacha↗

NASA NTRS1992

A global change data base using Thematic Mapper data - Earth Monitoring Educational System (EMES)

Some of the main directions in creating an education program in earth system science aimed at combining top science and technology with high academic performance are presented. The creation of an Earth Monitoring Educational System (EMES) integrated with the research interests of the NASA Ames Research Center and one or more universities is proposed. Based on the integration of a global network of cooperators to build a global data base for assessments of global change, EMES would promote degrees at all levels in global ecology at associated universities and colleges, and extracurricular courses for multilevel audiences. EMES objectives are to: train specialists; establish a tradition of solving regional problems concerning global change in a systemic manner, using remote sensing technology as the monitoring tool; and transfer knowledge on global change to the national and world communities. South America is proposed as the pilot continent for the project.

D'Antoni, Hector L.↗

NASA NTRS1997

NASA Worldwide Emergency Medical Assistance

In an effort to maintain employee health and welfare, ensure customer satisfaction, and to deliver high quality emergency medical care when necessary to employees located overseas, NASA has instituted a new contract with International SOS Assistance INC. International SOS Assistance INC. will provide civil servants and contractors engaged in official NASA business with many services upon request during a medical or personal emergency. Through the years, International SOS Assistance INC. has developed the expertise necessary to provide medical service in all remote areas of the world. One phone call connects you to the SOS network of multilingual staff trained to help resolve travel, medical, legal, and security problems. The SOS network of critical care and aeromedical specialists operates 24 hours a day, 365 days a year from SOS Alarm Centers around the world. This exhibit illustrates the details of the NASA-International SOS Assistance INC. agreement.

Martin, George A.↗

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↗