Search NASA⌕ Search

SEARCH · Search NASA

Results for “Generative 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.

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

At least 595 records · Page 33

Generalizability of Manual Control Skills Between Control Tasks of Varying Difficulty

This paper presents the results of an experiment that was performed at NASA Ames Research Center using 18 participants in two different groups who trained a task for ten days, with the goal of identifying how skill generalization would occur between two similar tasks of varying difficulty. A cybernetic approach was used. The first group was trained in a simple one-dimensional tracking task and transferred to a difficult two-dimensional tracking task. For the second group, this was reversed. Training with a simple task before transferring to the difficult task resulted in a slower convergence to final performance. However, it did allow participants to start with a better initial performance in the difficult task. Furthermore, after training with a simple task, participants controlled with a higher gain and generated lower lead time constants. However, possibly due to the number of participants, this experiment did not find any statistical evidence to support the conclusion that training with a simple task version helps in learning a more complex task.

skill generalizability↗

Generalizability of Manual Control Skills between Control Tasks of Varying Difficulty

This paper presents the results of an experiment that was performed at NASA Ames Research Center using 18 participants in two different groups who trained a task for ten days, with the goal of identifying how skill generalization would occur between two similar tasks of varying difficulty. A cybernetic approach was used. The first group was trained in a simple one-dimensional tracking task and transferred to a difficult two-dimensional tracking task. For the second group, this was reversed. Training with a simple task before transferring to the difficult task resulted in a slower convergence to final performance. However, it did allow participants to start with a better initial performance in the difficult task. Furthermore, after training with a simple task, participants controlled with a higher gain and generated lower lead time constants. However, possibly due to the number of participants, this experiment did not find any statistical evidence to support the conclusion that training with a simple task version helps in learning a more complex task.

Pieters, Marc A.↗

GeneLab for High Schools – Bioinformatic Training For Students And Educators

Modern biological sciences are increasingly based on high-throughput molecular techniques, including genomics, transcriptomics, and proteomics. NASA’s GeneLab program has collected extensive data from ‘omics’ studies, curated them into an accessible platform and provided data analysis/visualization tools to facilitate the generation of new hypotheses and research directions. GeneLab for High Schools (GL4HS), launched in 2017, has endeavored to utilize this database and provide tools for students to understand and analyze omics datasets whilst also learning about spaceflight research. The GL4HS program ran in person at Ames from 2017-2019 and has run virtually since 2020. Each year fifteen high school students are trained to analyze and interpret GeneLab transcriptomic data. Additionally, in the last several years we have expanded our “teacher training program” to include 10 teachers total in an effort to enable this program to be utilized in classrooms across the USA. Teachers also join the NASA GeneLab Education Working Group (EWG) enabling support as they implement custom GL4HS modules into their classrooms. The GL4HS program consists of three main components – (1) core learning modules, (2) networking and teamwork, and (3) an independent learning project. Students are also taught critical networking and science communication skills facilitating their ability to ‘sell their science’ in innovative and creative ways. This program has enabled students to learn about biology in space and to have a glimpse into the world of research for the first time. Many of the students in this program shared that the course was transformative to their perception about biological sciences and how it linked to other areas of STEM. The ultimate and long-term goal of GL4HS is to expand the program to multiple locations thereby facilitating the reach of NASA Space Biology beyond NASA-centric regions.

GeneLab↗

Independent Reliability Assessment of the NASA GSFC Laser Transmitter for the LISA Program

The Laser Interferometer Space Antenna (LISA) is a partnership between the European Space Agency (ESA) and NASA to build a Gravitational Wave (GW) observatory. The observatory, which consists of a three-spacecraft constellation with a nominal separation of 2.5 million km between each spacecraft, provides a tool for scientists to directly detect gravitational waves generated from various astronomical phenomena in a waveband that is not accessible from Earth. NASA is developing laser transmitters as one of the potential US contributions to LISA. The NASA laser design leverages lessons learned from previous flight missions and included the latest technologies in photonics packaging and reliability engineering to ensure a laser lifetime of >16 years covering integration and test through a possible extended mission phase. As part of the laser development process, NASA’s Goddard Space Flight Center (GSFC) requested support from the NASA Engineering and Safety Center (NESC) to independently assess the Technology Readiness Level (TRL) of the LISA Laser System (LS). The independent assessment included the following tasks: (a) assess the design for weaknesses and suggest improvements to mitigate risks, (b) assess the laser reliability plan for weaknesses and suggest improvements to mitigate risks and improve effectiveness, and (c) assess the current redundancy plan on laser subsystems for weaknesses and suggest improvements to mitigate risks and improve effectiveness. The NESC team comprised of a team of subject matter experts (SMEs) and performed a 12-month review of every aspect of the laser design. We present the assessment findings and the current development progress of the LISA laser to meet the mission requirements with a delivery of a form, fit, and functional TRL6 laser to the LSIA mission by late 2023.

LISA↗

An expert system shell for inferring vegetation characteristics

The NASA VEGetation Workbench (VEG) is a knowledge based system that infers vegetation characteristics from reflectance data. The report describes the extensions that have been made to the first generation version of VEG. An interface to a file of unkown cover type data has been constructed. An interface that allows the results of VEG to be written to a file has been implemented. A learning system that learns class descriptions from a data base of historical cover type data and then uses the learned class descriptions to classify an unknown sample has been built. This system has an interface that integrates it into the rest of VEG. The VEG subgoal PROPORTION.GROUND.COVER has been completed and a number of additional techniques that infer the proportion ground cover of a sample have been implemented.

Harrison, P. Ann↗

Machine Learning the COSMO Model for Predicting Thermodynamics of Electrolyte Mixtures

Bottom-up design of electrolyte mixtures for battery systems requires predicting macro thermodynamic properties from molecular constituents. For instance, molten salt electrolyte batteries require conditions far above room temperature to operate. Therefore, discovering mixtures with increasingly lower eutectic melting points is desirable. A model that can approximate chemical activity is a valuable tool to search through the vast compositional design space. Machine learning can predict properties of materials such as vibrational free energies, electronic energy gaps, and thermal conductivities. Moreover, they can learn physical models such as interatomic potentials. The COSMO-SAC model uses theory and empirical parameterization to predict liquid-vapor and liquid-solid properties using first-principles calculations. However, obtaining activity coefficients required for parameterizing the COSMO-SAC model is costly and limited to a select chemical space. In this work, we explored if machine learning methods could improve the COSMO-SAC model and bridge density functional theory calculations to liquid phase thermodynamic properties. Our data-driven approach uses existing databases for sigma-profiles of organic solvents and reconciles their methodological differences via ensemble averaging. First, an optimal machine learning model is constructed for each dataset. Our machine learning algorithms use the sigma-profile as an input feature to predict binary mixtures' activity coefficients using multi-output regression. Each dataset uses different choices of functionals, methods, and basis sets. Therefore, our ensemble model attempts to predict corrected activity coefficients given the combination of all the model outputs. The activity coefficients used for training are generated using the COSMO-SAC model. This approach enables the extraction of meaningful information from the existing datasets to improve the COSMO-SAC model for obtaining thermodynamic properties of electrolyte mixtures. With the liquid phase activities, we can identify electrolyte mixtures that meet desired phase equilibria conditions.

Thermodynamics↗

ISSLIVE! Bringing the Space Station to Every Generation

Just 200 miles above us, the International Space Station (ISS) is orbiting. Each day, the astronauts on board perform a variety of activities from exercise, science experiments, and maintenance. Yet, many on the ground don?t know about these daily activities. ISSLive! - an education project - is working to bridge this knowledge gap with traditional education channels such as schools, but also non-traditional channels with the non-technical everyday public. ISSLive! provides a website that seamlessly integrates planning and telemetry data, video feeds, 3D models, and iOS and android applications. Through the site, users are able to view astronauts? daily schedules, in plain English alongside the original data. As an example, when an astronaut is working with a science experiment, a user will be able to read about the activity and for more detailed activities follow provided links to view more information -- all integrated into the same site. Live telemetry data from a predefined set can also be provided alongside the activities. For users to learn more, 3D models of the external and internal parts of the ISS are available, allowing users to explore the station and even select sensors, such as temperature, and view a real-time chart of the data. Even ground operations are modelled with a 3D mission control center, providing users information on the various flight control disciplines and showing live data that they would be monitoring. Some unique activities are also highlighted, and have dedicated spaces to explore in more detail. Education is the focus of ISSLive!, even from the beginning when university students participated in the development process as part of their master?s projects. Focus groups at a Houston school showed interest in the project, and excitement towards including ISSLive! in their classroom. Through this inclusion, student?s knowledge can be assessed with projects, oral presentations, and other assignments. For the public citizens outside of the traditional education system, ISSLive! provides a single, interactive, and engaging experience to learn about the ISS and its role in space exploration, international collaboration, and science. While traditional students are using ISSLive! in the classroom, their parents, grandparents, and friends are using it at home. ISSLive! truly brings the daily operations of the ISS into the daily lives of the public from every generation.

Harris, Philip D.↗

NASA/Mir Phase 1: A Lesson Learned in Long Duration Mission Planning and Operations

The NASA/Mir Phase I Program is a precursor to the assembly and operations of the International Space Station (ISS). The Phase I Program covers a four-year period and encompasses over ten shuttle flights to the Mir, culminating with the flight of STS-91 in June 1998. The Mir-Orbiting Station (Mir-OS) provides an excellent environment, both onboard and on the ground, for learning and studying the characteristics associated with crew-tended operations on long duration missions. By the end of the Phase I program, NASA astronauts will have accumulated over two years of continuous operations experience working and living onboard the Mir-OS. Ground controllers, working in Russia and at remote sites in the United States, will have gained valuable experience in the generation, maintenance, and coordination of the information and products required to support the long duration crew members onboard the Mir-OS. The experience gained by the crew and ground support personnel in the area of long duration mission operations has resulted in a number of factors that need to be considered in the definition and implementation of the processes and products for the ISS. While there are many areas in which experience has been gained, this paper focuses on the lessons learned regarding the level of detail and flexibility of crew timelines. Provided in this paper is an overview of the characteristics associated with long duration mission timeline development and execution, a summary of applicable lessons learned identified and documented through participation in the NASA/Mir Phase I Program, a detailed discussion of "Gross Timelines" as implementation which addresses the lessons learned. Also discussed are the challenges that must be overcome in getting the ISS program to recognize, evaluate, and learn from the crew and ground controller experience gained through participation in the NASA/Mir Phase I Program.

Hagopian, Jeff↗

Gravity Sensor Plasticity in the Space Environment

The ability of the brain to learn from experience and to adapt to new environments is recognized to be profound. This ability, called 'neural plasticity,' depends directly on properties of neurons (nerve cells) that permit them to change in dimension, sprout new parts called spines, change the shape and/or size of existing parts, and to generate, alter, or delete synapses. (Synapses are communication sites between neurons.) These neuronal properties are most evident during development, when evolution guides the laying down of a general plan of the nervous system. However, once a nervous system is established, experience interacts with cellular and genetic mechanisms and the internal milieu to produce unique neuronal substrates that define each individual. The capacity for experience-related neuronal growth in the brain, as measured by the potential for synaptogenesis, is speculated to be in the trillions of synapses, but the range of increment possible for any one part of the nervous system is unknown. The question has been whether more primitive endorgans such as gravity sensors of the inner ear have a capacity for adaptive change, since this is a form of learning from experience.

Ross, Muriel D.↗

Learning Lessons from the X-37 Project

The X-37 was planned as an automated vehicle capable of flight-testing new aerospace technologies in combined environments that are beyond the capability of existing ground or flight platforms. Flight demonstration with the X-37 architecture and configuration in relevant environments was planned to reduce the risk of developing launch vehicle technologies for sustainable, affordable exploration and other aerospace applications. Current plans are for the X-37 Approach and Landing Test Vehicle (ALTV) to be atmospheric tested in 2005 from Scaled Composite's White Knight carrier aircraft at up to 40,000 feet over California's Mojave Spaceport, with and turnaround maintenance performed. The fight Operations Control Center will conduct the mission, using a streamlined operations concept. Taxi-tow and captive-carry tests will be conducted prior to the atmospheric-test series. Sponsored by the Defense Advanced Research Projects Agency (DARPA) with NASA participation, technical objectives are to: (1) mature Computed Air Data System/Remote Pressure Sensor technology, (2) manage energy during Terminal Area Energy Management/Heading Alignment Cone maneuvers, and (3) validate the aerodatabase. The X-37 Project began in 1999 under a cooperative agreement as an element of NASA's Future X Program and transitioned to a NASA Research Announcement under the Space Launch Initiative. In mid-2004, NASA transferred ownership to DARPA, with its heritage of performing high-risk, high-payoff research and development. NASA contributes technical expertise, including risk analysis and system integration. The Boeing Company is the prime contractor, with nationwide suppliers. This recent partnership exemplifies the synergy attainable when NASA Centers, other Government agencies, and industry work together toward a common goal - contributing to the knowledge base for U.S. exploration and other aerospace endeavors. The X-37 team represents a range of space transportation disciplines - from engineering to management. Some members have been with the project since its inception. All have gained priceless experience during the design, manufacturing, and testing of the ALTV, as well as through developing advanced orbital flight technologies, such as state-of-the-art Thermal Protection Systems and hot structures. Throughout this process, the X-37 Project team captures lessons that are directly applicable to other such efforts. The upcoming ALTV flights offer another dimension of data and first-hand experience that will prove invaluable to those designing new generations of reusable spacecraft. And ongoing technology developments will expand the aerospace knowledge base. Delivering prototype hardware is always a risky proposition. During the course of the X-37 effort, the team has experienced many challenging opportunities, delivering significant accomplishments and learning numerous lessons in the process. The ability to manage the risk landscape is key to overcoming obstacles, especially technical hurdles that are encountered in progressing hardware from design to flight. The approach to managing risk under this partnership is evolving but, in general, the team allocates resources to reduce the likelihood of severe-consequence risks, thus maximizing mission success and ensuring that the X-37 Project delivers value to its stakeholders. As the team sharpens its focus on operations, it continues to contribute knowledge to those who would undertake high-risk, high-payoff research and development and provides valuable experience to implement the exploration vision.

Turner, Susan↗

Learning Lessons from the X-37 Project

The X-37 was planned as an automated vehicle capable of flight-testing new aerospace technologies in combined environments that are beyond the capability of existing ground or flight platforms. Flight demonstration with the X-37 architecture and configuration in relevant environments was planned to reduce the risk of developing launch vehicle technologies for sustainable, affordable exploration and other aerospace applications. Current plans are for the X-37 Approach and Landing Test Vehicle (ALTV) to be atmospheric tested in 2005 from Scaled Composite s White Knight carrier aircraft at up to 40,000 feet over California's Mojave Spaceport, with landing and turnaround maintenance performed. The Flight Operations Control Center will conduct the mission, using a streamlined operations concept. Taxi-tow and captive-carry tests will be conducted prior to the atmospheric-test series. Sponsored by the Defense Advanced Research Projects Agency (DARPA) with NASA participation, technical objectives are to: (1) mature Computed Air Data System/Remote Pressure Sensor technology, (2) manage energy during Terminal Area Energy Management/Heading Alignment Cone maneuvers, and (3) validate the aerodatabase. The X-37 Project began in 1999 under a cooperative agreement as an element of NASA's Future X Program and transitioned to a NASA Research Announcement under the Space Launch Initiative. In mid-2004, NASA transferred ownership to DARPA, with its heritage of performing high-risk, high-payoff research and development (R&D). NASA contributes technical expertise, including risk analysis and system integration. The Boeing Company is the prime contractor, with nationwide suppliers. This partnership exemplifies the synergy attainable when NASA Centers, other Government agencies, and industry work together toward a common goal - contributing to the knowledge base for U.S. exploration and other aerospace endeavors. The X-37 team represents a range of space transportation disciplines - from engineering to management. Some members have been with the project since its inception. All have gained priceless experience during the design, manufacturing, and testing of the ALTV, as well as through developing advanced orbital flight technologies, such as state-of-the-art Thermal Protection Systems and hot structures. Throughout this process, the X-37 Project team captures lessons that are directly applicable to other such efforts. The upcoming ALTV flights offer another dimension of data and first-hand experience that will prove invaluable to those designing new generations of reusable spacecraft. And ongoing technology developments will expand the aerospace knowledge base. Delivering prototype hardware is always a risky proposition. During the course of this effort, the X-37 team has experienced many challenging opportunities, delivering significant accomplishments and learning numerous lessons in the process. The ability to manage the risk landscape is key to overcoming obstacles, especially technical hurdles that are encountered in progressing hardware from design to flight. The approach to managing risk under this partnership is evolving but, in general, the team allocates resources to reduce the likelihood of severe-consequence risks, thus maximizing mission success and ensuring that the X-37 Project delivers value to its stakeholders. As the team sharpens its focus on operations, it continues to contribute knowledge to those who would undertake high-risk, high-payoff R&D and provides valuable experience to implement the Vision for Space Exploration.

Turner, Susan↗

Understanding Machine Learning in Earth Science: A Natural Language Processing Approach

Machine learning (ML) is being increasingly utilized in Earth science research. Benefits of ML include efficiency, reduction of human error, and ability to extract hidden patterns within data. However, the mutual lack of each other’s domain knowledge by ML and Earth science stands as a barrier to timely and effective implementation. Earth science, in particular, faces challenges in generating sample data, compared to those of traditional ML problems such as face recognition or stock predictions, where data is abundant and not lacking in ground truth, which is necessary for labeling. Earth science data are more varying in formats, such as HDF5 and image resolutions, and are not standardized across instruments, even within a given Earth science discipline. Previous studies have been done to outline the specific challenges that Earth science faces with ML, while others have focused on using existing publications to mine information efficiently. Other resources such as Scikit-Learn have developed decision trees for choosing appropriate machine learning algorithms, but application within Earth science subjects becomes much more complex. For the current study, we propose a methodology and tool that aids in implementation of ML in Earth science using natural language processing (NLP). Our work comprises three main parts: (1) analyzing existing publications related to ML and Earth science, using natural language processing: (2) extracting from the publications information on ML models subjects in Earth Science: and (3) visualizing the extracted relationships as a network graph. The resulting network graph should aid the Earth science communities in applying optimal ML algorithms and guiding data preparation through visualization of similar studies. The network graph and analysis of document similarity will be the basis of our next step, which is to develop a decision tree for selecting optimal machine learning methodologies for specified Earth science applications.

Zheng, Laura↗

A Cognitive Systems Engineering Approach to Developing HMI Requirements for New Technologies

This document examines the challenges inherent in designing and regulating to support human-automation interaction for new technologies that will deployed into complex systems. A key question for new technologies, is how work will be accomplished by the human and machine agents. This question has traditionally been framed as how functions should be allocated between humans and machines. Such framing misses the coordination and synchronization that is needed for the different human and machine roles in the system to accomplish their goals. Coordination and synchronization demands are driven by the underlying human-automation architecture of the new technology, which are typically not specified explicitly by the designers. The human machine interface (HMI) which is intended to facilitate human-machine interaction and cooperation, however, typically is defined explicitly and therefore serves as a proxy for human-automation cooperation requirements with respect to technical standards for technologies. Unfortunately, mismatches between the HMI and the coordination and synchronization demands of the underlying human-automation architecture, can lead to system breakdowns. A methodology is needed that both designers and regulators can utilize to evaluate the expected performance of a new technology given potential human-automation architectures. Three experiments were conducted to inform the minimum HMI requirements a detect and avoid system for unmanned aircraft systems (UAS). The results of the experiments provided empirical input to specific minimum operational performance standards that UAS manufacturers will have to meet in order to operate UAS in the National Airspace System (NAS). These studies represent a success story for how to objectively and systematically evaluate prototype technologies as part of the process for developing regulatory requirements. They also provide an opportunity to reflect on the lessons learned from a recent research effort in order to improve the methodology for defining technology requirements for regulators in the future. The biggest shortcoming of the presented research program was the absence of the explicit definition, generation and analysis of potential human-automation architectures. Failure to execute this step in the research process resulted in less efficient evaluation of the candidate prototypes technologies in addition to the complete absence of different approaches to human-automation cooperation. For example, all of the prototype technologies that were evaluated in the research program assumed a human-automation architecture that relied on serial processing from the automation to the human. While this type of human-automation architecture is typical across many different technologies and in many different domains, it ignores different architectures where humans and automation work in parallel. Defining potential human-automation architectures a priori also allows regulators to develop scenarios that will stress the performance boundaries of the technology during the evaluation phase. The importance of adding this step of generating and evaluating candidate human-automation architectures prior to formal empirical evaluation is discussed.

human systems integration↗

Multi-Objective Reinforcement Learning for Cognitive Radio Based Satellite Communications

Previous research on cognitive radios has addressed the performance of various machine learning and optimization techniques for decision making of terrestrial link properties. In this paper, we present our recent investigations with respect to reinforcement learning that potentially can be employed by future cognitive radios installed onboard satellite communications systems specifically tasked with radio resource management. This work analyzes the performance of learning, reasoning, and decision making while considering multiple objectives for time-varying communications channels, as well as different crosslayer requirements. Based on the urgent demand for increased bandwidth, which is being addressed by the next generation of high-throughput satellites, the performance of cognitive radio is assessed considering links between a geostationary satellite and a fixed ground station operating at Ka-band (26 GHz). Simulation results show multiple objective performance improvements of more than 3:5 times for clear sky conditions and 6:8 times for rain conditions.

ionosphere↗

Hybrid Model Based Approaches for Systems Health Management and Prognostics

To facilitate and solve the prediction problem, awareness of the current health state of the system is key, since it is necessary to perform condition-based predictions. To accurately predict the future state of any system, it is required to possess knowledge of its current health state and future operational conditions. Latest achievements of data-driven algorithms in regression of complex nonlinear functions and classification tasks have generated a growing interest in artificial intelligence for industrial applications. Complex multi-physics models as well as digital twins, once purely built on physics and corresponding simplified lumped parameter iterations, can now benefit from machine learning algorithms to mitigate the lack of understanding of some complex behavior. Given models of the current and future system behavior, a general approach of model-based prognostics can solve the prediction problem and further decision making. In principle, data driven approaches can replace expensive experimental test-setups as well as reduce the number of simulations needed to explore, e.g., the parametric space of a multi-parameter model. Nonetheless, the limitations of pure data-driven methods came to light rather quickly, at least for some industries. In many industrial applications, data acquisition is costly, and the volume of data that can be collected does not satisfy the requirements for an effective model training and cross-validation. Therefore, some recent works in the area of machine learning is focusing on blending physics with data-driven algorithms, thus mitigating the drawbacks of the two approaches and emphasizing respective advantages. Partial physical knowledge of the problem can aid the learning process by “guiding” the algorithm towards efficient solutions that satisfy the physics driving the system behavior. The result is a hybrid modeling approach combining physical knowledge as well data driven methods to develop a unified hybrid approach. A hybrid framework for fusing information from physics-based performance models along with deep learning algorithms for prognostics of complex safety critical systems is presented. In this framework, physics-based performance models infer unobservable model parameters related to the system's components health solving a calibration problem in the deep learning approach.

Hybrid Modeling↗

Systems Health Management and Prognostics Approaches for Electric Aircrafts

As more and more electric vehicles emerge in our daily operation progressively, a very critical challenge lies in the prediction of remaining driving flying time/distance for the flying vehicles. This information is important, particularly in the case of auto vehicles, because such vehicles can become self-aware, autonomously compute its own capabilities, and identify how to best plan and successfully complete vehicular missions safely. In case of electric aircrafts, computing the remaining flying time is also safety-critical, since an aircraft that runs out of power (battery charge) while in the air will eventually lose control leading to catastrophe. To facilitate and solve the prediction problem, awareness of the current health state of the system is key, since it is necessary to perform condition-based predictions. To accurately predict the future state of any system, it is required to possess knowledge of its current health state and future operational conditions. Latest achievements of data-driven algorithms in regression of complex nonlinear functions and classification tasks have generated a growing interest in artificial intelligence for industrial applications. Complex multi-physics models as well as digital twins, once purely built on physics and corresponding simplified lumped parameter iterations, can now benefit from machine learning algorithms to mitigate the lack of understanding of some complex behavior. Given models of the current and future system behavior, a general approach of model-based prognostics can solve the prediction problem and further decision-making. A systematic prediction framework is implemented to identify all possible sources of uncertainty, quantify each of them individually, and mathematically estimate their combined effect on the system-level quantity of interest, in this case, the remaining flying time/distance of the unmanned aircraft. Note - This presentation contains all previously published information.

Systems Health Managent↗

Temporal Interpolation of Geostationary Satellite Imagery With Optical Flow

Applications of satellite data in areas such as weather tracking and modeling, ecosystem monitoring, wildfire detection, and land-cover change are heavily dependent on the tradeoffs to spatial, spectral, and temporal resolutions of observations. In weather tracking, high-frequency temporal observations are critical and used to improve forecasts, study severe events, and extract atmospheric motion, among others. However, while the current generation of geostationary (GEO) satellites has hemispheric coverage at 10-15-min intervals, higher temporal frequency observations are ideal for studying mesoscale severe weather events. In this work, we present a novel application of deep learning-based optical flow to temporal upsampling of GEO satellite imagery. We apply this technique to 16 bands of the GOES-R/Advanced Baseline Imager mesoscale dataset to temporally enhance full-disk hemispheric snapshots of different spatial resolutions from 10 to 1 min. Experiments show the effectiveness of task-specific optical flow and multiscale blocks for interpolating high-frequency severe weather events relative to bilinear and global optical flow baselines. Finally, we demonstrate strong performance in capturing variability during convective precipitation events.

Image processing↗

Hybrid Approaches to Systems Health Management and Prognostics

To facilitate and solve the prediction problem, awareness of the current health state of the system is key, since it is necessary to perform condition-based predictions. To accurately predict the future state of any system, it is required to possess knowledge of its current health state and future operational conditions. Latest achievements of data-driven algorithms in regression of complex nonlinear functions and classification tasks have generated a growing interest in artificial intelligence for industrial applications. Complex multi-physics models as well as digital twins, once purely built on physics and corresponding simplified lumped parameter iterations, can now benefit from machine learning algorithms to mitigate the lack of understanding of some complex behavior. Given models of the current and future system behavior, a general approach of model-based prognostics can solve the prediction problem and further decision making. In principle, data driven approaches can replace expensive experimental test-setups as well as reduce the number of simulations needed to explore, e.g., the parametric space of a multi-parameter model. Nonetheless, the limitations of pure data-driven methods came to light rather quickly, at least for some industries. In many industrial applications, data acquisition is costly, and the volume of data that can be collected does not satisfy the requirements for an effective model training and cross-validation. Therefore, some recent works in the area of machine learning is focusing on blending physics with data-driven algorithms, thus mitigating the drawbacks of the two approaches and emphasizing respective advantages. Partial physical knowledge of the problem can aid the learning process by “guiding” the algorithm towards efficient solutions that satisfy the physics driving the system behavior. The result is a hybrid modeling approach combining physical knowledge as well data driven methods to develop a unified hybrid approach. A hybrid framework for fusing information from physics-based performance models along with deep learning algorithms for prognostics of complex safety critical systems is presented. In this framework, physics-based performance models infer unobservable model parameters related to the system's components health solving a calibration problem in the deep learning approach.

Systems Health Management↗