Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “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 415 records · Page 23

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 cross-layer 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.

software defined radio↗

Challenges in the Verification of Reinforcement Learning Algorithms

Machine learning (ML) is increasingly being applied to a wide array of domains from search engines to autonomous vehicles. These algorithms, however, are notoriously complex and hard to verify. This work looks at the assumptions underlying machine learning algorithms as well as some of the challenges in trying to verify ML algorithms. Furthermore, we focus on the specific challenges of verifying reinforcement learning algorithms. These are highlighted using a specific example. Ultimately, we do not offer a solution to the complex problem of ML verification, but point out possible approaches for verification and interesting research opportunities.

Van Wesel, Perry↗

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↗

ISS Training Best Practices and Lessons Learned

Training our crew members for long duration exploration-class missions (LDEM) will have to be qualitatively and quantitatively different from current training practices. However, there is much to be learned from the extensive experience NASA has gained in training crew members for missions on board the International Space Station (ISS). Furthermore, the operational experience on board the ISS provides valuable feedback concerning training effectiveness. Keeping in mind the vast differences between current ISS crew training and training for LDEM, the needs of future crew members, and the demands of future missions, this ongoing study seeks to document current training practices and lessons learned. The goal of the study is to provide input to the design of future crew training that takes as much advantage as possible of what has already been learned and avoids as much as possible past inefficiencies. Results from this study will be presented upon its completion. By researching established training principles, examining future needs, and by using current practices in spaceflight training as test beds, this research project is mitigating program risks and generating templates and requirements to meet future training needs.

ISS↗

Machine Learning Approaches to Increasing Value of Spaceflight Omics Databases

The number of spaceflight bioscience mission opportunities is too small to allow all relevant biological and environmental parameters to be experimentally identified. Simulated spaceflight experiments in ground-based facilities (GBFs), such as clinostats, are each suitable only for particular investigations -- a rotating-wall vessel may be 'simulated microgravity' for cell differentiation (hours), but not DNA repair (seconds) -- and introduce confounding stimuli, such as motor vibration and fluid shear effects. This uncertainty over which biological mechanisms respond to a given form of simulated space radiation or gravity, as well as its side effects, limits our ability to baseline spaceflight data and validate mission science. Machine learning techniques autonomously identify relevant and interdependent factors in a data set given the set of desired metrics to be evaluated: to automatically identify related studies, compare data from related studies, or determine linkages between types of data in the same study. System-of-systems (SoS) machine learning models have the ability to deal with both sparse and heterogeneous data, such as that provided by the small and diverse number of space biosciences flight missions; however, they require appropriate user-defined metrics for any given data set. Although machine learning in bioinformatics is rapidly expanding, the need to combine spaceflight/GBF mission parameters with omics data is unique. This work characterizes the basic requirements for implementing the SoS approach through the System Map (SM) technique, a composite of a dynamic Bayesian network and Gaussian mixture model, in real-world repositories such as the GeneLab Data System and Life Sciences Data Archive. The three primary steps are metadata management for experimental description using open-source ontologies, defining similarity and consistency metrics, and generating testing and validation data sets. Such approaches to spaceflight and GBF omics data may soon enable unique insight into which measured phenomena correlate to biological mechanisms that are truly affected by spaceflight conditions; which are most likely to be confounded by other variables; and which are insufficiently characterized, significantly increasing existing and future science return from ISS and spaceflight missions.

Gentry, Diana↗

A Machine Learning Concept for DTN Routing

This paper discusses the concept and architecture of a machine learning based router for delay tolerant space networks. The techniques of reinforcement learning and Bayesian learning are used to supplement the routing decisions of the popular Contact Graph Routing algorithm. An introduction to the concepts of Contact Graph Routing, Q-routing and Naive Bayes classification are given. The development of an architecture for a cross-layer feedback framework for DTN (Delay-Tolerant Networking) protocols is discussed. Finally, initial simulation setup and results are given.

Delay Tolerant Networks↗

Supervised Learning Applied to Air Traffic Trajectory Classification

Given the recent increase of interest in introducing new vehicle types and missions into the National Airspace System, a transition towards a more autonomous air traffic control system is required in order to enable and handle increased density and complexity. This paper presents an exploratory effort of the needed autonomous capabilities by exploring supervised learning techniques in the context of aircraft trajectories. In particular, it focuses on the application of machine learning algorithms and neural network models to a runway recognition trajectory-classification study. It investigates the applicability and effectiveness of various classifiers using datasets containing trajectory records for a month of air traffic. A feature importance and sensitivity analysis are conducted to challenge the chosen time-based datasets and the ten selected features. The study demonstrates that classification accuracy levels of 90% and above can be reached in less than 40 seconds of training for most machine learning classifiers when one track data point, described by the ten selected features at a particular time step, per trajectory is used as input. It also shows that neural network models can achieve similar accuracy levels but at higher training time costs.

Bosson, Christabelle S.↗

Supervised Learning Applied to Air Traffic Trajectory Classification

Given the recent increase of interest in introducing new vehicle types and missions into the National Airspace System, a transition towards a more autonomous air traffic control system is required in order to enable and handle increased density and complexity. This paper presents an exploratory effort of the needed autonomous capabilities by exploring supervised learning techniques in the context of aircraft trajectories. In particular, it focuses on the application of machine learning algorithms and neural network models to a runway recognition trajectory-classification study. It investigates the applicability and effectiveness of various classifiers using datasets containing trajectory records for a month of air traffic. A feature importance and sensitivity analysis are conducted to challenge the chosen time-based datasets and the ten selected features. The study demonstrates that classification accuracy levels of 90% and above can be reached in less than 40 seconds of training for most machine learning classifiers when one track data point, described by the ten selected features at a particular time step, per trajectory is used as input. It also shows that neural network models can achieve similar accuracy levels but at higher training time costs.

Bosson, Christabelle↗

ISS Training Best Practices and Lessons Learned

Training our crew members for long-duration Deep Space Transport (DST) missions will have to be qualitatively and quantitatively different from current training practices. However, there is much to be learned from the extensive experience NASA has gained in training crew members for missions on board the International Space Station (ISS). Furthermore, the operational experience on board the ISS provides valuable feedback concerning training effectiveness. Keeping in mind the vast differences between current ISS crew training and training for DST missions, the needs of future crew members, and the demands of future missions, this ongoing study seeks to document current training practices and lessons learned. The goal of the study is to provide input to the design of future crew training that takes as much advantage as possible of what has already been learned and avoids as much as possible past inefficiencies. Results from this study will be presented upon its completion. By researching established training principles, examining future needs, and by using current practices in spaceflight training as test beds, this research project is mitigating program risks and generating templates and requirements to meet future training needs.

training↗

Quantum Machine Learning

Quantum computing promises an unprecedented ability to solve intractable problems by harnessing quantum mechanical effects such as tunneling, superposition, and entanglement. The Quantum Artificial Intelligence Laboratory (QuAIL) at NASA Ames Research Center is the space agency's primary facility for conducting research and development in quantum information sciences. QuAIL conducts fundamental research in quantum physics but also explores how best to exploit and apply this disruptive technology to enable NASA missions in aeronautics, Earth and space sciences, and space exploration. At the same time, machine learning has become a major focus in computer science and captured the imagination of the public as a panacea to myriad big data problems. In this talk, we will discuss how classical machine learning can take advantage of quantum computing to significantly improve its effectiveness. Although we illustrate this concept on a quantum annealer, other quantum platforms could be used as well. If explored fully and implemented efficiently, quantum machine learning could greatly accelerate a wide range of tasks leading to new technologies and discoveries that will significantly change the way we solve real-world problems.

Biswas, Rupak↗

Laser Tracker Utilization Methodology in Measuring Truth Trajectories for INS Testing on 6 Degree of Freedom Table at the Marshall Space Flight Center's Contact Dynamics Simulation Laboratory with Lessons Learned

When performing Inertial Navigation System (INS) testing at the Marshall Space Flight Center's (MSFC) Contact Dynamics Simulation Laboratory (CDSL) early in 2017, a Leica Geosystems AT901 Laser Tracker system (LLT) measured the twist & sway trajectories as generated by the 6 Degree Of Freedom (6DOF) Table in the CDSL. These LLT measured trajectories were used in the INS software model validation effort. Several challenges were identified and overcome during the preparation for the INS testing, as well as numerous lessons learned. These challenges included determining the position and attitude of the LLT with respect to an INS-shared coordinate frame using surveyed monument locations in the CDSL and the accompanying mathematical transformation, accurately measuring the spatial relationship between the INS and a 6DOF tracking probe due to lack of INS visibility from the LLT location, obtaining the data from the LLT during a test, determining how to process the results for comparison with INS data in time and frequency domains, and using a sensitivity analysis of the results to verify the quality of the results. While many of these challenges were identified and overcome before or during testing, a significant lesson on test set-up was not learned until later in the data analysis process. It was found that a combination of trajectory-dependent gimbal locking and environmental noise introduced non-negligible noise in the angular measurements of the LLT that spanned the evaluated frequency spectrum. The lessons learned in this experiment may be useful for others performing INS testing in similar testing facilities.

Leggett, Jared O.↗

Machine Learning Application to Atmospheric Chemistry Modeling

Atmospheric chemistry is a high-dimensionality, large-data problem and thus may be suited to machine-learning algorithms. We show here the potential of a random forest regression algorithm to replace the gas-phase chemistry solver in the GEOS-Chem chemistry model. In this proof-of-concept study, we used one month of model output to train random forest regression models to predict the concentrations of each long-lived chemical species after integration based upon the physical and chemical conditions before the chemical integration. The choice of prediction type has a strong impact on the skill of the regression model. We find best results from predicting the change in concentration for very long-lived species and the absolute concentration for shorter lived species. The skill of the machine learning algorithm is further improved by using a family approach for NO and NO2 rather than treating them independently.By replacing the numerical integrator with the random forest algorithm and running this model for one month, we find that the model is able to reproduce many of the features of the reference chemistry simulation. Replacing the integration methodology with a machine learning algorithm has the potential to be substantially faster. There are a wide range of applications for such an approach, e.g. to generate boundary conditions, for use in air quality forecasts or chemical data assimilation systems, etc.

Keller, Christoph A.↗

Generating Exploration Mission-3 Trajectories to a 9:2 NRHO using Machine Learning

The purpose of this thesis is to design a machine learning algorithm platform that provides expanded knowledge of mission availability through a launch season by improving trajectory resolution and introducing launch mission forecasting. The specific scenario addressed in this paper is one in which data is provided for four deterministic translational maneuvers through a mission to a Near Rectilinear Halo Orbit (NRHO) with a 9:2 synodic frequency. Current launch availability knowledge under NASA's Orion Orbit Performance Team is established by altering optimization variables associated to given reference launch epochs. This current method can bean abstract task and relies on an orbit analyst to structure a mission based on an established mission design methodology associated to the performance of Orion and NASA's Space Launch System. Introducing a machine learning algorithm trained to construct mission scenarios within the feasible range of known trajectories reduces the required interaction of the orbit analyst by removing the needed step of optimizing the orbit to fit an expected translational response required of the spacecraft. In this study, k-Nearest Neighbor and Bayesian Linear Regression successfully predicted classical orbital elements for the launch windows observed. However both algorithms had limitations due to their approaches to model fitting. Training machine learning algorithms off of classical orbital elements introduced a repetitive approach to reconstructing mission segments for different arrival opportunities through the launch window and can prove to be a viable method of launch window scan generation for future missions.

Guzman, Esteban↗

Atmospheric Chemistry Modeling Using Machine Learning

Atmospheric chemistry models are a central tool to study the impact of chemical constituents on the environment, vegetation and human health. These models split the atmosphere in a large number of grid-boxes and consider the emission of compounds into these boxes and their subsequent transport, deposition, and chemical processing. The chemistry is represented through a series of simultaneous ordinary differential equations, one for each compound. Given the difference in life-times between the chemical compounds (milli-seconds for O1D to years for CH4) these equations are numerically stiff and solving them consists of a significant fraction of the computational burden of a chemistry model. We have investigated a machine learning approach to emulate the chemistry instead of solving the differential equations numerically. From a one-month simulation of the GEOS-Chem model we have produced a training dataset consisting of the concentration of compounds before and after the differential equations are solved, together with some key physical parameters for every grid-box and time-step. From this dataset we have trained a machine learning algorithm (regression forest) to be able to predict the concentration of the compounds after the integration step based on the concentrations and physical state at the beginning of the time step. We have then included this algorithm back into the GEOS-Chem model, bypassing the need to integrate the chemistry. This machine learning approach shows many of the characteristics of the full simulation and has the potential to be substantially faster. There are a wide range of application for such an approach - generating boundary conditions, for use in air quality forecasts, chemical data assimilation systems, etc. We discuss speed and accuracy of our approach, and highlight some potential future directions for improving it.

Keller, Christoph A.↗

Machine Learning Application to Atmospheric Chemistry Modeling

Atmospheric chemistry models are a central tool to study the impact of chemical constituents on the environment, vegetation and human health. These models split the atmosphere in a large number of grid-boxes and consider the emission of compounds into these boxes and their subsequent transport, deposition, and chemical processing. The chemistry is represented through a series of simultaneous ordinary differential equations, one for each compound. Given the difference in life-times between the chemical compounds (milli-seconds for O (sup 1) D (Deuterium) to years for CH4) these equations are numerically stiff and solving them consists of a significant fraction of the computational burden of a chemistry model. We have investigated a machine learning approach to emulate the chemistry instead of solving the differential equations numerically. From a one-month simulation of the GEOS-Chem model we have produced a training dataset consisting of the concentration of compounds before and after the differential equations are solved, together with some key physical parameters for every grid-box and time-step. From this dataset we have trained a machine learning algorithm (regression forest) to be able to predict the concentration of the compounds after the integration step based on the concentrations and physical state at the beginning of the time step. We have then included this algorithm back into the GEOS-Chem model, bypassing the need to integrate the chemistry. This machine learning approach shows many of the characteristics of the full simulation and has the potential to be substantially faster. There are a wide range of application for such an approach - generating boundary conditions, for use in air quality forecasts, chemical data assimilation systems, etc. We discuss speed and accuracy of our approach, and highlight some potential future directions for improving it.

Keller, Christoph A.↗

Atmospheric Chemistry Modeling and Air Quality Forecasting Using Machine Learning

Atmospheric chemistry models are a central tool to study the impact of chemical constituents on the environment, vegetation and human health. These models split the atmosphere in a large number of grid-boxes and consider the emission of compounds into these boxes and their subsequent transport, deposition, and chemical processing. The chemistry is represented through a series of simultaneous ordinary differential equations, one for each compound. Given the difference in life-times between the chemical compounds (milli-seconds for O1D to years for CH4) these equations are numerically stiff and solving them consists of a significant fraction of the computational burden of a chemistry model.We have investigated a machine learning approach to emulate the chemistry instead of solving the differential equations numerically. From a one-month simulation of the GEOS-Chem model we have produced a training dataset consisting of the concentration of compounds before and after the differential equations are solved, together with some key physical parameters for every grid-box and time-step. From this dataset we have trained a machine learning algorithm (regression forest) to be able to predict the concentration of the compounds after the integration step based on the concentrations and physical state at the beginning of the time step. We have then included this algorithm back into the GEOS-Chem model, bypassing the need to integrate the chemistry.This machine learning approach shows many of the characteristics of the full simulation and has the potential to be substantially faster. There are a wide range of application for such an approach - generating boundary conditions, for use in air quality forecasts, chemical data assimilation systems, etc. We discuss speed and accuracy of our approach, and highlight some potential future directions for improving it.

Keller, Christoph A.↗

Reinforcement Learning Applied to Cognitive Space Communications

The future of space exploration depends on robust, reliable communication systems. As the number of such communication systems increase, automation is fast becoming a requirement to achieve this goal. A reinforcement learning solution can be employed as a possible automation method for such systems. The goal of this study is to build a reinforcement learning algorithm which optimizes data throughput of a single actor. A training environment was created to simulate a link within the NASA Space Communication and Navigation (SCaN) infrastructure, using state of the art simulation tools developed by the SCaN Center for Engineering, Networks, Integration, and Communications (SCENIC) laboratory at NASA Glenn Research Center to obtain the closest possible representation of the real operating environment. Reinforcement learning was then used to train an agent inside this environment to maximize data throughput. The simulation environment contained a single actor in low earth orbit capable of communicating with twenty-five ground stations that compose the Near-Earth Network (NEN). Initial experiments showed promising training results, so additional complexity was added by augmenting simulation data with link fading profiles obtained from real communication events with the International Space Station. A grid search was performed to find the optimal hyperparameters and model architecture for the agent. Using the results of the grid search, an agent was trained on the augmented training data. Testing shows that the agent performs well inside the training environment and can be used as a foundation for future studies with added complexity and eventually tested in the real space environment.

Schubert, Carson D.↗

Analyzing Machine Learning Predictions of Passive Microwave Brightness Temperature Spectral Difference Over Snow-Covered Terrain in High Mountain Asia

Snow is an important component of the terrestrial freshwater budget in high mountainAsia (HMA) and contributes to the runoff in Himalayan rivers through snowmelt. Despitethe importance of snow in HMA, considerable spatiotemporal uncertainty exists across the different estimates of snow water equivalent for this region. In order to better estimate snow water equivalent, radiative transfer models are often used in conjunction with microwave brightness temperature measurements. In this study, the efficacy of support vector machines (SVMs), a machine learning technique, to predict passive microwave brightness temperature spectral difference (1Tb) as a function of geophysical variables (snow water equivalent, snow depth, snow temperature, and snow density) is explored through a sensitivity analysis. The use of machine learning (as opposed to radiative transfer models) is a relatively new and novel approach for improving snow water equivalent estimates. The Noah-MP land surface model within the NASALand Information System framework is used to simulate the hydrologic cycle over HMA and model geophysical variables that are then used for SVM training. The SVMsserve as a nonlinear map between the geophysical space (modeled in Noah-MP) andthe observation space (1Tb as measured by the radiometer). Advanced MicrowaveScanning Radiometer-Earth Observing System measured passive microwave brightness temperatures over snow-covered locations in the HMA region are used as training data during the SVM training phase. Sensitivity of well-trained SVMs to each Noah-MP modeled state variable is assessed by computing normalized sensitivity coefficients. Sensitivity analysis results generally conform with the known first-order physics. Input states that increase volume scattering of microwave radiation, such as snow density and snow water equivalent, exhibit a plurality of positive normalized sensitivity coefficients. In general, snow temperature was the most sensitive input to the SVM predictions. The sensitivity of each state is location and time dependent. The signs of normalized sensitivity coefficients that indicate physical irrationality are ascribed to significant cross-correlation between Noah-MP simulated states and decreased SVM prediction capability at specific locations due to insufficient training data. SVM prediction pitfalls do exist that serve to highlight the limitations of this particular machine learning algorithm.

high mountain Asia↗