SEARCH · Search NASA
Results for “Learning algorithms”
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.
Machine Learning Based Algorithms for Global Dust Aerosol Detection from Satellite Images: Inter-Comparisons and Evaluation
Explore the source record for details and available documents.
Approximate Forest Completion and Learning-Augmented Algorithms for Metric Minimum Spanning Trees
Explore the source record for details and available documents.
Learning classification trees
Algorithms for learning classification trees have had successes in artificial intelligence and statistics over many years. How a tree learning algorithm can be derived from Bayesian decision theory is outlined. This introduces Bayesian techniques for splitting, smoothing, and tree averaging. The splitting rule turns out to be similar to Quinlan's information gain splitting rule, while smoothing and averaging replace pruning. Comparative experiments with reimplementations of a minimum encoding approach, Quinlan's C4 and Breiman et al. Cart show the full Bayesian algorithm is consistently as good, or more accurate than these other approaches though at a computational price.
Decision and Control of Complex Systems – A Data-Drive Framework
During the project period, we have collaborated with other team members and developed novel algorithms for novelty detection, continual learning, and graph learning algorithms for dynamic systems. The results are documented in publications and meeting notes. Moreover, we leverage virtual collaboration tools (such as Basecamp, Microsoft Teams and Zoom) for technical exchanges. Our research on novelty detection was published at AAAI 2022 and Lecture Notes in Artificial Intelligence, Springer Nature. The newly developed algorithms were successfully applied to realistic cases, including thermal data from buildings at Pacific Northwest National Lab and microelectronic data provided by GlobalFoundries. Multiple publications have been produced from this project, in collaboration with other team members. Three PhD students were supported in this project to conduct their research.
Deep Reinforcement Learning Based Control of Wind Turbines for Fast Frequency Response
In order to fulfill vital auxiliary grid services, such as load regulation, spin and non-spin reserve provision, and frequency support during emergencies, there is often a requirement for certain wind farms to operate in de-loaded modes. Leveraging the swift response capabilities of wind farms, this study demonstrates that reserving power in de-loaded modes can significantly enhance power grid stability and reliability during system contingencies. Controlling wind farms optimally for frequency support is intricate due to the nonlinearity of models and controllers and the complexity of wind farm interactions with power systems. Here, to address this challenge, this paper introduces a novel approach that integrates wind turbines into reinforcement learning-based solutions for frequency response. This innovative methodology utilizes the state-of-the-art reinforcement learning algorithm known as the surrogate-gradient-based evolutionary strategy. The proposed learning-based algorithm provides continuous control of wind farm output to rapidly stabilize system frequency and prevent unnecessary trips of under-frequency load shedding relays. To facilitate efficient training, parallel computing techniques are employed. The proposed methodology is evaluated on a modified IEEE-39 bus system, and simulation results reveal its efficacy in reliably supporting power system frequency and preventing the need for unnecessary load shedding.
Automatic Detection and Classification of Aurora in THEMIS All‐Sky Images
We report a novel machine-learning algorithm for automatically detecting and classifying aurora in all–sky images (ASI) that is largely trained without requiring ground–truth labels. By including a small number of labeled images, we are able to automatically label all of the approximately 700 million images in the Time History of Events and Macroscale Interactions during Substorms (THEMIS) ASI data set from 2008 to 2022. We use a two–stage approach. In the first stage, we adapt the Simple framework for Contrastive Learning of Representations (SimCLR) algorithm to learn latent representations of THEMIS all–sky images. We then finetune a classifier network on the latent representations our model learns of the manually labeled Oslo aurora THEMIS (OATH) data set. We demonstrate that this two–stage approach achieves excellent classification results on data for which there is no current ML classification benchmark. The outcome of this work will facilitate efficient information retrieval for researchers interested in specific categories of aurora and will enable large scale statistical studies and machine learning analyses of THEMIS all–sky images that have not previously been possible. To demonstrate possible ways to utilize this database, we performed a statistical analysis of the occurrence rates of auroral labels with respect to solar wind parameters, interplanetary magnetic field vector, and geomagnetic indices. We further investigate the occurrence rates of auroral phenomena in the annotated data set and their geoeffectiveness by utilizing the co–located THEMIS ground magnetometer data set.
The power of neural nets
Implementation of the Hopfield net which is used in the image processing type of applications where only partial information about the image may be available is discussed. The image classification type of algorithm of Hopfield and other learning algorithms, such as the Boltzmann machine and the back-propagation training algorithm, have many vital applications in space.
Learning Grasp Context Distinctions that Generalize
Control-based approaches to grasp synthesis create grasping behavior by sequencing and combining control primitives. In the absence of any other structure, these approaches must evaluate a large number of feasible control sequences as a function of object shape, object pose, and task. This work explores a new approach to grasp synthesis that limits consideration to variations on a generalized localize-reach-grasp control policy. A new learning algorithm, known as schema structured learning, is used to learn which instantiations of the generalized policy are most likely to lead to a successful grasp in different problem contexts. Two experiments are described where Dexter, a bimanual upper torso, learns to select an appropriate grasp strategy as a function of object eccentricity and orientation. In addition, it is shown that grasp skills learned in this way can generalize to new objects. Results are presented showing that after learning how to grasp a small, representative set of objects, the robot's performance quantitatively improves for similar objects that it has not experienced before.
Training Knowledge Bots for Physics-Based Simulations Using Artificial Neural Networks
Millions of complex physics-based simulations are required for design of an aerospace vehicle. These simulations are usually performed by highly trained and skilled analysts, who execute, monitor, and steer each simulation. Analysts rely heavily on their broad experience that may have taken 20-30 years to accumulate. In addition, the simulation software is complex in nature, requiring significant computational resources. Simulations of system of systems become even more complex and are beyond human capacity to effectively learn their behavior. IBM has developed machines that can learn and compete successfully with a chess grandmaster and most successful jeopardy contestants. These machines are capable of learning some complex problems much faster than humans can learn. In this paper, we propose using artificial neural network to train knowledge bots to identify the idiosyncrasies of simulation software and recognize patterns that can lead to successful simulations. We examine the use of knowledge bots for applications of computational fluid dynamics (CFD), trajectory analysis, commercial finite-element analysis software, and slosh propellant dynamics. We will show that machine learning algorithms can be used to learn the idiosyncrasies of computational simulations and identify regions of instability without including any additional information about their mathematical form or applied discretization approaches.
Empirical Analysis and Automated Classification of Security Bug Reports
With the ever expanding amount of sensitive data being placed into computer systems, the need for effective cybersecurity is of utmost importance. However, there is a shortage of detailed empirical studies of security vulnerabilities from which cybersecurity metrics and best practices could be determined. This thesis has two main research goals: (1) to explore the distribution and characteristics of security vulnerabilities based on the information provided in bug tracking systems and (2) to develop data analytics approaches for automatic classification of bug reports as security or non-security related. This work is based on using three NASA datasets as case studies. The empirical analysis showed that the majority of software vulnerabilities belong only to a small number of types. Addressing these types of vulnerabilities will consequently lead to cost efficient improvement of software security. Since this analysis requires labeling of each bug report in the bug tracking system, we explored using machine learning to automate the classification of each bug report as a security or non-security related (two-class classification), as well as each security related bug report as specific security type (multiclass classification). In addition to using supervised machine learning algorithms, a novel unsupervised machine learning approach is proposed. An ac- curacy of 92%, recall of 96%, precision of 92%, probability of false alarm of 4%, F-Score of 81% and G-Score of 90% were the best results achieved during two-class classification. Furthermore, an accuracy of 80%, recall of 80%, precision of 94%, and F-score of 85% were the best results achieved during multiclass classification.
Reinforcement Learning for Weakly-Coupled MDPs and an Application to Planetary Rover Control
Weakly-coupled Markov decision processes can be decomposed into subprocesses that interact only through a small set of bottleneck states. We study a hierarchical reinforcement learning algorithm designed to take advantage of this particular type of decomposability. To test our algorithm, we use a decision-making problem faced by autonomous planetary rovers. In this problem, a Mars rover must decide which activities to perform and when to traverse between science sites in order to make the best use of its limited resources. In our experiments, the hierarchical algorithm performs better than Q-learning in the early stages of learning, but unlike Q-learning it converges to a suboptimal policy. This suggests that it may be advantageous to use the hierarchical algorithm when training time is limited.
Virtual to Physical: Reinforcement Learning to Optimize SNS Particle Accelerator Controls
Complex accelerators must have control systems that can handle dynamic nonlinear environments. This makes traditional control methods unsuitable as they can struggle to adapt to these uncertainties. This provides an ideal environment for reinforcement learning algorithms as they are adaptable and generalizable. We present a reinforcement learning pipeline that can effectively handle the dynamics of a complex accelerator. We test and prove our pipelines capabilities on multiple environments including the Spallation Neutron Source (SNS) and the Beam Test Facility (BTF) at Oakridge National Lab (ORNL). Due to the limited time available to train an online algorithm like reinforcement learning on a real accelerator, we utilize a virtual twin accelerator (VIRAC) developed by ORNL to pretrain the policy and show its ability to converge in the virtual environment. We then test the adaptability of the pretrained RL model by applying it on the real accelerator and comparing the results. Utilizing our Scientific Optimization and Controls Toolkit (SOCT) and open-source standards such as Gymnasium we create and solve for a MEBT orbit correction problem in the SNS and an emittance maximization problem in the BTF. We show how Twin Delayed Deep Deterministic Policy Gradient (TD3) can solve this optimization environment in the virtual accelerator and transfer this policy onto the real accelerator for inference and model retraining. We show how reinforcement learning can be utilized as a control system for complex accelerators and provide a model pipeline for how an implementation performs and can be adapted to new accelerator control problems.
Future applications of artificial intelligence to Mission Control Centers
Future applications of artificial intelligence to Mission Control Centers are presented in the form of the viewgraphs. The following subject areas are covered: basic objectives of the NASA-wide AI program; inhouse research program; constraint-based scheduling; learning and performance improvement for scheduling; GEMPLAN multi-agent planner; planning, scheduling, and control; Bayesian learning; efficient learning algorithms; ICARUS (an integrated architecture for learning); design knowledge acquisition and retention; computer-integrated documentation; and some speculation on future applications.
Induction as Knowledge Integration
Two key issues for induction algorithms are the accuracy of the learned hypothesis and the computational resources consumed in inducing that hypothesis. One of the most promising ways to improve performance along both dimensions is to make use of additional knowledge. Multi-strategy learning algorithms tackle this problem by employing several strategies for handling different kinds of knowledge in different ways. However, integrating knowledge into an induction algorithm can be difficult when the new knowledge differs significantly from the knowledge the algorithm already uses. In many cases the algorithm must be rewritten. This paper presents Knowledge Integration framework for Induction (KII), a KII, that provides a uniform mechanism for integrating knowledge into induction. In theory, arbitrary knowledge can be integrated with this mechanism, but in practice the knowledge representation language determines both the knowledge that can be integrated, and the costs of integration and induction. By instantiating KII with various set representations, algorithms can be generated at different trade-off points along these dimensions. One instantiation of KII, called RS-KII, is presented that can implement hybrid induction algorithms, depending on which knowledge it utilizes. RS-KII is demonstrated to implement AQ-11, as well as a hybrid algorithm that utilizes a domain theory and noisy examples. Other algorithms are also possible.
Using Machine Learning to Predict Core Sizes of High-Efficiency Turbofan Engines
With the rise in big data and analytics, machine learning is transforming many industries. It is being increasingly employed to solve a wide range of complex problems, producing autonomous systems that support human decision-making. For the aircraft engine industry, machine learning of historical and existing engine data could provide insights that help drive for better engine design. This work explored the application of machine learning to engine preliminary design. Engine core-size prediction was chosen for the first study because of its relative simplicity in terms of number of input variables required (only three). Specifically, machine-learning predictive tools were developed for turbofan engine core-size prediction, using publicly available data of two hundred manufactured engines and engines that were studied previously in NASA aeronautics projects. The prediction results of these models show that, by bringing together big data, robust machine-learning algorithms and automation, a machine learning-based predictive model can be an effective tool for turbofan engine core-size prediction. The promising results of this first study paves the way for further exploration of the use of machine learning for aircraft engine preliminary design.
Evaluation of Classifier Complexity for Delay Tolerant Network Routing
The growing popularity of small cost effective satellites (SmallSats, CubeSats, etc.) creates the potential for a variety of new science applications involving multiple nodes functioning together or independently to achieve a task, such as swarms and constellations. As this technology develops and is deployed for missions in Low Earth Orbit and beyond, the use of delay tolerant networking (DTN) techniques may improve communication capabilities within the network. In this paper, a network hierarchy is developed from heterogeneous networks of SmallSats, surface vehicles, relay satellites and ground stations which form an integrated network. There is a tradeoff between complexity, flexibility, and scalability of user defined schedules versus autonomous routing as the number of nodes in the network increases. To address these issues, this work proposes a machine learning classifier based on DTN routing metrics. A framework is developed which will allow for the use of several categories of machine learning algorithms (decision tree, random forest and deep learning) to be applied to a dataset of historical network statistics, which allows for the evaluation of algorithm complexity versus performance to be explored. We develop the emulation of a hierarchical network, consisting of tens of nodes which form a cognitive network architecture. CORE (Common Open Research Emulator) is used to emulate the network using bundle protocol and DTN IP neighbor discovery.
Multi-Objective Reinforcement Learning-based Deep Neural Networks for Cognitive Space Communications
Future communication subsystems of space exploration missions can potentially benefit from software-defined radios (SDRs) controlled by machine learning algorithms. In this paper, we propose a novel hybrid radio resource allocation management control algorithm that integrates multi-objective reinforcement learning and deep artificial neural networks. The objective is to efficiently manage communications system resources by monitoring performance functions with common dependent variables that result in conflicting goals. The uncertainty in the performance of thousands of different possible combinations of radio parameters makes the trade-off between exploration and exploitation in reinforcement learning (RL) much more challenging for future critical space-based missions. Thus, the system should spend as little time as possible on exploring actions, and whenever it explores an action, it should perform at acceptable levels most of the time. The proposed approach enables on-line learning by interactions with the environment and restricts poor resource allocation performance through virtual environment exploration. Improvements in the multiobjective performance can be achieved via transmitter parameter adaptation on a packet-basis, with poorly predicted performance promptly resulting in rejected decisions. Simulations presented in this work considered the DVB-S2 standard adaptive transmitter parameters and additional ones expected to be present in future adaptive radio systems. Performance results are provided by analysis of the proposed hybrid algorithm when operating across a satellite communication channel from Earth to GEO orbit during clear sky conditions. The proposed approach constitutes part of the core cognitive engine proof-of-concept to be delivered to the NASA Glenn Research Center SCaN Testbed located onboard the International Space Station.