SEARCH · Search NASA

Results for “Active 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.

SourceResearch connectionFrom yearThrough year

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

At least 775 records · Page 43

All sources NASA NTRS DOE OSTI

DOE OSTI2024

Physics-Guided Continual Learning for Predicting Emerging Aqueous Organic Redox Flow Battery Material Performance

Aqueous organic redox flow batteries (AORFBs) have gained popularity in renewable energy storage due to their low cost, environmental friendliness and scalability. The rapid discovery of aqueous soluble organic (ASO) redox-active materials necessitates efficient machine learning surrogates for predicting battery performance. The physics-guided continual learning (PGCL) method proposed in this study can incrementally learn data from new ASO electrolytes while addressing catastrophic forgetting issues in conventional machine learning. Using a AORFB database with a thousand potential materials generated by a 780 $\text{cm}^2$ interdigitated cell model, PGCL incorporates AORFB physics to optimize the continual learning task formation and training strategies to retain previously learned battery material knowledge. Finally, the trained PGCL demonstrates its capability in assessing emerging ASO materials within the established parameter space when evaluated with the dihydroxyphenazine isomers.

25 ENERGY STORAGE↗

DOE OSTI2020

Lessons Learned from More than Three Decades of Decommissioning and RAW Management in Slovakia - 20074

The purpose of this paper is to describe utilization of experience of JAVYS Company acquired while acting as the Slovak national decommissioning and radioactive waste management entity. JAVYS manages both the decommissioning of A1 NPP (shut down after series of accidents) and V1 NPP (shut down after standard operation) and related radioactive waste management. Besides JAVYS is responsible for management of institutional radioactive waste in Slovakia. The paper is focusing on selected successfully completed projects and related lessons learned from development of special procedures and implementation of activities within decommissioning and management of generated waste streams from cradle to grave. Recently, experience and lessons learned from all aforementioned activities are used internationally to provide assistance to other countries in order to overcome difficulties and to successfully implement various projects dealing with decommissioning and radioactive waste management. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

DOE OSTI2014

The North American Carbon Program Multi-scale Synthesis and Terrestrial Model Intercomparison Project – Part 2: Environmental driver data

Ecosystems are important and dynamic components of the global carbon cycle, and terrestrial biospheric models (TBMs) are crucial tools in further understanding of how terrestrial carbon is stored and exchanged with the atmosphere across a variety of spatial and temporal scales. Improving TBM skills, and quantifying and reducing their estimation uncertainties, pose significant challenges. The Multi-scale Synthesis and Terrestrial Model Intercomparison Project (MsTMIP) is a formal multi-scale and multi-model intercomparison effort set up to tackle these challenges. The MsTMIP protocol prescribes standardized environmental driver data that are shared among model teams to facilitate model model and model observation comparisons. In this article, we describe the global and North American environmental driver data sets prepared for the MsTMIP activity to both support their use in MsTMIP and make these data, along with the processes used in selecting/processing these data, accessible to a broader audience. Based on project needs and lessons learned from past model intercomparison activities, we compiled climate, atmospheric CO 2 concentrations, nitrogen deposition, land use and land cover change (LULCC), C3 / C4 grasses fractions, major crops, phenology and soil data into a standard format for global (0.5⁰ x 0.5⁰ resolution) and regional (North American: 0.25⁰ x 0.25⁰ resolution) simulations. In order to meet the needs of MsTMIP, improvements were made to several of the original environmental data sets, by improving the quality, and/or changing their spatial and temporal coverage, and resolution. The resulting standardized model driver data sets are being used by over 20 different models participating in MsTMIP. Lastly, the data are archived at the Oak Ridge National Laboratory Distributed Active Archive Center (ORNL DAAC, http://daac.ornl.gov) to provide long-term data management and distribution.

54 ENVIRONMENTAL SCIENCES↗

NASA NTRS2008

Using SecondLife Online Virtual World Technology to Introduce Educators to the Digital Culture

The rapidly changing culture resulting from new technologies and digital gaming has created an increasing language gap between traditional educators and today's learners (Natkin, 2006; Seely-Brown, 2000). This study seeks to use the online virtual world of SecondLife.com as a tool to introduce educators to this new environment for learning. This study observes the activities and perceptions of a group of educators given unscripted access to this virtual environment. The results 'suggest that although serious technology limitations do currently exist, the potential of this virtual world environment as a learning experience for educators is strong.

Jamison, John↗

NASA NTRSDate not supplied

Idea Evolution ... What's Next?

No research project lasts forever. Even the most wildly successful programs will eventually come to an end. The challenge in that moment, when a project ends, is how to take what was learned in that project and apply it to the next research activity you undertake. Although not always possible, information and insights from a project that is underway or coming to a close can be leveraged to identify a new research direction and advance existing tangentially related activities. In this presentation, a common thread will be followed through a series of sequential research projects where lessons learned in each activity were built into the next enabling each new research project to advance further and faster. Initial research focused on lunar dust adhesion mitigation coalesced into two major contributors to adhesion interactions; which were, not surprisingly, surface chemistry and topography. This knowledge was applied to addressing insect residue adhesion mitigation on commercial aircraft leading edge surfaces. Composite epoxy coatings formulated with controlled surface chemistry and topography were evaluated and led to identification of additional relevant considerations: dynamics and surface morphology. Collectively, these considerations were applied to address impact ice adhesion mitigation where further properties were elucidated: surface mechanical properties and durability. Seeking commonality between these research endeavors led to greater understanding of each new research objective and ultimately, identification of robust, viable pathways toward meaningful results.

Adhesion Mitigation↗

DOE OSTI2016

A general-purpose machine learning framework for predicting properties of inorganic materials

A very active area of materials research is to devise methods that use machine learning to automatically extract predictive models from existing materials data. While prior examples have demonstrated successful models for some applications, many more applications exist where machine learning can make a strong impact. To enable faster development of machine-learning-based models for such applications, we have created a framework capable of being applied to a broad range of materials data. Our method works by using a chemically diverse list of attributes, which we demonstrate are suitable for describing a wide variety of properties, and a novel method for partitioning the data set into groups of similar materials to boost the predictive accuracy. In this manuscript, we demonstrate how this new method can be used to predict diverse properties of crystalline and amorphous materials, such as band gap energy and glass-forming ability.

36 MATERIALS SCIENCE↗

NASA NTRS2004

Education Outreach Associated with Technology Transfer in a Colonia of South Texas: Green Valley Farms Science and Space Club for Middle School Aged Children in Green Valley Farms, San Benito, Texas

Texas colonias are unincorporated subdivisions characterized by inadequate water and wastewater infrastructure, inadequate drainage and road infrastructure, substandard housing, and poverty. Since 1989 the Texas Legislature has implemented policies to halt further development of colonias and to address water and wastewater infrastructure needs in existing and new colonias along the border with Mexico. Government programs and non-government and private organization projects aim to address these infrastructure needs. Texas Tech University's Water Resources Center demonstrated the use of alternative on-site wastewater treatment in the Green Valley Farms colonia, San Benito, Texas. The work in Green Valley Farms was a component of a NASA-funded project entitled Evaluation of NASA's Advanced Life Support Integrated Water Recovery System for Non-Optimal Conditions and Terrestrial Applications. Two households within the colonia are demonstration sites for constructed wetlands. A colonia resident and activist identified educational opportunities for colonia children as a primary goal for many colonia residents. Colonia parents view education as the door to opportunity and escape from poverty for their children. The educational outreach component of the project in Green Valley Farms was a Science and Space Club for middle-school age students. Involved parents, schoolteachers, and school administrators enthusiastically supported the monthly club meetings and activities. Each month, students participated in interactive learning experiences about water use and reuse in space and on earth. Activities increased knowledge and interest in water resource issues and in science and engineering fields. The Institute for the Development and Enrichment of Advanced Learners (IDEAL) at Texas Tech University provided full scholarships for five students from Green Valley Farms to attend the Shake Hands With Your Future camp at Texas Tech University in June 2003. The educational outreach component was evaluated in February 2004 using survey instruments for students and parents, and interviews with science teachers and counselors.

Potess, Marla D.↗

DOE OSTI2023

A comparison of machine learning methods to classify radioactive elements using prompt-gamma-ray neutron activation data

The detection of illicit radiological materials is critical to establishing a robust second line of defence in nuclear security. Neutron-capture prompt-gamma activation analysis (PGAA) can be used to detect multiple radioactive materials across the entire Periodic Table. However, long detection times and a high rate of false positives pose a significant hindrance in the deployment of PGAA-based systems to identify the presence of illicit substances in nuclear forensics. In the present work, six different machine-learning algorithms were developed to classify radioactive elements based on the PGAA energy spectra. The model performance was evaluated using standard classification metrics and trend curves with an emphasis on comparing the effectiveness of algorithms that are best suited for classifying imbalanced datasets. We analyse the classification performance based on Precision, Recall, F1-score, Specificity, Confusion matrix, ROC-AUC curves, and Geometric Mean Score (GMS) measures. The tree-based algorithms (Decision Trees, Random Forest and AdaBoost) have consistently outperformed Support Vector Machine and K-Nearest Neighbours. Based on the results presented, AdaBoost is the preferred classifier to analyse data containing PGAA spectral information due to the high recall and minimal false negatives reported in the minority class.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2021

Deep Reinforcement Learning Enabled Physical-Model-Free Two-Timescale Voltage Control Method for Active Distribution Systems

Active distribution networks are being challenged by frequent and rapid voltage violations due to renewable energy integration. Conventional model-based voltage control methods rely on accurate parameters of the distribution networks, which are difficult to achieve in practice. This paper proposes a novel physical-model-free two-timescale voltage control framework for active distribution systems. To achieve fast control of PV inverters, the whole network is first partitioned into several subnetworks using voltage-reactive power sensitivity. Then, the scheduling of PV inverters in the multiple sub-networks is formulated as Markov games and solved by a multi-agent soft actor-critic (MASAC) algorithm, where each subnetwork is modeled as an intelligent agent. All agents are trained in a centralized manner to learn a coordinated strategy while being executed based on only local information for fast response. For the slower time-scale control, OLTCs and switched capacitors are coordinated by a single agent-based SAC algorithm using the global information with considering control behaviors of the inverters. Particularly, the two-level agents are trained concurrently with information exchange according to the reward signal calculated from the data-driven surrogate model. Comparative tests with different benchmark methods on IEEE 33-and 123-bus systems and 342-node low voltage distribution system demonstrate that the proposed method can effectively mitigate the fast voltage violations and achieve systematical coordination of different voltage regulation assets without the knowledge of accurate system model.

24 POWER TRANSMISSION AND DISTRIBUTION↗

NASA NTRS1999

Aerospace Engineering Systems and the Advanced Design Technologies Testbed Experience

Continuous improvement of aerospace product development processes is a driving requirement across much of the aerospace community. As up to 90% of the cost of an aerospace product is committed during the first 10% of the development cycle, there is a strong emphasis on capturing, creating, and communicating better information (both requirements and performance) early in the product development process. The community has responded by pursuing the development of computer-based systems designed to enhance the decision-making capabilities of product development individuals and teams. Recently, the historical foci on sharing the geometrical representation and on configuration management are being augmented: 1) Physics-based analysis tools for filling the design space database; 2) Distributed computational resources to reduce response time and cost; 3) Web-based technologies to relieve machine-dependence; and 4) Artificial intelligence technologies to accelerate processes and reduce process variability. The Advanced Design Technologies Testbed (ADTT) activity at NASA Ames Research Center was initiated to study the strengths and weaknesses of the technologies supporting each of these trends, as well as the overall impact of the combination of these trends on a product development event. Lessons learned and recommendations for future activities are reported.

VanDalsem, William R.↗

NASA NTRS2020

Kibo Robot Programming Challenge Final Activity Report

On October 8th, 2020 the Kibo Robot Programming Challenge (RPC) Finals Event took place. Student teams from Australia, Indonesia, Japan, Singapore, Taiwan, Thailand, and UAE were the finalists of the competition and became the first students to ever upload APKs to an Astrobee robot (Bumble) on the ISS. This was the culmination of a joint effort between JAXA’s Int-Ball developing team in Tsukuba, Japan and NASA’s Astrobee Facility team at NASA Ames Research Center\ in California, USA. The collaboration between JAXA and NASA started in late 2017. Throughout this time mutual visits by the engineering and management teams were organized. In July 2019 the Kibo RPC concept was formally defined and the competition started. Hundreds of students across the Asia Pacific region participated and during the final event they did so in real time with the participation of NASA’s astronaut, Chris Cassidy. Chris interacted with the students, JAXA personnel and with the robot during the activity. This report aims to summarize the lessons learned from the several crew and non-crew tended activities, the evaluations performed on ground, the coordination of resources both in the ground and at the International Space Station (ISS) as well as operations. It identifies the issues the teams faced and the solutions put in place to mitigate them.

Astrobee↗

NASA NTRS2022

Thinking Inside the Box: A Hands-on Student Activity for Building a Contamination Containment Glovebox to Encourage Problem Solving in a Collaborative Environment

Engineers from the National Aeronautics and Space Administration (NASA) and education experts from the Virginia Space Grant Consortium (VSGC) partnered together to create a hands-on student activity to teach students about problem solving, working in a collaborative environment, and about the unique career fields of contamination control and planetary protection. The activity focuses on contamination containment gloveboxes, which are sealed containers where operators outside the glovebox can safely manipulate hazardous or contamination-sensitive materials inside the glovebox through glove ports on the container. The activity utilizes common household materials and teams of students work together to design and build a glovebox using the materials provided. Once the glovebox has been constructed, students perform a task under a time constraint by using their glovebox to assemble a puzzle “contaminated” with corn starch. In a post-activity debrief, teams discuss lessons learned such as how the actual built glovebox differed from the sketched design, the challenge of managing a budget for materials, how the team dealt with surprises, and if their glovebox allowed enough room for the operator to perform the task. This activity has been part of VSGC’s Virginia Earth System Science Scholars (VESSS) summer academy program for high school students since 2016, and has been an engaging method to teach students teamwork, creativity, hands-on experimentation, communication, and reasoning skills while also teaching them about unique engineering fields such as contamination control and planetary protection.

Student activity↗

NASA NTRSDate not supplied

Thinking Inside the Box: A Hands-On Student Activity for Building a Contamination Containment Glovebox to Encourage Problem Solving in a Collaborative Environment

Contamination containment gloveboxes are sealed containers where operators outside the glovebox can safely manipulate hazardous or contamination-sensitive materials inside the glovebox through glove ports on the container. Containment gloveboxes are used in the space industry to study sample materials returned from space such as lunar, asteroid, and comet materials, to manufacture sensitive instruments and space ight hardware, and to perform contamination-sensitive experiments. A hands-on activity has been developed by contamination control engineer and STEM education experts as part of the Virginia Earth System Science Scholars (VESSS) summer academy program to teach high school students about gloveboxes and about problem solving in a collaborative environment. In this activity, student teams are given a list of common household materials (e.g. plastic bags, plastic straws, aluminum foil, tape, disposable gloves, etc.) for building their own glovebox. Students work together to sketch and design their glovebox before being provided a kit of materials, which they must purchase along with any extra materials with a mock team budget. They are given 30 minutes to build their glovebox, however, they do not know what will be placed inside the glovebox or what operations they will need to perform within the glovebox. At the end of the build time, teams are given a small, sealed paper envelope which they place in the glovebox. Each team selects a team member to be designated as the operator, and the operator places their hands in the gloves of the glovebox. The operator uses their gloves to open the envelope in the glovebox, and they discover they have 20 minutes to assemble a jigsaw puzzle. However, the puzzle is \contaminated" with talcum powder. After the 20 minute time period, teams are judged on how well they completed and cleaned the contaminated puzzle. In a post-activity debrief, teams discuss lessons learned such as how the actual built box di ered from the sketched design, the challenge of managing a budget for materials, how the team dealt with surprises, and if their glovebox allowed enough room for the operator to perform the task. This activity has been part of the VESSS summer academy since 2016, and teaches students teamwork, creativity, hands-on experimentation, communication, and reasoning skills. In a demonstration at IAC, a volunteer from the audience will be chosen to assemble a glovebox during the presentation using the same kit of materials and will demonstrate handling puzzle pieces in the completed glovebox.

Elaine Seasly↗

NASA NTRS1997

Multiple subclasses of Purkinje cells in the primate floccular complex provide similar signals to guide learning in the vestibulo-ocular reflex

The neural "learning rules" governing the induction of plasticity in the cerebellum were analyzed by recording the patterns of neural activity in awake, behaving animals during stimuli that induce a form of cerebellum-dependent learning. We recorded the simple- and complex-spike responses of a broad sample of Purkinje cells in the floccular complex during a number of stimulus conditions that induce motor learning in the vestibulo-ocular reflex (VOR). Each subclass of Purkinje cells carried essentially the same information about required changes in the gain of the VOR. The correlation of simple-spike activity in Purkinje cells with activity in vestibular pathways could guide learning during low-frequency but not high-frequency stimuli. Climbing fiber activity could guide learning during all stimuli tested but only if compared with the activity present approximately 100 msec earlier in either vestibular pathways or Purkinje cells.

Non-NASA Center↗

NASA NTRS1999

Aerospace Engineering Systems

Continuous improvement of aerospace product development processes is a driving requirement across much of the aerospace community. As up to 90% of the cost of an aerospace product is committed during the first 10% of the development cycle, there is a strong emphasis on capturing, creating, and communicating better information (both requirements and performance) early in the product development process. The community has responded by pursuing the development of computer-based systems designed to enhance the decision-making capabilities of product development individuals and teams. Recently, the historical foci on sharing the geometrical representation and on configuration management are being augmented: Physics-based analysis tools for filling the design space database; Distributed computational resources to reduce response time and cost; Web-based technologies to relieve machine-dependence; and Artificial intelligence technologies to accelerate processes and reduce process variability. Activities such as the Advanced Design Technologies Testbed (ADTT) project at NASA Ames Research Center study the strengths and weaknesses of the technologies supporting each of these trends, as well as the overall impact of the combination of these trends on a product development event. Lessons learned and recommendations for future activities will be reported.

VanDalsem, William R.↗

DOE OSTI2026

Hierarchical semi-Markov models with duration-aware dynamics for activity sequences

Residential electricity demand at granular scales is driven by what people do and for how long. Accurately forecasting this demand for applications like microgrid management and demand response therefore requires generative models for activities that can produce realistic daily activity sequences, capturing both the timing and duration of human behavior. This paper develops a generative model of human activity sequences using nationally representative time-use diaries at a 10-min resolution. We use this model to quantify which demographic factors are most critical for improving predictive performance. We propose a hierarchical semi-Markov framework that addresses two key modeling challenges. First, a time-inhomogeneous Markov router learns the patterns of “which activity comes next.” Second, a semi-Markov hazard component explicitly models activity durations, capturing “how long” activities realistically last. To ensure statistical stability when data are sparse, the model pools information across related demographic groups and time blocks. The entire framework is trained and evaluated using survey design weights to ensure our findings are representative of the U.S. population. On a held-out test set, we demonstrate that explicitly modeling durations with the hazard component provides a substantial and statistically significant improvement over purely Markovian models. Furthermore, our analysis reveals a clear hierarchy of demographic factors: Sex, Day-Type, and Household Size provide the largest predictive gains, while Region and Season, though important for energy calculations, contribute little to predicting the activity sequence itself. The result is an interpretable and robust generator of synthetic activity traces, providing a high-fidelity foundation for downstream energy systems modeling.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2024

Lessons Learned from the Clean Energy to Communities (C2C) Peer-Learning Cohort on Planning and Funding for Electric Vehicle Charging Infrastructure Deployment

From June to December 2023, the U.S. Department of Energy (DOE) National Renewable Energy Laboratory (NREL) partnered with World Resources Institute (WRI) to run a peer-learning cohort for local governments on Planning and Funding for Electric Vehicle Charging Infrastructure Deployment. This cohort effort, funded by DOE's Clean Energy to Communities Program, paired 15 local and regional governments with Clean Cities and Communities coalitions to translate cohort learnings to local context and conduct activities that brought participants closer developing of public electric vehicle charging infrastructure plans. This document shares key takeaways, lessons learned, and resources from the six-month cohort.

ADVANCED PROPULSION SYSTEMS↗

DOE OSTI2022

General-Purpose Unsupervised Cyber Anomaly Detection via Non-Negative Tensor Factorization

Distinguishing malicious anomalous activities from unusual but benign activities is a fundamental challenge for cyber defenders. Prior studies have shown that statistical user behavior analysis yields accurate detections by learning behavior profiles from observed user activity. These unsupervised models are able to generalize to unseen types of attacks by detecting deviations from normal behavior, without knowledge of specific attack signatures. However, approaches proposed to date based on probabilistic matrix factorization are limited by the information conveyed in a two-dimensional space. Non-negative tensor factorization, on the other hand, is a powerful unsupervised machine learning method that naturally models multi-dimensional data, capturing complex and multi-faceted details of behavior profiles. Herein, our new unsupervised statistical anomaly detection methodology matches or surpasses state-of-the-art supervised learning baselines across several challenging and diverse cyber application areas, including detection of compromised user credentials, botnets, spam e-mails, and fraudulent credit card transactions.

97 MATHEMATICS AND COMPUTING↗