Search NASA⌕ Search

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.

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

At least 1,369 records · Page 76

MO-E-213-03: Newer Radiation Protection Requirements in Last Decade

The focus of work of medical physicists in 1980’s was on quality control and quality assurance. Radiation safety was important but was dominated by occupational radiation protection. A series of over exposures of patients in radiotherapy, nuclear medicine and observation of skin injuries among patients undergoing interventional procedures in 1990’s started creating the need for focus on patient protection. It gave medical physicists new directions to develop expertise in patient dosimetry and dose management. Publications creating awareness on cancer risks from CT in early part of the current century and over exposures in CT in 2008 brought radiation risks in public domain and created challenging situations for medical physicists. Increasing multiple exposures of individual patient and patient doses of few tens of mSv or exceeding 100 mSv are increasing the role of medical physicists. Expansion of usage of fluoroscopy in the hands of clinical professionals with hardly any training in radiation protection shall require further role for medical physicists. The increasing publications in journals, recent changes in Safety Standards, California law, all increase responsibilities of medical physicists in patient protection. Newer technological developments in dose efficiency and protective devices increase percentage of time devoted by medical physicists on radiation protection activities. Without radiation protection, the roles, responsibilities and day-to-day involvement of medical physicists in diagnostic radiology becomes questionable. In coming years either medical radiation protection may emerge as a specialty or medical physicists will have to keep major part of day-to-day work on radiation protection. Learning Objectives: To understand how radiation protection has been increasing its role in day-to-day activities of medical physicist To be aware about international safety Standards, national and State regulations that require higher attention to radiation protection than in past To be aware about possible emergence of medical radiation protection as a specialty and challenges for medical physicists.

60 APPLIED LIFE SCIENCES↗

Using Machine-Learning Methods and Expert Prediction Probabilities to Forecast Solar Flares

It has long been known that studying connection between solar flares and properties of magnetic field in active regions is very important for understanding the flare physics and developing space weather forecasts. The Helioseismic and Magnetic Imager onboard the Solar Dynamics Observatory (SDO/HMI) obtains tremendous amounts of magnetic field data products. However the operational NOAA Space Weather Prediction Center (SWPC) forecasts of solar flares still represent prediction probabilities issued by the experts. In this research we investigate the possibilities to enhance the daily operational flare forecasts performed at the SWPC by developing a synergy of the expert predictions and physics-based criteria, and by employing machine-learning methods. Among the physics-based criteria we consider the descriptors of the Polarity Inversion Line (PIL) and Space weather HMI Active Region Patches (SHARP), and derive from them daily characteristics of the entire Sun. We also consider the daily descriptors of the GOES Soft X-Ray (SXR) 1-8 Angstroms flux such as the flare history of the previous days and averaged X-Ray flux. We estimate the effectiveness in separation of flaring and non-flaring cases for each characteristic, as well as for the expert prediction probabilities, and find that some PIL, SHARP and SXR descriptors are as effective as the expert prediction probabilities and should be considered to issue the flare forecast. Finally, we train and test several Machine-Learning classification algorithms (Support Vector Classifiers with various kernel functions, k-Nearest Neighbor Classifier, Random Forest Classifier, and Neural Networks) using the most effective descriptors and expert prediction probabilities, and compare the obtained predictions with the current SWPC forecasts.

Machine-Learning↗

Leveraging High-throughput Computation and Machine Learning to Discover and Understand Low-Temperature Fast Oxygen Conductors (Final Technical Report)

The major goals of this work are twofold: (1) to enable transformative basic understanding of structure-property-performance relationships governing oxygen transport in oxygen-active materials and (2) facilitate the discovery and rational design of new oxygen-active materials which transport oxygen efficiently at low temperature. Transformative understanding and materials design will be accomplished by synergistically combining materials data mining, machine learning, high-throughput computation and targeted experiments.

36 MATERIALS SCIENCE↗

Machine-Learned Structure-Property Relationship in Metallic Glasses (Final Report)

The goal of the proposed work was to gain the ability to predict properties from the known coordinates (relative positions) of atoms in a metallic glass, presuming that information about which regions of the glass are fertile for rearrangment (defects) are encoded in this structural information. This goal is important to the science of metallic glasses. This research of applied machine learning methods to automate the development of a relationship between structural measures and thermally and stress-activated events in the metallic glass. In this way, the work aimed to building a bridge between structure and properties for this class of materials. The work is expected to have timely impact on guiding the tuning of internal structures of metallic glasses for desired properties. It also represents an advance in applying machine learning techniques to discerning the properties of materials.

36 MATERIALS SCIENCE↗

Deep Reinforcement Learning for Distribution System Cyber Attack Defense with DERs

The use of smart inverter capabilities of distributed energy resources (DERs) enhances the grid reliability but in the meanwhile exhibits more vulnerabilities to cyber-attacks. This paper proposes a deep reinforcement learning (DRL)-based defense approach. The defense problem is reformulated as a Markov decision making process to control DERs and minimizing load shedding to address the voltage violations caused by cyber-attacks. The original soft actor-critic (SAC) method for continuous actions has been extended to handle discrete and continuous actions for controlling DERs' setpoints and loadshedding scenarios. Numerical comparison results with other control approaches, such as Volt-VAR and Volt-Watt on the modified IEEE 33-node, show that the proposed method can achieve better voltage regulation and have less power losses in the presence of cyber-attacks.

active distribution systems↗

MSU IETC LSTM Ethernet Decode (AN EDGE)

This research explores the ability of machine learning to perform signal separation of an Ethernet style encoded, full-duplex communication. Typical signal separation currently requires an active tap of the communication line, followed by a recombination and retransmission of the data. The purpose of this research is to study a passive approach to data acquisition from a full-duplex signal. The machine learning model used in this research is a long-short-term memory recurrent neural network (LSTM-RNN). The results show that the LSTM was largely successful in recreating the transmission signal from the measured data points, though the separated signals have not yet been tested using a decoding method.

Full Duplex Signals↗

Comparison of Cyclooxygenase-1 Crystal Structures: Cross-Talk between Monomers Comprising Cyclooxygenase-1 Homodimers

Prostaglandin endoperoxide H synthases (PGHSs)-1 and -2 (also called cyclooxygenases (COXs)-1 and -2) catalyze the committed step in prostaglandin biosynthesis. Both isoforms are targets of nonsteroidal antiinflammatory drugs (NSAIDs). PGHSs are homodimers that exhibit half-of-sites COX activity; moreover, some NSAIDs cause enzyme inhibition by binding only one monomer. To learn more about the cross-talk that must be occurring between the monomers comprising each PGHS-1 dimer, we analyzed structures of PGHS-1 crystallized under five different conditions including in the absence of any tightly binding ligand and in the presence of nonspecific NSAIDs and of a COX-2 inhibitor. When crystallized with substoichiometric amounts of an NSAID, both monomers are often fully occupied with inhibitor; thus, the enzyme prefers to crystallize in a fully occupied form. In comparing the five structures, we only observe changes in the positions of residues 123-129 and residues 510-515. In cases where one monomer is fully occupied with an NSAID and the partner monomer is incompletely occupied, an alternate conformation of the loop involving residues 123-129 is seen in the partially occupied monomer. We propose, on the basis of this observation and previous cross-linking studies, that cross-talk between monomers involves this mobile 123-129 loop, which is located at the dimer interface. In ovine PGHS-1 crystallized in the absence of an NSAID, there is an alternative route for substrate entry into the COX site different than the well-known route through the membrane binding domain.

36 MATERIALS SCIENCE↗

Informatics guided discovery of surface structure-chemistry relationships in catalytic nanoparticles

A data driven discovery strategy based on statistical learning principles is used to discover new correlations between electronic structure and catalytic activity of metal surfaces. From the quantitative formulations derived from this informatics based model, a high throughput computational framework for predicting binding energy as a function of surface chemistry and adsorption configuration that bypasses the need for repeated electronic structure calculations has been developed.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Machine Learning–Augmented Laser-Induced Breakdown Spectroscopy for Spectral Discrimination of Iron Oxalates

Enhanced characterization and phase identification of post-PUREX Pu Oxalates (PuOXA) are pivotal for nonproliferation and pre-detonation nuclear forensics. Despite significant advances in the characterization of PuO 2 samples, little is known about the impact of both the chemical structure and oxidation states of PuOXA (i.e., Pu(III) and Pu(IV)) have on optical emission signatures. Here, we demonstrate the analytical capabilities of laser-induced breakdown spectroscopy (LIBS) applied to Fe(II) and Fe(III) oxalate samples as surrogates for PuOXA, highlighting the discriminating features in the LIBS emission spectra arising from differences in the oxidation states within mixed FeOXA samples. We report the enhancement of spectral feature selection using Principal Component Analysis (PCA), which enables the analytical superiority of machine learning algorithms such as Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), Partial Least Squares Regression (PLSR), Support Vector Regression (SVR), and Random Forest Regression (RFR) over conventional univariate techniques for phase discrimination and chemometric analysis. Cluster analysis revealed how both matrix effects and laser ablation influence cluster separability by introducing spectral artifacts that misdirect the maximization of variance. PCA-selected emission lines were used in the regression models, demonstrating that both univariate and multivariate linear regression models (i.e., PLSR and SVR) can achieve acceptable performance, with machine learning models outperforming conventional calibration regressions. Furthermore, the application of non-linearly activated PCA-selected emission lines illustrates how simplifying the data while retaining captured variance enables the use of less complex and more computationally efficient models. Furthermore, this is particularly evident in the underperformance of RFR, which suffers from increased computational costs and overfitting owing to its high complexity.

Oxalates↗

Investigating permafrost carbon dynamics in Alaska with artificial intelligence

Abstract Positive feedbacks between permafrost degradation and the release of soil carbon into the atmosphere impact land–atmosphere interactions, disrupt the global carbon cycle, and accelerate climate change. The widespread distribution of thawing permafrost is causing a cascade of geophysical and biochemical disturbances with global impacts. Currently, few earth system models account for permafrost carbon feedback (PCF) mechanisms. This research study integrates artificial intelligence (AI) tools and information derived from field-scale surveys across the tundra and boreal landscapes in Alaska. We identify and interpret the permafrost carbon cycling links and feedback sensitivities with GeoCryoAI, a hybridized multimodal deep learning (DL) architecture of stacked convolutionally layered, memory-encoded recurrent neural networks (NN). This framework integratesin-situmeasurements and flux tower observations for teacher forcing and model training. Preliminary experiments to quantify, validate, and forecast permafrost degradation and carbon efflux across Alaska demonstrate the fidelity of this data-driven architecture. More specifically, GeoCryoAI logs the ecological memory and effectively learns covariate dynamics while demonstrating an aptitude to simulate and forecast PCF dynamics—active layer thickness (ALT), carbon dioxide flux (CO 2 ), and methane flux (CH 4 )—with high precision and minimal loss (i.e. ALT RMSE : 1.327 cm [1969–2022]; CO 2 RMSE : 0.697µmolCO 2 m −2 s −1 [2003–2021]; CH 4 RMSE : 0.715 nmolCH 4 m −2 s −1 [2011–2022]). ALT variability is a sensitive harbinger of change, a unique signal characterizing the PCF, and our model is the first characterization of these dynamics across space and time.

Environmental Sciences & Ecology↗

WE-E-18C-01: Multi-Energy CT: Current Status and Recent Innovations

Conventional computed tomography (CT) uses a single polychromatic x-ray spectrum and energy integrating detectors, and produces images whose contrast depends on the effective attenuation coefficient of the broad spectrum beam. This can introduce errors from beam hardening and does not produce the optimal contrast-to-noise ratio. In addition, multiple materials can have the same effective attenuation coefficient, causing different materials to be indistinguishable in conventional CT images. If transmission measurements at two or more energies are obtained, even with polychromatic beams, more specific information about the object can be obtained. If the object does not contain materials with k-edges in the spectrum, the x-ray attenuation can be well-approximated by a linear combination of two processes (photoelectric absorption and Compton scattering) or, equivalently, two basis materials. For such cases, two spectral measurements suffice, although additional measurements can provide higher precision. If K-edge materials are present, additional spectral measurements can allow these materials to be isolated. Current commercial implementations use varied approaches, including two sources operating a different kVp, one source whose kVp is rapidly switched in a single scan, and a dual layer detector that can provide spectral information in every reading. Processing of the spectral information can be performed in the raw data domain or in the image domain. The process of calculating the amount of the two basis functions implicitly corrects for beam hardening and therefore can lead to improvements in quantitative accuracy. Information can be extracted to provide material specific information beyond that of conventional CT. This additional information has been shown to be important in several clinical applications, and can also lead to more efficient clinical protocols. Recent innovations in x-ray sources, detectors, and systems have made multi-energy CT much more practical and improved its performance. In addition, this is a very active area of research and further improvements are expected through further technological improvements. Learning Objectives: Basic principles of multi-energy CT Current implementations of mutli-energy CT Data and image analysis methods in multi-energy CT Current clinical applications of dual energy CT5. recent innovations and anticipated advances in multi-energy CT.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Considerations for Corridor and Community DC Fast Charging Complex System Design

The Idaho National Laboratory (INL), a U.S. Department of Energy (DOE) national laboratory located in Idaho Falls, Idaho, has been DOE’s lead laboratory for the field testing of light-duty plug-in electric vehicles (PEVs), charging infrastructure, and other alternative vehicle technologies for 25 years. INL has tested and collected data from more than 17,000 charging stations, documenting efficiencies, charge profiles, and PEV drivers’ behaviors when using charging infrastructure. Based on the experience of INL staff and support personnel, DOE requested that INL perform three tasks: • Identify pertinent lessons learned from previous direct current (DC) fast charger (DCFC) deployment and data collection activities in order to perform an analysis of the experience to date with DC fast charging systems • Establish the criteria for siting DC fast charging systems, including access to current or future sizeable penetrations of PEVs and existing power, the potential to be used by local (intracity) as well as pass-through (intercity) PEV drivers, expandability, and accessible to the federal highway system • Develop a draft system specification that lists the components that will be incorporated in a DC fast charging complexes.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

DoE as a “Digital Innovation” Sponsor of the WCRP OSC2023 (Final Report)

The WCRP Open Science Conference (https://wcrp-osc2023.org/) was a once-in-a-decade opportunity to jointly explore the transformative actions urgently needed to ensure a sustainable future. Held in Kigali, Rwanda on October 23 -27, 2023, it showcased advances in climate science, helped identify gaps and opportunities, and provided a forum for communities to jointly develop future activities. Scientists, practitioners, politicians, policy makers, intergovernmental agencies and NGOs showcased their work, learned from each other, and explored new ways to work together.

54 ENVIRONMENTAL SCIENCES↗

Data Validation Experiments with a Computer-Generated Imagery Dataset for International Nuclear Safeguards

Computer vision models have great potential as tools for international nuclear safeguards verification activities, but off-the-shelf models require fine-tuning through transfer learning to detect relevant objects. Because open-source examples of safeguards-relevant objects are rare, and to evaluate the potential of synthetic training data for computer vision, we present the Limbo dataset. Limbo includes both real and computer-generated images of uranium hexafluoride containers for training computer vision models. Here, we generated these images iteratively based on results from data validation experiments that are detailed here. The findings from these experiments are applicable both for the safeguards community and the broader community of computer vision research using synthetic data.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗

Technology advancements for servicing of future spacecraft systems

Problems associated with the in-orbit repair and maintenance of spacecraft systems are examined with reference to experience gained from three servicing missions: in-orbit capture, repair, and reflight of the Solar Maximum Mission satellite, capture and return to earth of the Palapa and Westar communications satellites, and in-orbit repair of Syncom 3. It is then shown how the lessons learned from the three servicing missions are applied to current and future servicing activities. In particular, planned servicing missions for the Hubble Space Telescope, tools and servicing facilities development, and the development of the Explorer Platform are discussed.

Cepollina, F. J.↗

Evaluation and analysis of the orbital maneuvering vehicle video system

The work accomplished in the summer of 1989 in association with the NASA/ASEE Summer Faculty Research Fellowship Program at Marshall Space Flight Center is summarized. The task involved study of the Orbital Maneuvering Vehicle (OMV) Video Compression Scheme. This included such activities as reviewing the expected scenes to be compressed by the flight vehicle, learning the error characteristics of the communication channel, monitoring the CLASS tests, and assisting in development of test procedures and interface hardware for the bit error rate lab being developed at MSFC to test the VCU/VRU. Numerous comments and suggestions were made during the course of the fellowship period regarding the design and testing of the OMV Video System. Unfortunately from a technical point of view, the program appears at this point in time to be trouble from an expense prospective and is in fact in danger of being scaled back, if not cancelled altogether. This makes technical improvements prohibitive and cost-reduction measures necessary. Fortunately some cost-reduction possibilities and some significant technical improvements that should cost very little were identified.

Moorhead, Robert J., II↗

The Relationship Between Cosmic-Ray Exposure Ages And Mixing Of CM Chondrite Lithologies

Carbonaceous (C) chondrites are primitive materials probably deriving from C, P and D asteroids, and as such potentially include samples and analogues of the target asteroids of the Dawn, Hayabusa2 and OSIRIS-Rex missions. Foremost among the C chondrites are the CM chondrites, the most common type, and which have experienced the widest range of early solar system processes including oxidation, hydration, metamorphism, and impact shock deformation, often repeatedly or cyclically [1]. To track the activity of these processes in the early solar system, it is critical to learn how many separate bodies are represented by the CMs. Nishiizumi and Caffee [2] have reported that the CMs are unique in displaying several distinct peaks for cosmic-ray exposure (CRE) age groups, and that excavation from significant depth and exposure as small entities in space is the best explanation for the observed radionuclide data. There are either 3 or 4 CRE groups for CMs (Fig.1). We decided to systematically characterize the petrography in each of the CRE age groups to determine whether the groups have significant petrographic differences with these reflecting different parent asteroid geological processing or multiple original bodies. We previously re-ported preliminary results of our work [3], however we have now reexamined these meteorites from the perspective of brecciation, with interesting new results.

Zolensky, M. E.↗

AEROKATS and ROVER Education Network (AREN) – Exploring Through Teamwork

Exploring our home planet and other venues, requires a broad range of talents and contributions. The NASA SciAct AEROKATS and ROVER Education Network (AREN) project aims to bring an array of roles and responsibilities to a project-based learning environment focused on exploring the world around us. Teamwork is critical, and activities range from artistic, fabrication, technical design, data analysis, project planning, communications, and structured field activities. The objective is to create these teams highlighting individual skills and interests combined to form unique and productive environments.

Geoffrey L Bland↗