Engineering Papers⌕ Search

SEARCH · Engineering Papers

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 973 records · Page 54

Robust spatial memory maps encoded by networks with transient connections

The spiking activity of principal cells in mammalian hippocampus encodes an internalized neuronal representation of the ambient space-a cognitive map. Once learned, such a map enables the animal to navigate a given environment for a long period. However, the neuronal substrate that produces this map is transient: the synaptic connections in the hippocampus and in the downstream neuronal networks never cease to form and to deteriorate at a rapid rate. How can the brain maintain a robust, reliable representation of space using a network that constantly changes its architecture? We address this question using a computational framework that allows evaluating the effect produced by the decaying connections between simulated hippocampal neurons on the properties of the cognitive map. Using novel Algebraic Topology techniques, we demonstrate that emergence of stable cognitive maps produced by networks with transient architectures is a generic phenomenon. The model also points out that deterioration of the cognitive map caused by weakening or lost connections between neurons may be compensated by simulating the neuronal activity. Lastly, the model explicates the importance of the complementary learning systems for processing spatial information at different levels of spatiotemporal granularity.

59 BASIC BIOLOGICAL SCIENCES↗

What we have (not)learned from the ultrarelativistic heavy ion collisions

The field of ultrarelativistic heavy ion collisions is today a flourishing activity both on the experimental and on the theoretical side. Although the theoretical justifications to study these collisions was given already more than three decades ago and the experimental studies have a history of more than 25 years we are still very much in the dark as to the details of the processes and of the characteristics of the matter created in collisions. Increasing the energy of collisions has brought new insights but has also resulted with new challenges. In the present paper I will try from a personal perspective to report on the answers we have collected and on the problems we are faced with. The account is partial, taking into account that it is impossible to render justice to every aspect of the field.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

The Environments of Green Pea Galaxies. I. The KISS Sample

We present environmental analyses for 13 KPNO International Spectroscopic Survey Green Pea (GP) galaxies. These galaxies were discovered via their strong [O ιιι] emission in the redshift range 0.29 < z < 0.42, and they are undergoing a major burst of star formation. A primary goal of this study is to understand what role the environment plays in driving the current star formation activity. By studying the environments around these extreme star-forming galaxies, we can learn more about what triggers their star formation processes and how they fit into the narrative of galaxy evolution. Using the Hydra multifiber spectrograph on the WIYN 3.5 m telescope, we mapped out the galaxy distribution around each of the GPs (out to ~15 Mpc at the redshifts of the targets). Using three density analysis methodologies chosen for their compatibility with the geometry of our redshift survey, we categorized the galaxian densities of the GPs into different density regimes. We find that the GPs in our sample tend to be located in low-density environments. We find no correlation between the density and the SFRs seen in the GPs. We conclude that the environments the GPs are found in are likely not the driving factor behind their extreme star formation activity.

79 ASTRONOMY AND ASTROPHYSICS↗

Investigating the interconnectedness of active transportation and public transit usage as a primer for Mobility-as-a-Service adoption and deployment

With the advent of Mobility-as-a-Service packages to reduce car usage and (by extension) greenhouse gas emissions, it is crucial that researchers and practitioners consider mutual determinants and outcomes that link the adoption of multiple alternative modes. This study therefore investigates the joint usage of active travel (walking, cycling, bike-sharing) and public transit (bus, rail) modes with respect to personal and situational contexts. Online survey data (n = 826) were collected across six Midwestern U.S. states using Amazon MTurk. Respondents indicated their average weekly usage of eight travel modes across three trip purposes so that multimodality could be assessed. Several psychological constructs were extracted via (a) the stages of change framework, used to indicate willingness to adopt new behavior, and (b) confirmatory factor analysis conducted on Likert scales rooted in theories of community, identity, norms, personality, and well-being. A multiple-indicators multiple-causes structural equation model is then employed to investigate the process of adopting a modality style that incorporates active and transit modes. The model confirms that compatible physical and social contexts, as well as navigational skills and openness to learning, are key primers of multimodalism. However, a path juncture stemming from neighborhood support for mobility innovation illustrates a potential polarity in outcomes between individuals and communities. In addition, the stage of active mobility adoption is linked to identity and norm activation, offering further guidance on what influences readiness for change. The seamless integration of mobility services is critical to matching the convenience and comfort of the private vehicle; understanding potential pathways to sustainable mobility, though, requires analyses and interventions that are driven by well-being outcomes and grounded in rigorous psychological frameworks. Here, the research findings offer practical guidance for identifying intervention opportunities to be linked with MaaS enrollment while demonstrating the need to illuminate how mobility might relate to social cohesion, identity expression, and various sources of satisfaction.

42 ENGINEERING↗

Machine learning guided selection of broad-spectrum epitope-specific functional antibodies for "Disease X"

Our project established and demonstrated a transfer learning framework that enables prediction of antibody–antigen interactions across related viruses. The approach focused on three major activities: 1. Conserved region and epitope identification – We compared viral protein structures and sequences to identify shared receptor-binding domains and neutralizing epitope regions across variants and related viruses. These conserved features formed the foundation for discovering broadly functional antibodies. 2. Machine learning model development – We built neural network–based models that integrate epitope features with antibody sequence information. Instead of relying solely on structural or physical properties, the models learned transferable patterns that describe antibody binding potential across different viral families. 3. Transfer learning and validation – Using SARS-CoV-2 and Ebola as source systems, we successfully transferred learned epitope features to predict antibody interactions for SARS CoV-1 and Marburg virus. Iterative cycles of dataset generation, retraining, and evaluation improved generalization and predictive power, ensuring the framework can adapt to new threats.

59 BASIC BIOLOGICAL SCIENCES↗

Machine learning-based prediction of enzyme substrate scope: Application to bacterial nitrilases

Predicting the range of substrates accepted by an enzyme from its amino acid sequence is challenging. Although sequenc- and structure-based annotation approaches are often accurate for predicting broad categories of substrate specificity, they generally cannot predict which specific molecules will be accepted as substrates for a given enzyme, particularly within a class of closely related molecules. Combining targeted experimental activity data with structural modeling, ligand docking, and physicochemical properties of proteins and ligands with various machine learning models provides complementary information that can lead to accurate predictions of substrate scope for related enzymes. Here we describe such an approach that can predict the substrate scope of bacterial nitrilases, which catalyze the hydrolysis of nitrile compounds to the corresponding carboxylic acids and ammonia. Each of the four machine learning models (logistic regression, random forest, gradient-boosted decision trees, and support vector machines) performed similarly (average ROC = 0.9, average accuracy = ~82%) for predicting substrate scope for this dataset, although random forest offers some advantages. Finally, this approach is intended to be highly modular with respect to physicochemical property calculations and software used for structural modeling and docking.

59 BASIC BIOLOGICAL SCIENCES↗

Deep learning of interface structures from simulated 4D STEM data: cation intermixing vs. roughening ∗

Abstract Interface structures in complex oxides remain an active area of condensed matter physics research, largely enabled by recent advances in scanning transmission electron microscopy (STEM). Yet the nature of the STEM contrast in which the structure is projected along the given direction precludes separation of possible structural models. Here, we utilize deep convolutional neural networks (DCNN) trained on simulated 4D STEM datasets to predict structural descriptors of interfaces. We focus on the widely studied interface between LaAlO 3 and SrTiO 3 , using dynamical diffraction theory and leveraging high performance computing to simulate thousands of possible 4D STEM datasets to train the DCNN to learn properties of the underlying structures on which the simulations are based. We test the DCNN on simulated data and show that it is possible (with >95% accuracy) to identify a physically rough from a chemically diffuse interface and create a DCNN regression model to predict step positions. We quantify the applicability of the model to different thicknesses and the transferability of the approach. The method shown here is general and can be applied for any inverse imaging problem where forward models are present.

42 ENGINEERING↗

MO-E-213-00: What Is Medical Physics Without Radiation Safety?

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↗

MO-E-213-01: Increasing Role of Medical Physicist in Radiation Protection

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↗

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↗

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↗