Search NASA⌕ Search

SEARCH · Search NASA

Results for “Learning systems”

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 865 records · Page 48

BioMart Central Portal: an open database network for the biological community

BioMart Central Portal is a first of its kind, community-driven effort to provide unified access to dozens of biological databases spanning genomics, proteomics, model organisms, cancer data, ontology information and more. Anybody can contribute an independently maintained resource to the Central Portal, allowing it to be exposed to and shared with the research community, and linking it with the other resources in the portal. Users can take advantage of the common interface to quickly utilize different sources without learning a new system for each. The system also simplifies cross-database searches that might otherwise require several complicated steps. Several integrated tools streamline common tasks, such as converting between ID formats and retrieving sequences. The combination of a wide variety of databases, an easy-to-use interface, robust programmatic access and the array of tools make Central Portal a one-stop shop for biological data querying. Here, we describe the structure of Central Portal and show example queries to demonstrate its capabilities. Database URL: http://central.biomart.org.

59 BASIC BIOLOGICAL SCIENCES↗

Novel Proposals for FAIR, Automated, Recommendable, and Robust Workflows

Lightning talks of the Workflows in Support of Large-Scale Science (WORKS) workshop are a venue where the workflow community (researchers, developers, and users) can discuss work in progress, emerging technologies and frameworks, and training and education materials. This paper summarizes the WORKS 2022 lightning talks, which cover five broad topics: data integrity of scientific workflows; a machine learning-based recommendation system; a Python toolkit for running dynamic ensembles of simulations; a cross-platform, high-performance computing utility for processing shell commands; and a meta(data) framework for reproducing hybrid workflows.

Abhinit, Ishan↗

Distributed Cross-Channel Hierarchical Aggregation for Foundation Models

Vision-based scientific foundation models hold significant promise for advancing scientific discovery and innovation. This potential stems from their ability to aggregate images from diverse sources—such as varying physical groundings or data acquisition systems—and to learn spatio-temporal correlations using transformer architectures. However, tokenizing and aggregating images can be compute-intensive, a challenge not fully addressed by current distributed methods. In this work, we introduce the Distributed Cross-Channel Hierarchical Aggregation (D-CHAG) approach designed for datasets with a large number of channels across image modalities. Our method is compatible with any model-parallel strategy and any type of vision transformer architecture, significantly improving computational efficiency. We evaluated D-CHAG on hyperspectral imaging and weather forecasting tasks. When integrated with tensor parallelism and model sharding, our approach achieved up to a 75% reduction in memory usage and more than doubled sustained throughput on up to 1,024 AMD GPUs on the Frontier Supercomputer.

Tsaris, Aristeidis (aris) [ORNL] (ORCID:0000000277↗

Gen IV Education and Training Working Group Webinars’ Initiative

Collaboration and support among national laboratories, industry, universities, and research and development organizations are vital to not only maintain a skilled and competent nuclear workforce but also to avert the risk of human resource shortages. As stated in a recent IAEA paper [1], the world nuclear electrical generating capacity is projected to increase to 554 GW(e) by 2030 and up to 874 GW(e) by 2050 (Fig. 1). This represents a 42% increase over current levels by 2030 and a doubling of the current capacity by 2050. To promote Education and Training (E&T) on Gen IV reactor systems and other nuclear related topics of interest, the Gen IV Education and Training Working Group (ETWG) identifies and advertises training courses; engages collaboration with other international education and training organizations; delivers webinars dedicated to Gen IV systems; and maintains a modern social medium platform to exchange information and ideas on Gen IV R&D topics, as well as on related GIF education and training activities. At the end of June 2020, the GIF ETWG has produced, podcasted and posted forty-one webinars covering the six Gen IV systems and various subjects addressing e.g. the economics of the nuclear fuel cycle, sustainability aspects of Gen IV systems, nuclear fuels and materials challenges, the thorium fuel cycle, energy conversion systems, and lessons learned for knowledge management and preservation. This paper describes the development of these webinars from the initial concept to its full realization, with future webinars planned in 2021, addressing topics such as materials and fuels performance for advanced reactors, small modular reactor.

Paviet, Patricia D.↗

Fast Adaptive Neural Control of Resonant Extraction at Fermilab

We present progress on the development of a machine learning (ML) regulation system for third-order resonant extraction of the beam delivered to the Mu2e experiment at Fermilab. We consider classical and ML-based controllers optimized on semi-analytic simulations and provide performance comparisons for several models. Additionally, we discuss the efficiency of each model in training, which has implications for future work on adaptive control. We also discuss progress on developing optimized implementations of ML models for edge-based inference.

Whitbeck, A. [Fermilab] (ORCID:0000000342245164)↗

Lessons from commissioning and operations of the ICARUS cryogenic system at Fermilab

Results and lessons from three years of commissioning and operations of the cryogenic and purificationsystems of the ICARUS neutrino detector installed at the Fermilab are described. The detector uses liquid argon stored in two separate containers of about 275 m 3 each. The liquid argon must be kept in very stable thermal conditions, and the contamination of electronegative impurities must be consistently kept at small fractions of parts per billion. Since its fill in early 2020, the detector has been commissioned and then operated in neutrino beams at Fermilab for the search of sterile neutrinos and measurements of neutrino-argon cross sections. The results of operating the cryogenic and purification systems and lessons learned, including challenges in reaching the design electron lifetime in argon bath, operating and servicing liquid nitrogen and argon circulation pumps, argon condensers and purifiers, are described. Plans for future operations and list of recommendations are presented.

43 PARTICLE ACCELERATORS↗

The FIT Model - Fuel-cycle Integration and Tradeoffs

All mass streams from fuel separation and fabrication are products that must meet some set of product criteria – fuel feedstock impurity limits, waste acceptance criteria (WAC), material storage (if any), or recycle material purity requirements such as zirconium for cladding or lanthanides for industrial use. These must be considered in a systematic and comprehensive way. The FIT model and the “system losses study” team that developed it [Shropshire2009, Piet2010] are an initial step by the FCR&D program toward a global analysis that accounts for the requirements and capabilities of each component, as well as major material flows within an integrated fuel cycle. This will help the program identify near-term R&D needs and set longer-term goals. The question originally posed to the “system losses study” was the cost of separation, fuel fabrication, waste management, etc. versus the separation efficiency. In other words, are the costs associated with marginal reductions in separations losses (or improvements in product recovery) justified by the gains in the performance of other systems? We have learned that that is the wrong question. The right question is: how does one adjust the compositions and quantities of all mass streams, given uncertain product criteria, to balance competing objectives including cost? FIT is a method to analyze different fuel cycles using common bases to determine how chemical performance changes in one part of a fuel cycle (say used fuel cooling times or separation efficiencies) affect other parts of the fuel cycle. FIT estimates impurities in fuel and waste via a rough estimate of physics and mass balance for a set of technologies. If feasibility is an issue for a set, as it is for “minimum fuel treatment” approaches such as melt refining and AIROX, it can help to make an estimate of how performances would have to change to achieve feasibility.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Strategies for International Cooperation in Support of Energy Development in Pacific Island Nations

The U.S. Department of Energy's National Renewable Energy Laboratory (NREL) has been partnering with island communities around the world to address the technical, policy, social, and economic hurdles to deploying energy efficiency and renewable energy technologies (RETs) on small, islanded systems. The lessons learned from these partnerships are briefly summarized in this document with the goal of supporting the International Renewable Energy Agency (IRENA) in the development of specific near-term and longer-term strategies for island RET deployment.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Multi-Target Camera Tracking, Hand-off and Display LDRD 158819 Final Report

Modern security control rooms gather video and sensor feeds from tens to hundreds of cameras. Advanced camera analytics can detect motion from individual video streams and convert unexpected motion into alarms, but the interpretation of these alarms depends heavily upon human operators. Unfortunately, these operators can be overwhelmed when a large number of events happen simultaneously, or lulled into complacency due to frequent false alarms. This LDRD project has focused on improving video surveillance-based security systems by changing the fundamental focus from the cameras to the targets being tracked. If properly integrated, more cameras shouldn’t lead to more alarms, more monitors, more operators, and increased response latency but instead should lead to better information and more rapid response times. For the course of the LDRD we have been developing algorithms that take live video imagery from multiple video cameras, identify individual moving targets from the background imagery, and then display the results in a single 3D interactive video. In this document we summarize the work in developing this multi-camera, multi-target system, including lessons learned, tools developed, technologies explored, and a description of current capability.

47 OTHER INSTRUMENTATION↗

Multitask Recommender Systems for Cancer Drug Response

The problem we are currently trying to address is that there are many types of cancer drugs and many types of cancers and there is not always experimental data for a specific cancer type and cancer drug interaction. While there is a large possible set of feasible drug and cancer combinations, testing each pair is not realistic due to the high monetary cost of cell-based assays. Thus, this leaves researchers with a difficult choice of what drugs they should test on specific cancer types. This issue is known as the cold-start problem. Our focus is on developing recommender systems capable of addressing the cold-start problem as it relates to interaction between cancer types and cancer drugs. One of the most effective ways to address the cold-start problem is through large data analysis, however due to the cost prohibitive nature of cancer research the largest available data set size is the Genomics of Drug Sensitivity in Cancer with 494,973 genomic associations. To achieve optimal model performance on the cold-start problem, it is advantageous to employ multitask algorithms that are capable of transferring information between cancer datasets. The aim of this report is to draw from adaptations and state of the art developments in both algorithms for recommender systems and multitask learning to model the interaction between cancer cell lines and cancer drugs. Cancer cell lines are defined by the US National Cancer Institute as "cancer cells that keep dividing and growing over time, under certain conditions in a laboratory". This paper will focus on evaluating the performance of Neural Collaborative Filtering and Gaussian Processes, as well as their multitask adaptations, on cancer datasets from CCLE, NCI60, GDSC and CTRP. These methods will be evaluated on model performance in regression prediction but also in interpretability.

60 APPLIED LIFE SCIENCES↗

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↗

The Art of Automation: Translating Electron Microscopy Workflows Into Automated Processes

Acquiring data using a scanning transmission electron microscope (STEM) is a complex, multi-step process. The intricacy of the process depends on the type of sample, composition of the material, desired results of the experiment, resolution requirement and other experimental factors. Each experiment presents unique complications, such as sample drift and contamination, that the microscopist must consider when acquiring data. All these challenges are handled fluidly and expertly by experienced microscopists, but to reach new levels of innovation in material development, including greater reproducibility, throughput, and precision, the automation of these workflows is essential. The initial phase of this work involved translating intuition-based workflows into discrete, programmable steps. Some common key stages in STEM workflows are the initial tuning, scanning the sample for areas of interest, and then acquiring the data. Each stage can be broken further into specific parameter adjustments, such as aberration correction and dwell time optimization, depending on the experiment. When deconstructing various experiments each step was assessed for automation feasibility based on the amount of real time operator decisions. There are steps that lend themselves to automation more readily than others, such as course focusing and sample screening, but there is potential for full automation of all stages with time. As an initial step, an automated montage routine was developed, allowing for the efficient acquisition of large portions of the sample without requiring continuous intervention from the operator. The automation of this small process of the procedure demonstrates the value of this capability. A major challenge in automation arises from discrepancies between commanded, reported and actual stage movements. Using systematic tests, stage movement was quantified. This error can be corrected algorithmically for more accurate workflows in the future. Expanding automation capabilities would result in larger, more efficient data acquisition which allows for more robust statistical analysis. Additionally, this work lays the groundwork for a closed loop system where machine learning algorithms would intake automatically acquired data and make real time decisions. By progressively automating this instrument, this work establishes the foundation for fully automated experimentation in transmission electron microscopy.

97 MATHEMATICS AND COMPUTING↗

Fast Adaptive Neural Control of Resonant Extraction at Fermilab

We present progress on the development of a machine learning (ML) regulation system for third-order resonant extraction of the beam delivered to the Mu2e experiment at Fermilab. We consider classical and ML-based controllers optimized on semi-analytic simulations and provide perfor- mance comparisons for several models. Additionally, we discuss the efficiency of each model in training, which has implications for future work on adaptive control. We also discuss progress on developing optimized implementations of ML models for edge-based inference.

Whitbeck, A. [Fermilab]↗

Quantum Computing Algorithms and Applications for Coherent and Strongly Correlated Chemical Systems

This project advanced quantum algorithms, quantum information theory, strongly correlated electronic structure methods, molecular quantum materials, and exciton transport imaging in coherent condensed phase systems. Across the award period, the team developed new methods for open-quantum-system simulation, Hamiltonian learning, state tomography, reduced-density-matrix and contracted-quantum eigensolver approaches, and quantum diagnostics for device capability and openness.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Portrait and Classification of Individual Haze Particulates

Haze (known as “Mai” in Chinese) threatens the health of billions of people across the globe. To begin solving this problem without severely slowing down the economy, one has to mechanistically and geographically pinpoint the sources of these pollutants, the key of which is to thoroughly characterize and fingerprint the particulates. Here we present a broad survey and classification of thousands of individual airborne particu-lates by using the Scanning Electron Microscope (SEM) to measure their diverse mor-phologies and chemistries, which could eventually be organized into a “haze finger-print database”. For instance, one collection in Xi’an City, China during March-April 2014 yielded 494 airborne particulates that settled on silicon wafers placed outside the window of a 3rd floor office. These 494 particulates were manually imaged with high resolution (down to 2 nm), elementally mapped using Energy-dispersive X-ray Spec-troscopy (EDS), and were identified and categorized into presumed source classes such as construction activities (Ca, Al, Si-O), coal burning (sulfates), biologic (pollen, bac-teria), automotive, mining, steel making, and etc. About 20% of the particulates have mysterious origins, as it is still unclear how they were formed, and a fraction of them contained clearly hazardous elements such as lead and chromium. For future work, we propose using unmanned aerial vehicles with a special “rolling film” substrate that can autonomously collect airborne particulates, a customized SEM auto-imaging system, and machine learning software to establish an online open-access database. The end goal would be to monitor and analyze the particulate pollutants that are pumped into our atmosphere every day, and precisely track down their sources so we can better model and police the quality of the air around us.

54 ENVIRONMENTAL SCIENCES↗

MicroSight Optics

MicroSight is an innovative gunsight technology that allows a marksman's eye to focus on both the front gunsight and the intended target. The MicroSight improves both firearm safety and performance by imaging two objects at different focal distances. The MicroSight was developed at Idaho National Laboratory, and has been licensed by Apollo Optical Systems. You can learn more about INL's research programs at http://www.facebook.com/idahonationallaboratory.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗

Corpus-based Customization for an Ontology

CCAT scans a corpus of text for terms, and computes lexical similarity between corpus terms and taxonomy terms. Based on a set of metrics and a learning algorithm, the system inserts corpus terms into the taxonomy. Conversely, terms from the taxonomy are disambiguated based on the text in the corpus. Unused terms are discarded, and infrequently used senses of terms are collapsed to make the taxonomy more manageable.

Source record↗

Case Study: Natural Gas Regional Transport Trucks

Learn about Ryder System, Inc.'s experience in deploying nearly 200 CNG and LNG heavy-duty trucks and construction and operation of L/CNG stations using ARRA funds. Using natural gas in its fleet, Ryder mitigated the effects of volatile fuel pricing and reduced lifecycle GHGs by 20% and petroleum by 99%.

Compressed natural gas, cng, liquefied natural gas↗