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 1,369 records · Page 76
All sourcesNASA NTRSDOE OSTI
NASA NTRS1994

Six Years of Parallel Computing at NAS (1987 - 1993): What Have we Learned?

In the fall of 1987 the age of parallelism at NAS began with the installation of a 32K processor CM-2 from Thinking Machines. In 1987 this was described as an "experiment" in parallel processing. In the six years since, NAS acquired a series of parallel machines, and conducted an active research and development effort focused on the use of highly parallel machines for applications in the computational aerosciences. In this time period parallel processing for scientific applications evolved from a fringe research topic into the one of main activities at NAS. In this presentation I will review the history of parallel computing at NAS in the context of the major progress, which has been made in the field in general. I will attempt to summarize the lessons we have learned so far, and the contributions NAS has made to the state of the art. Based on these insights I will comment on the current state of parallel computing (including the HPCC effort) and try to predict some trends for the next six years.

Simon, Horst D.↗
DOE OSTI2022

Instantiation of HCML Demonstrating Bayesian Predictive Modeling for Attentional Control

The research team developed models of Attentional Control (AC) that are unique to existing modeling approaches in the literature. The goal was to enable the research team to (1) make predictions about AC and human performance in real-world scenarios and (2) to make predictions about individual characteristics based on human data. First, the team developed a proof-of-concept approach for representing an experimental design and human subjects data in a Bayesian model, then demonstrated an ability to draw inferences about conditions of interest relevant to real-world scenarios. Ultimately, this effort was successful, and we were able to make reasonable (meaning supported by behavioral data) inferences about conditions of interest to develop a risk model for AC (where risk is defined as a mismatch between AC and attentional demand). The team additionally defined a path forward for a human-constrained machine learning (HCML) approach to make predictions about an individual's state based on performance data. The effort represents a successful first step in both modeling efforts and serves as a basis for future work activities. Numerous opportunities for future work have been defined.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

SLAB: simultaneous labeling and binding affinity prediction for protein–ligand structures

Machine learning models are often used as scoring functions to predict the binding affinity of a protein–ligand complex. These models are trained with limited amounts of data with experimentally measured binding affinity values. A large number of compounds are labeled inactive through single-concentration screens without measuring binding affinities. These inactive compounds, along with the active ones, can be used to train binary classification models, while regression models are trained using compounds with binding affinities only. However, the classification and regression tasks are often handled separately, without sharing the learned feature representations. In this paper, we propose a novel model architecture that jointly performs regression and classification objectives, aiming to maximize data utilization and improve predictive performance by leveraging two complementary tasks. In our setup, the regression yields the binding affinity, whereas the classification task yields the label as active or inactive. We demonstrate our method using PDBbind, the standard 3D structure database, as well as a dataset of flavivirus protease compounds with binding affinity data. Our experiments show that the new joint training strategy improves the accuracy of the model, increasing applicability in various practical drug screening scenarios.

Biological and medical sciences↗
NASA NTRS1999

Lesson Plan Prototype for International Space Station's Interactive Video Education Events

The outreach and education components of the International Space Station Program are creating a number of materials, programs, and activities that educate and inform various groups as to the implementation and purposes of the International Space Station. One of the strategies for disseminating this information to K-12 students involves an electronic class room using state of the art video conferencing technology. K-12 classrooms are able to visit the JSC, via an electronic field trip. Students interact with outreach personnel as they are taken on a tour of ISS mockups. Currently these events can be generally characterized as: Being limited to a one shot events, providing only one opportunity for students to view the ISS mockups; Using a "one to many" mode of communications; Using a transmissive, lecture based method of presenting information; Having student interactions limited to Q&A during the live event; Making limited use of media; and Lacking any formal, performance based, demonstration of learning on the part of students. My project involved developing interactive lessons for K-12 students (specifically 7th grade) that will reflect a 2nd generation design for electronic field trips. The goal of this design will be to create electronic field trips that will: Conform to national education standards; More fully utilize existing information resources; Integrate media into field trip presentations; Make support media accessible to both presenters and students; Challenge students to actively participate in field trip related activities; and Provide students with opportunities to demonstrate learning

Zigon, Thomas↗
NASA NTRS2000

Neural activation during response competition

The flanker task, introduced by Eriksen and Eriksen [Eriksen, B. A., & Eriksen, C. W. (1974). Effects of noise letters upon the identification of a target letter in a nonsearch task. Perception & Psychophysics, 16, 143--149], provides a means to selectively manipulate the presence or absence of response competition while keeping other task demands constant. We measured brain activity using functional magnetic resonance imaging (fMRI) during performance of the flanker task. In accordance with previous behavioral studies, trials in which the flanking stimuli indicated a different response than the central stimulus were performed significantly more slowly than trials in which all the stimuli indicated the same response. This reaction time effect was accompanied by increases in activity in four regions: the right ventrolateral prefrontal cortex, the supplementary motor area, the left superior parietal lobe, and the left anterior parietal cortex. The increases were not due to changes in stimulus complexity or the need to overcome previously learned associations between stimuli and responses. Correspondences between this study and other experiments manipulating response interference suggest that the frontal foci may be related to response inhibition processes whereas the posterior foci may be related to the activation of representations of the inappropriate responses.

Brain Mapping/methods↗
NASA NTRSDate not supplied

Exploring Anomalous PM 2.5 from Wildfires and Dust Storms using Data and Services at NASA GES DISC

The presence of fine particles in the atmosphere with a diameter of less than 2.5 µm, called particulate matter 2.5 (PM 2.5 ), poses a significant threat to human health as a criteria air pollutant. Fortunately, NASA's Goddard Earth Sciences Data and Information Services Center (GES DISC) provides easy access to several PM 2.5 concentration products. These datasets include the reanalysis of global hourly and monthly aerosol components including PM 2.5 data from the Modern-Era Retrospective analysis for Research and Applications, version 2 (MERRA-2), as well as 3-hourly real-time ensemble forecasts of PM 2.5 from the Hazardous Air Quality Ensemble System (HAQES). The HAQES products are developed by the George Mason University Air Quality Laboratory as part of NASA's Health Air Quality Applied Science Team (HAQAST). The GES DISC is actively collaborating with scientists in the HAQAST program to further expand air quality data collections. Two new datasets are currently being archived: one is the machine learning-based global hourly PM 2.5 derived from MERRA-2; the other is the localized data (NO 2 , O 3 , and PM 2.5 ) time series derived from NASA's GEOS Composition Forecasting (GEOS-CF) system. In this presentation, we will explore the spatial patterns and long-distance transport characteristics of elevated PM 2.5 during extreme pollution events, such as the June 2023 Canadian wildfires, which are still active at the time of writing; and severe spring dust storms in 2023 over Asia. To gain comprehensive insights, we will utilize various PM 2.5 data in conjunction with satellite-observed aerosol data from TROPOspheric Monitoring Instrument (TROPOMI) on Sentinel-5P. The primary focus of this presentation will be to demonstrate effective use of data tools and services to visualize and explore extreme air pollution phenomena. Additionally, we will provide guidance on how users can download specific data of interest, facilitating further analysis and research in this critical area.

air quality↗
DOE OSTI2021

Deep Learning Systems for Increased Safeguards Surveillance Review Productivity

Nuclear safeguards inspectors expend significant time and maintain intense focus in reviewing video surveillance for safeguards relevant events. To increase efficiency and reduce the time burden of safeguards inspectors performing surveillance data review, this paper presents a novel deep learning (DL) systems concept to integrate generalized DL models into the safeguards surveillance review workflow. The Agency is investigating several DL algorithms for object recognition, localization, tracking, and flagging relevant activities. The project team is working closely with nuclear safeguards inspectors to identify review use cases (based on specific safeguards objectives) and collect their associated requirements. We focused on CANDU and LWR Nuclear Power Plants (NPPs) and their associated dry storage areas as these present a particularly heavy burden on the inspector surveillance review process due to the number of these facilities under safeguards worldwide. Initial DL algorithm results on safeguards data are promising. Using a convolutional neural network, the team attained a mean average precision (mAP) of 92.9% identifying and localizing spent fuel (SF) casks from a 475 surveillance image dataset. Further, the team had initial success in training a recurrent neural network to identify reactor area activities in video clips, successfully indicating when SF casks enter or exit a pool. We discuss how such DL algorithms would be integrated into the Next Generation Surveillance Review (NGSR) software application. Another issue impacting review productivity is the long time inspectors may have to wait when running these algorithms in NGSR. We present a concept to pre-process remotely collected surveillance data with DL models as the data arrives to IAEA headquarters so that results are already available when starting a new review in NGSR. The proposed DL system concept shows a pathway and workflow for increasing an inspector’s surveillance review productivity by quickly and accurately identifying declared and undeclared safeguards relevant objects and activities in large quantities of surveillance imagery data.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗
DOE OSTI2025

Nonlocal, Pattern-Aware Response and Feedback Framework for Regional Climate Response

We devise a pattern-aware feedback framework for representing the forced climate response using a suite of Green’s function experiments with solar radiation perturbations. By considering the column energy balance, a comprehensive linear response function (CLRF) for important climate variables and feedback quantities such as moist static energy, sea surface temperature, albedo, cloud optical depth, and lapse rate is learned from Green’s function data. The learned CLRF delineates the effects of the energy diffusion in both the ocean and atmosphere and the pattern-aware feedbacks from the aforementioned radiatively active processes. The CLRF can then be decomposed into forcing–response mode pairs, which are in turn used to construct a reduced-order model describing the dominant dynamics of climate responses. These mode pairs capture nonlocal effects and teleconnections in the climate and thus make the reduced-order model apt for capturing regional features of climate response. A key observation is that the CLRF captures the polar-amplified response as the most excitable mode of the climate system, and this mode is explainable in the data-learned pattern-aware feedback framework. The reduced-order model can be used for predicting the response for a given forcing and for reconstructing the forcing from a given response; we demonstrate these capabilities for multiple independent forcing scenarios.

Feedback↗
NASA NTRS2004

Lessons Learned from Two Years of On-Orbit Global Positioning System Experience on International Space Station

The Global Positioning System Subsystem (GPS) for International Space Station (ISS) was activated April 12,2002 following the installation of the SO truss segment that included the GPS antennas on Shuttle mission STS-110. The ISS GPS receiver became the primary source for position, velocity, and attitude information for ISS two days after activation. The GPS receiver also provides a time reference for manual control of ISS time, and will be used for automatic time updates after problems are resolved with the output from the receiver. After two years of on-orbit experience, the GPS continues to be used as the primary navigation source for ISS; however, enough problems have surfaced that the firmware in the GPS attitude code has had to be totally rewritten and new algorithms developed, the firmware that processed the time output from the GPS receiver had to be rewritten, while the GPS navigation code has had minor revisions. The factors contributing to the delivery of a GPS receiver for use on ISS that requires extensive operator intervention to function are discussed. Observations from two years worth of GPS solutions will also be discussed. The technical solutions to the anomalous GPS receiver behavior will be discussed.

Gomez, Susan F.↗
NASA NTRS2010

Lessons Learned from the Wide Field Camera 3 Flight Correlation

The Wide Field Camera 3 (WFC3) instrument was installed into the Hubble Space Telescope (HST) as part of the activities for STS (Space Transportation System)-125 (HST Servicing Mission 4). Initial model predictions for power and radiator temperature were not in good agreement with flight data during a relatively hot, stable period, with the flight power and temperatures being significantly higher than predictions. Significant efforts were undertaken to identify the causes of the discrepancies and to resolve the flight model correlation problems as the thermal vacuum test correlation indicated good agreement. The WFC3 thermal design performance has proven difficult to accurately predict, since the power dissipation on the radiator typically increases as the radiator temperature increases, due to a Thermo Electric Cooler (TEC) attached to the this radiator. This self beating continues until the radiative emissive capability is met for a given temperature, and only then does the system find a quasi-steady regime. Various other factors may also contribute to the radiator temperature, such as backloadlng from the observatory itself and the planet, local high-absorptivity regions near fasteners/holes, and temperature varying parasitic heat leaks from the instrument itself to the radiator. Each of these effects in turn may increase the radiator temperature, and furthermore the demand on the TEC.

Peabody, Hume L.↗
NASA NTRS2011

EMU Lessons Learned Database

As manned space exploration takes on the task of traveling beyond low Earth orbit, many problems arise that must be solved in order to make the journey possible. One major task is protecting humans from the harsh space environment. The current method of protecting astronauts during Extravehicular Activity (EVA) is through use of the specially designed Extravehicular Mobility Unit (EMU). As more rigorous EVA conditions need to be endured at new destinations, the suit will need to be tailored and improved in order to accommodate the astronaut. The Objective behind the EMU Lessons Learned Database(LLD) is to be able to create a tool which will assist in the development of next-generation EMUs, along with maintenance and improvement of the current EMU, by compiling data from Failure Investigation and Analysis Reports (FIARs) which have information on past suit failures. FIARs use a system of codes that give more information on the aspects of the failure, but if one is unfamiliar with the EMU they will be unable to decipher the information. A goal of the EMU LLD is to not only compile the information, but to present it in a user-friendly, organized, searchable database accessible to all familiarity levels with the EMU; both newcomers and veterans alike. The EMU LLD originally started as an Excel database, which allowed easy navigation and analysis of the data through pivot charts. Creating an entry requires access to the Problem Reporting And Corrective Action database (PRACA), which contains the original FIAR data for all hardware. FIAR data are then transferred to, defined, and formatted in the LLD. Work is being done to create a web-based version of the LLD in order to increase accessibility to all of Johnson Space Center (JSC), which includes converting entries from Excel to the HTML format. FIARs related to the EMU have been completed in the Excel version, and now focus has shifted to expanding FIAR data in the LLD to include EVA tools and support hardware such as the Pistol Grip Tool (PGT) and the Battery Charger Module (BCM), while adding any recently closed EMU-related FIARs.

Matthews, Kevin M., Jr.↗
DOE OSTI2023

Internal calibration of transient kinetic data via machine learning

The temporal analysis of products (TAP) reactor provides a vast amount of transient kinetic information that may be used to describe a variety of chemical features including residence time distributions, kinetic coefficients, number of active sites, reaction mechanism, etc. However, as with any measurement device, the TAP reactor signal is convoluted with noise and drift is common. In order to reduce the uncertainty of the kinetic measurement and any derived parameters or mechanisms, proper preprocessing must be performed prior to any advanced type of analysis. This preprocessing includes baseline correction, i.e., a shift in the voltage response, and calibration, i.e., a scaling of the flux response based on prior experiments. The traditional methodology of preprocessing requires significant user discretion and reliance on separate calibration experiments that may drift over time. Herein we use machine learning techniques combined with physical constraints to understand the noise and drift that is being generated within and between experiments for enhancement of the chemical kinetic signal. As such, the proposed methodology demonstrates clear benefits over the traditional preprocessing approach by eliminating the need for separate calibration experiments or heuristic input from the user.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Plug & play directed evolution of proteins with gradient-based discrete MCMC

Abstract A long-standing goal of machine-learning-based protein engineering is to accelerate the discovery of novel mutations that improve the function of a known protein. We introduce a sampling framework for evolving proteins in silico that supports mixing and matching a variety of unsupervised models, such as protein language models, and supervised models that predict protein function from sequence. By composing these models, we aim to improve our ability to evaluate unseen mutations and constrain search to regions of sequence space likely to contain functional proteins. Our framework achieves this without any model fine-tuning or re-training by constructing a product of experts distribution directly in discrete protein space. Instead of resorting to brute force search or random sampling, which is typical of classic directed evolution, we introduce a fast Markov chain Monte Carlo sampler that uses gradients to propose promising mutations. We conduct in silico directed evolution experiments on wide fitness landscapes and across a range of different pre-trained unsupervised models, including a 650 M parameter protein language model. Our results demonstrate an ability to efficiently discover variants with high evolutionary likelihood as well as estimated activity multiple mutations away from a wild type protein, suggesting our sampler provides a practical and effective new paradigm for machine-learning-based protein engineering.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Opportunities for enhancing MLCommons efforts while leveraging insights from educational MLCommons earthquake benchmarks efforts

MLCommons is an effort to develop and improve the artificial intelligence (AI) ecosystem through benchmarks, public data sets, and research. It consists of members from start-ups, leading companies, academics, and non-profits from around the world. The goal is to make machine learning better for everyone. In order to increase participation by others, educational institutions provide valuable opportunities for engagement. In this article, we identify numerous insights obtained from different viewpoints as part of efforts to utilize high-performance computing (HPC) big data systems in existing education while developing and conducting science benchmarks for earthquake prediction. As this activity was conducted across multiple educational efforts, we project if and how it is possible to make such efforts available on a wider scale. This includes the integration of sophisticated benchmarks into courses and research activities at universities, exposing the students and researchers to topics that are otherwise typically not sufficiently covered in current course curricula as we witnessed from our practical experience across multiple organizations. As such, we have outlined the many lessons we learned throughout these efforts, culminating in the need for benchmark carpentry for scientists using advanced computational resources. The article also presents the analysis of an earthquake prediction code benchmark while focusing on the accuracy of the results and not only on the runtime; notedly, this benchmark was created as a result of our lessons learned. Energy traces were produced throughout these benchmarks, which are vital to analyzing the power expenditure within HPC environments. Additionally, one of the insights is that in the short time of the project with limited student availability, the activity was only possible by utilizing a benchmark runtime pipeline while developing and using software to generate jobs from the permutation of hyperparameters automatically. It integrates a templated job management framework for executing tasks and experiments based on hyperparameters while leveraging hybrid compute resources available at different institutions. The software is part of a collection called cloudmesh with its newly developed components, cloudmesh-ee (experiment executor) and cloudmesh-cc (compute coordinator).

58 GEOSCIENCES↗
DOE OSTI2021

Developing Multi-Gene CRISPRa/I Programs to Accelerate DBTL Cycles in ABF Hosts Engineered for Chemical Production (CRADA 468)

Bacterial metabolism is comprised of large and complex gene networks that can produce valuable chemical products. Sophisticated organism engineering efforts are required to optimize production of high-value compounds from these networks. In principle, synthetic multi-gene transcriptional programs could be constructed to reengineer these networks for efficient industrial chemical production. In practice, however, our incomplete ability to understand and model the underlying networks, combined with our limited ability to predictably control the expression of multiple genes makes achieving this goal difficult. To overcome these challenges, we will combine new CRISPR-Cas multi-gene expression programs with computational modeling, machine learning, and multi-omics data to enhance the efficacy of design-build-test-learn (DBTL) cycles. For industrially promising microorganisms in early stages of development, creating technologies for rapidly engineering complex multi-gene programs could be transformative for accelerating data- and model-driven strain design. New CRISPR-Cas tools allow programmable gene activation (CRISPRa) or repression (CRISPRi) at multiple genes simultaneously, using the catalytically inactive Cas9 protein (dCas9) with guide RNAs that recognize DNA targets through predictable Watson-Crick base pairing. To enable accelerated DBTL cycles, we will combine these technologies with advanced Agile BioFoundry (ABF) capabilities for multi-omics data collection and machine learning. We will demonstrate the immediate applicability of these tools by rapidly improving the production of an industrial aromatic in multiple ABF organisms. We recently identified and optimized new transcriptional activators that can be linked to programmable CRISPR-Cas DNA binding domains to activate gene expression in E. coli. We can now use these CRISPRa tools as generalizable trans-acting regulators for combinatorial multi-gene expression tuning that can be easily transferred to new pathways and networks without additional genome engineering. We anticipate these tools will also transfer to new hosts. We have recently found that CRISPRa systems developed in E. coli can be readily ported to Pseudomonas putida, suggesting that multi-gene CRISPRa/i programs for diverse ABF organisms may be within reach.

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS2012

Design and Evaluation of a Water Recirculation Loop Maintenance Device for the Advanced Spacesuit Water Membrane Evaporator

A dual-bed device to maintain the water quality of the Advanced Spacesuit Water Membrane Evaporation (SWME) water recirculation loop has been designed and is undergoing testing. The SWME is a heat rejection device under development at the NASA Johnson Space Center to perform thermal control for advanced spacesuits. One advantage to this technology is the potential for a significantly greater degree of tolerance to contamination when compared to the existing sublimator technology. The driver for the development of a water recirculation maintenance device is to further enhance this advantage through the leveraging of fluid loop management lessons learned from the International Space Station (ISS). A bed design that was developed for a Hamilton Sundstrand military application, and considered for a potential ISS application with the Urine Processor Assembly, provides a low pressure drop means for water maintenance in a recirculation loop. The bed design is coupled with high-capacity ion exchange resins, organic adsorbents, and a cyclic methodology developed for the Extravehicular Mobility Unit Transport Water Loop. The bed design further leverages a sorbent developed for the ISS that introduces a biocide in a microgravity-compatible manner for the Internal Active Thermal Control System. The leveraging of these water maintenance technologies to the SWME recirculation loop is a unique demonstration of applying the valuable lessons learned on the ISS to the next generation of crewed spaceflight Environmental Control and Life Support System hardware.

Steele, John W.↗
DOE OSTI2024

Extreme sparsification of physics-augmented neural networks for interpretable model discovery in mechanics

Data-driven constitutive modeling with neural networks has received increased interest in recent years due to its ability to easily incorporate physical and mechanistic constraints and to overcome the challenging and time-consuming task of formulating phenomenological constitutive laws that can accurately capture the observed material response. However, even though neural network-based constitutive laws have been shown to generalize proficiently, the generated representations are not easily interpretable due to their high number of trainable parameters. Sparse regression approaches exist that allow for obtaining interpretable expressions, but the user is tasked with creating a library of model forms which by construction limits their expressiveness to the functional forms provided in the libraries. Here, in this work, we propose to train regularized physics-augmented neural network-based constitutive models utilizing a smoothed version of $L^0$-regularization. This aims to maintain the trustworthiness inherited by the physical constraints, but also enables interpretability which has not been possible thus far on any type of machine learning-based constitutive model where model forms were not assumed a priori but were actually discovered. During the training process, the network simultaneously fits the training data and penalizes the number of active parameters, while also ensuring constitutive constraints such as thermodynamic consistency. We show that the method can reliably obtain interpretable and trustworthy constitutive models for compressible and incompressible hyperelasticity, yield functions, and hardening models for elastoplasticity, using synthetic and experimental data. This work aims to set a new paradigm for interpretable machine learning models in the broad area of solid mechanics where low and limited data is available along with prior knowledge of physical constraints that the learned maps need to obey. This paradigm can potentially be extended to a broader spectrum of scientific exploration.

Data-driven constitutive models↗
DOE OSTI2023

Model metamers reveal divergent invariances between biological and artificial neural networks

Deep neural network models of sensory systems are often proposed to learn representational transformations with invariances like those in the brain. To reveal these invariances, we generated ‘model metamers’, stimuli whose activations within a model stage are matched to those of a natural stimulus. Metamers for state-of-the-art supervised and unsupervised neural network models of vision and audition were often completely unrecognizable to humans when generated from late model stages, suggesting differences between model and human invariances. Targeted model changes improved human recognizability of model metamers but did not eliminate the overall human–model discrepancy. The human recognizability of a model’s metamers was well predicted by their recognizability by other models, suggesting that models contain idiosyncratic invariances in addition to those required by the task. Metamer recognizability dissociated from both traditional brain-based benchmarks and adversarial vulnerability, revealing a distinct failure mode of existing sensory models and providing a complementary benchmark for model assessment.

59 BASIC BIOLOGICAL SCIENCES↗