SEARCH · Search NASA

Results for “compressed training”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

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

At least 199 records · Page 11

All sources NASA NTRS DOE OSTI

DOE OSTI2021

Predicting concrete compressive strength using hybrid ensembling of surrogate machine learning models

This study aims to implement a hybrid ensemble surrogate machine learning technique in predicting the compressive strength (CS) of concrete, an important parameter used for durability design and service life prediction of concrete structures in civil engineering projects. For this purpose, an experimental database consisting of 1030 records has been compiled from the machine learning repository of the University of California, Irvine. The database was used to train and validate four conventional machine learning (CML) models, namely Artificial Neural Network (ANN), Linear and Non-Linear Multivariate Adaptive Regression Splines (MARS-L and MARS-C), Gaussian Process Regression (GPR), and Minimax Probability Machine Regression (MPMR). Subsequently, the predicted outputs of CML models were combined and trained using ANN to construct the Hybrid Ensemble Model (HENSM). It is observed that the proposed HENSM produces higher predictive accuracy compared to the CML models used in the present study. The predictive performance of all models for CS prediction was compared using the testing dataset and it is found that the HENSM model attained the highest predictive accuracy in both phases. Based on the experimental results, the newly constructed HENSM model is very potential to be a new alternative in handling the overfitting issues of CML models and hence, can be used to predict the concrete CS, including the design of less polluting and more sustainable concrete constructions.

36 MATERIALS SCIENCE↗

NASA NTRS1988

Sonic Simulation of Near Projectile Hits

Measured frequencies identify projectiles and indicate miss distances. Developmental battlefield-simulation system for training soldiers uses sounds emitted by incoming projectiles to identify projectiles and indicate miss distances. Depending on projectile type and closeness of each hit, system generates "kill" or "near-kill" indication. Artillery shell simulated by lightweight plastic projectile launched by compressed air. Flow of air through groove in nose of projectile generates acoustic tone. Each participant carries audio receiver measure and process tone signal. System performs fast Fourier transforms of received tone to obtain dominant frequency during each succeeding interval of approximately 40 ms (an interval determined from practical signal-processing requirements). With modifications, system concept applicable to collision-warning or collision-avoidance systems.

Statman, J. I.↗

NASA NTRS2011

Category Learning Research in the Interactive Online Environment Second Life

The interactive online environment Second Life allows users to create novel three-dimensional stimuli that can be manipulated in a meaningful yet controlled environment. These features suggest Second Life's utility as a powerful tool for investigating how people learn concepts for unfamiliar objects. The first of two studies was designed to establish that cognitive processes elicited in this virtual world are comparable to those tapped in conventional settings by attempting to replicate the established finding that category learning systematically influences perceived similarity . From the perspective of an avatar, participants navigated a course of unfamiliar three-dimensional stimuli and were trained to classify them into two labeled categories based on two visual features. Participants then gave similarity ratings for pairs of stimuli and their responses were compared to those of control participants who did not learn the categories. Results indicated significant compression, whereby objects classified together were judged to be more similar by learning than control participants, thus supporting the validity of using Second Life as a laboratory for studying human cognition. A second study used Second Life to test the novel hypothesis that effects of learning on perceived similarity do not depend on the presence of verbal labels for categories. We presented the same stimuli but participants classified them by selecting between two complex visual patterns designed to be extremely difficult to label. While learning was more challenging in this condition , those who did learn without labels showed a compression effect identical to that found in the first study using verbal labels. Together these studies establish that at least some forms of human learning in Second Life parallel learning in the actual world and thus open the door to future studies that will make greater use of the enriched variety of objects and interactions possible in simulated environments compared to traditional experimental situations.

Andrews, Jan↗

DOE OSTI2025

Data from: 'Abiotic influences on continuous conifer forest structure across a subalpine watershed'

This package archives the core data used for analysis and inference in 'Abiotic influences on continuous conifer forest structure across a subalpine watershed' (Worsham et al., 2025). All data were collected in the East River, Washington Gulch, Slate River, and Coal Creek watersheds of Colorado. In the paper, we quantified the relative influence of climate, topographic, edaphic, and geologic factors on conifer stand structure and composition, and their functional relationships, at the watershed scale. We used waveform LiDAR data to derive spatially continuous stand structure metrics. We fused these with a species-level classification map to estimate tree species abundance. We applied generalized additive and generalized boosted models to evaluate the covariability of structural and compositional metrics with abiotic variables. The package contains the essential products required for reproducing our analysis and the tables and figures reported in the publication. The products comprise four classes: (1) geospatial data, (2) tabular data used for inferential analysis, (3) tabular data describing analytical results and performance statistics, and (4) a data user guide. (1) includes discretized waveform LiDAR data, locations and attributes of individual tree crowns, sampling locations and domain boundaries, a canopy height model, and raster files of estimated forest structural and compositional metrics at 100 m grid scale. (2) includes all response and explanatory variable values applied in inferential models. Response variables include conifer forest stand density, basal area, 95th percentile height, quadratic mean diameter, and others. Explanatory variables include climatic water deficit, actual evapotranspiration, elevation, heat load, soil available water content, and others. (3) includes results of training and testing several individual tree detection (ITD) algorithms, as well as inferential modeling results. (4) is a PDF user guide for this data package, including detailed descriptions and data dictionaries for all files. The data package root contains 17 assets: 8 compressed tape archive (.tar.gz) files, 5 comma-separated values (.csv) files, 3 Geographic Tagged Image File Format (GeoTIFF) (.tif) files, and 1 Portable Document Format (.pdf) file. The compressed .tar.gz archives contain ESRI shapefiles (.shp) .tif, compressed LASer (.laz), and .csv files. The archives must first be decompressed using the widely distributed command-line software utility TAR. All other files, including constituent files within the .tar.gz archives, can be opened in the open-source R statistical computing environment. Alternatively, .csv files may also be read in any simple text editor software or Microsoft Excel. Geospatial files including .shp and .tif files can also be opened in GIS software, such as QGIS (open-source) or ESRI ArcGIS (proprietary). The .pdf Data User Guide can be read with Adobe Acrobat Reader or other compatible readers.

2018 NEON and 2025 CHESS Campaigns↗

DOE OSTI2022

MetaText: Compositional Generalization in Deep Language Models

Compositional generalization, the ability to infer and reason using novel combinations of previously encountered entities and structures, is a trait of great utility across a variety of deep learning tasks; it implies a certain ability to reason using consistent and therefore interpretable rules, to understand the constituent parts of its input at multiple levels of granularity, to be robust to spurious differences between semantically equivalent inputs, and more. We seek to understand the degree to which existing natural language models achieve or fall short of compositional generalization across a variety of tasks, whether there are distinct types of compositional generalization in practice, and to identify avenues of intervention through which we can improve models’ compositional generalization ability. After exploring these questions using an array of models, tasks, and potential interventions we see that large, pretrained language models have encountered sufficient training data to account for a variety of fine-grained compositional behavior but still struggle to reason at the level of phrases or larger language structures. Non-intrusive, data-based interventions in the form of augmenting individual sequences with compressed versions of themselves or deriving new examples from induced grammars prove insufficient to encourage greater levels of compositional reasoning, indicating that future work might benefit most from focusing on changes to a model’s inductive bias at the architectural or loss level, or by integrating compositionality-boosting data interventions into the large-scale pretraining process itself.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Decode the Workload: Training Deep Learning Models for Efficient Compute Cluster Representation

Monitoring the status of a high throughput computing cluster running computationally intensive production jobs is a crucial yet challenging system administration task due to the complexity of such systems. To this end, we train autoencoders using the Linux kernel CPU metrics of the cluster. Additionally, we explore assisting these models with graph neural networks to share information across threads within a compute node. The models are compared in terms of their ability to: 1) Produce a compressed latent representation that captures the salient features of the input, 2) Detect anomalous activity, and 3) Make distinction between different kinds of jobs run at Jefferson Lab. The goal is to have a robust encoder whose compressed embeddings are used for several downstream tasks. We extend this study further by deploying these models in a human-in-the-loop production-based setting for the anomaly detection task and discuss the associated implementation aspects such as continual learning and the criterion to generate alarms. This study represents a first step in the endeavor towards building self-supervised large-scale foundation models for computing centers.

Mohammed, Ahmed↗

NASA NTRS1993

Teaching high-performance skills using above-real-time training

The above real-time training (ARTT) concept is an approach to teaching high-performance skills. ARTT refers to a training paradigm that places the operator in a simulated environment that functions at faster than normal time. It represents a departure from the intuitive, but not often supported, feeling that the best practice is determined by the training environment with the highest fidelity. This approach is hypothesized to provide greater 'transfer value' per simulation trial, by incorporating training techniques and instructional features into the simulator. Two related experiments are discussed. In the first, 25 naive male subjects performed three tank gunnery tasks on a simulator under varying levels of time acceleration (i.e., 1.0x, 1.6x, 2.0x, sequential, and mixed). They were then transferred to a standard (1.0x) condition for testing. Every accelerated condition or combination of conditions produced better training and transfer than the standard condition. Most effective was the presentation of trials at 1.0x, 1.6x, and 2.0x in a random order during training. Overall, the best ARTT group scored about 50 percent higher and trained in 25 percent less time compared to the real-time control group. In the second experiment, 24 mission-capable F-16 pilots performed three tasks on a part-task F-16A flight simulator under varying levels of time compression (i.e., 1.0x, 1.5x, 2.0x, and random). All subjects were then tested in a real-time environment. The emergency procedure (EP) task results showed increased accuracy for the ARTT groups. In testing (transfer), the ARTT groups not only performed the EP more accurately, but dealt with a simultaneous enemy significantly better than a real-time control group. Although the findings on an air combat maneuvering task and stern conversion task were mixed, most measures indicated that the ARTT groups performed better and faster than a real-time control group. Other implications for ARTT are discussed along with future research directions.

Guckenberger, Dutch↗

DOE OSTI2024

DLSIA: Deep Learning for Scientific Image Analysis

DLSIA (Deep Learning for Scientific Image Analysis) is a Python-based machine learning library that empowers scientists and researchers across diverse scientific domains with a range of customizable convolutional neural network (CNN) architectures for a wide variety of tasks in image analysis to be used in downstream data processing. DLSIA features easy-to-use architectures, such as autoencoders, tunable U-Nets and parameter-lean mixed-scale dense networks (MSDNets). Additionally, this article introduces sparse mixed-scale networks (SMSNets), generated using random graphs, sparse connections and dilated convolutions connecting different length scales. For verification, several DLSIA-instantiated networks and training scripts are employed in multiple applications, including inpainting for X-ray scattering data using U-Nets and MSDNets, segmenting 3D fibers in X-ray tomographic reconstructions of concrete using an ensemble of SMSNets, and leveraging autoencoder latent spaces for data compression and clustering. As experimental data continue to grow in scale and complexity, DLSIA provides accessible CNN construction and abstracts CNN complexities, allowing scientists to tailor their machine learning approaches, accelerate discoveries, foster interdisciplinary collaboration and advance research in scientific image analysis.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1989

Multisatellite and ground-based observations of transient ULF waves

Transient ULF pulsations associated with variations in solar wind plasma density observed by the IMP 8 satellite are presently studied in light of observations obtained during a fortuitous alignment of the AMPTE and Viking satellites with respect to the EISCAT Magnetometer Cross. It is found that the isolated 10-min oscillation in solar wind plasma density produced magnetic field compression oscillations within the magnetosphere at the same frequency, thereby enhancing resonant oscillations at approximately twice the frequency which were already present. Support is seen for the periodic solar wind density variation's exciting of a tailward-traveling large-scale magnetosphere wave train which excites local field line resonant oscillations.

Potemra, T. A.↗

NASA NTRS1991

Control of unsteady separated flow associated with the dynamic pitching of airfoils

Although studies have been done to understand the dependence of parameters for the occurrence of deep stall, studies to control the flow for sustaining lift for a longer time has been little. To sustain the lift for a longer time, an understanding of the development of the flow over the airfoil is essential. Studies at high speed are required to study how the flow behavior is dictated by the effects of compressibility. When the airfoil is pitched up in ramp motion or during the upstroke of an oscillatory cycle, the flow development on the upper surface of the airfoil and the formation of the vortex dictates the increase in lift behavior. Vortex shedding past the training edge decreases the lift. It is not clear what is the mechanism associated with the unsteady separation and vortex formation in present unsteady environment. To develop any flow control device, to suppress the vortex formation or delay separation, it is important that this mechanism be properly understood. The research activities directed toward understanding these questions are presented and the results are summarized.

Ahmed, Sajeer↗

DOE OSTI2023

Optimal sensor placement for reconstructing wind pressure field around buildings using compressed sensing

Deciding how to optimally deploy sensors in a large, complex, and spatially extended structure is critical to ensure that the surface pressure field is accurately captured for subsequent analysis and design. In some cases, reconstruction of missing data is required in downstream tasks such as the development of digital twins. Here, this paper presents a data-driven sparse sensor selection algorithm, aiming to provide the most information contents for reconstructing aerodynamic characteristics of wind pressures over tall building structures parsimoniously. The algorithm first fits a set of basis functions to the training data, then applies a computationally efficient QR algorithm that ranks existing pressure sensors in order of importance based on the state reconstruction to this tailored basis. The findings of this study show that the proposed algorithm successfully re- constructs the aerodynamic characteristics of tall buildings from sparse measurement locations, generating stable and optimal solutions across a range of conditions. As a result, this study serves as a promising first step toward leveraging the success of data-driven and machine learning algorithms to supplement traditional genetic algorithms currently used in wind engineering.

42 ENGINEERING↗

DOE OSTI2023

Predicting wind-driven spatial deposition through simulated color images using deep autoencoders

Abstract For centuries, scientists have observed nature to understand the laws that govern the physical world. The traditional process of turning observations into physical understanding is slow. Imperfect models are constructed and tested to explain relationships in data. Powerful new algorithms can enable computers to learn physics by observing images and videos. Inspired by this idea, instead of training machine learning models using physical quantities, we used images, that is, pixel information. For this work, and as a proof of concept, the physics of interest are wind-driven spatial patterns. These phenomena include features in Aeolian dunes and volcanic ash deposition, wildfire smoke, and air pollution plumes. We use computer model simulations of spatial deposition patterns to approximate images from a hypothetical imaging device whose outputs are red, green, and blue (RGB) color images with channel values ranging from 0 to 255. In this paper, we explore deep convolutional neural network-based autoencoders to exploit relationships in wind-driven spatial patterns, which commonly occur in geosciences, and reduce their dimensionality. Reducing the data dimension size with an encoder enables training deep, fully connected neural network models linking geographic and meteorological scalar input quantities to the encoded space. Once this is achieved, full spatial patterns are reconstructed using the decoder. We demonstrate this approach on images of spatial deposition from a pollution source, where the encoder compresses the dimensionality to 0.02% of the original size, and the full predictive model performance on test data achieves a normalized root mean squared error of 8%, a figure of merit in space of 94% and a precision-recall area under the curve of 0.93.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2024

HGQ: High Granularity Quantization for Real-time Neural Networks on FPGAs

Neural networks with sub-microsecond inference latency are required by many critical applications. Targeting such applications deployed on FPGAs, we present High Granularity Quantization (HGQ), a quantization-aware training framework that optimizes parameter bit-widths through gradient descent. Unlike conventional methods, HGQ determines the optimal bit-width for each parameter independently, making it suitable for hardware platforms supporting heterogeneous arbitrary precision arithmetic. In our experiments, HGQ shows superior performance compared to existing network compression methods, achieving orders of magnitude reduction in resource consumption and latency while maintaining the accuracy on several benchmark tasks. These improvements enable the deployment of complex models previously infeasible due to resource or latency constraints. HGQ is open-source and is used for developing next-generation trigger systems at the CERN ATLAS and CMS experiments for particle physics, enabling the use of advanced machine learning models for real-time data selection with sub-microsecond latency.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2024

Synthetic Streamflow Datasets to Support Emulation of Water Allocations via LSTM

This archive is the data companion to the bonney_et-al_2026_erc metarepo which generates synthetic data, trains an LSTM model, and generates performance metrics on the trained model. While the generation of the synthetic data is fully reprodicible, it is a computationally expensive process. This data archive contains the synthetic datasets needed for training and testing an LSTM model and reproduction of figures and tables. In addition, supplemenatary data products generating and visualizing results is also included, such as geospatial data for the basin. Contents There are two high level directories: `WRAP_archive/` and `repo_data/`. The `WRAP_archive` directory contains compressed intermediate dataproducts from the dataset generation workflow (marked as "I_Dataset_Generation" in the metarepo). These data products are not required by any scripts in the metarepo, but they are archived as they are expensive to generate and may have useful information for other analyses. The `repo_data` directory contains the necessary data for reproducing the workflow in the metarepo and should be decompressed and moved into the top level of the metarepo. Additional details are provided in README.md.

drought↗

NASA NTRS2024

Mechanical Testing of Soils from the South Range of the Utah Test and Training Range: Derivation of Soil Properties to Support the Earth Entry System Landing for Mars Sample Return

This report summarizes results from laboratory tests conducted by Applied Research Associates, Inc. (ARA) on soil samples collected from multiple sites within the South Range of the U.S. Air Force Utah Test and Training Range (UTTR). The goal of the laboratory tests was to establish soil constitutive properties and develop computational soil models enabling NASA to simulate impact landings of the Earth Entry System (EES) for the Mars Sample Return (MSR) mission. Test methods and results are presented describing the strength, compressibility, and stiffness of soils in the UTTR South Range including methods to incorporate the measured properties into Ansys LS-DYNAÒ constitutive material models for EES landing simulations.

Soil↗

NASA NTRS2012

Extreme Tele-Echocardiography: Methodology for Remote Guidance of In-Flight Echocardiography Aboard the International Space Station

Methods: In the year before launch of an ISS mission, potential astronaut echocardiographic operators participate in 5 sessions to train for echo acquisitions that occur roughly monthly during the mission, including one exercise echocardiogram. The focus of training is familiarity with the study protocol and remote guidance procedures. On-orbit, real-time guidance of in-flight acquisitions is provided by a sonographer in the Telescience Center of Mission Control. Physician investigators with remote access are able to relay comments on image quality to the sonographer. Live video feed is relayed from the ISS to the ground via the Tracking and Data Relay Satellite System with a 2- second transmission delay. The expert sonographer uses these images, along with twoway audio, to provide instructions and feedback. Images are stored in non-compressed DICOM format for asynchronous relay to the ground for subsequent off-line analysis. Results: Since June, 2009, a total of 27 resting echocardiograms and 5 exercise studies have been performed during flight. Average acquisition time has been 45 minutes, reflecting 26,000 km of ISS travel per study. Image quality has been adequate in all studies, and remote guidance has proven imperative for fine-tuning imaging and prioritizing views when communication outages limit the study duration. Typical resting studies have included 27 video loops and 30 still-frame images requiring 750 MB of storage. Conclusions: Despite limited crew training, remote guidance allows research-quality echocardiography to be performed by non-experts aboard the ISS. Analysis is underway and additional subjects are being recruited to define the impact of microgravity on cardiac structure and systolic and diastolic function.

Martin, David S.↗

DOE OSTI2020

Solving differential equations using deep neural networks

Recent work on solving partial differential equations (PDEs) with deep neural networks (DNNs) is presented. The paper reviews and extends some of these methods while carefully analyzing a fundamental feature in numerical PDEs and nonlinear analysis: irregular solutions. First, the Sod shock tube solution to the compressible Euler equations is discussed and analyzed. This analysis includes a comparison of a DNN-based approach with conventional finite element and finite volume methods, and demonstrates that the DNN is competitive in terms of degrees of freedom required for a given accuracy. Further, the DNN-based approach is extended to consider performance improvements and simultaneous parameter space exploration. Next, a shock solution to compressible magnetohydrodynamics (MHD) is solved for, and used in a scenario where experimental data is utilized to enhance a PDE system that is a priori insufficient to validate against the observed/experimental data. This is accomplished by enriching the model PDE system with source terms that are then inferred via supervised training with synthetic experimental data. The resulting DNN framework for PDEs enables straightforward system prototyping and natural integration of large data sets (be they synthetic or experimental), all while simultaneously enabling single-pass exploration of an entire parameter space.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

NASA NTRS2011

Extreme Tele-Echocardiography: Methodology for Remote Guidance of In-flight Echocardiography Aboard the International Space Station

Echocardiography is ideally suited for cardiovascular imaging in remote environments, but the expertise to perform it is often lacking. In 2001, an ATL HDI5000 was delivered to the International Space Station (ISS). The instrument is currently being used in a study to investigate the impact of long-term microgravity on cardiovascular function. The purpose of this report is to describe the methodology for remote guidance of echocardiography in space. Methods: In the year before launch of an ISS mission, potential astronaut echocardiographic operators participate in 5 sessions to train for echo acquisitions that occur roughly monthly during the mission, including one exercise echocardiogram. The focus of training is familiarity with the study protocol and remote guidance procedures. On-orbit, real-time guidance of in-flight acquisitions is provided by a sonographer in the Telescience Center of Mission Control. Physician investigators with remote access are able to relay comments on image optimization to the sonographer. Live video feed is relayed from the ISS to the ground via the Tracking and Data Relay Satellite System with a 2 second transmission delay. The expert sonographer uses these images along with two-way audio to provide instructions and feedback. Images are stored in non-compressed DICOM format for asynchronous relay to the ground for subsequent off-line analysis. Results: Since June, 2009, a total of 19 resting echocardiograms and 4 exercise studies have been performed in-flight. Average acquisition time has been 45 minutes, reflecting 26,000 km of ISS travel per study. Image quality has been adequate in all studies, but remote guidance has proven imperative for fine-tuning imaging and prioritizing views when communication outages limit the study duration. Typical resting studies have included 12 video loops and 21 still-frame images requiring 750 MB of storage. Conclusions: Despite limited crew training, remote guidance allows research-quality echocardiography to be performed by non-experts aboard the ISS. Analysis is underway and additional subjects are being recruited to define the impact of microgravity on cardiac structure and systolic and diastolic function.

Martin, David↗