Search NASA⌕ Search

SEARCH · Search NASA

Results for “deep data”

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
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Using Ultrasound Image Augmentation and Ensemble Predictions to Prevent Machine-Learning Model Overfitting

Deep learning predictive models have the potential to simplify and automate medical imaging diagnostics by lowering the skill threshold for image interpretation. However, this requires predictive models that are generalized to handle subject variability as seen clinically. Here, we highlight methods to improve test accuracy of an image classifier model for shrapnel identification using tissue phantom image sets. Using a previously developed image classifier neural network—termed ShrapML—blind test accuracy was less than 70% and was variable depending on the training/test data setup, as determined by a leave one subject out (LOSO) holdout methodology. Introduction of affine transformations for image augmentation or MixUp methodologies to generate additional training sets improved model performance and overall accuracy improved to 75%. Further improvements were made by aggregating predictions across five LOSO holdouts. This was done by bagging confidences or predictions from all LOSOs or the top-3 LOSO confidence models for each image prediction. Top-3 LOSO confidence bagging performed best, with test accuracy improved to greater than 85% accuracy for two different blind tissue phantoms. This was confirmed by gradient-weighted class activation mapping to highlight that the image classifier was tracking shrapnel in the image sets. Overall, data augmentation and ensemble prediction approaches were suitable for creating more generalized predictive models for ultrasound image analysis, a critical step for real-time diagnostic deployment.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2022

A Comparison of Infectious Disease Forecasting Methods across Locations, Diseases, and Time

Accurate infectious disease forecasting can inform efforts to prevent outbreaks and mitigate adverse impacts. This study compares the performance of statistical, machine learning (ML), and deep learning (DL) approaches in forecasting infectious disease incidences across different countries and time intervals. We forecasted three diverse diseases: campylobacteriosis, typhoid, and Q-fever, using a wide variety of features (n = 46) from public datasets, e.g., landscape, climate, and socioeconomic factors. We compared autoregressive statistical models to two tree-based ML models (extreme gradient boosted trees [XGB] and random forest [RF]) and two DL models (multi-layer perceptron and encoder–decoder model). The disease models were trained on data from seven different countries at the region-level between 2009–2017. Forecasting performance of all models was assessed using mean absolute error, root mean square error, and Poisson deviance across Australia, Israel, and the United States for the months of January through August of 2018. The overall model results were compared across diseases as well as various data splits, including country, regions with highest and lowest cases, and the forecasted months out (i.e., nowcasting, short-term, and long-term forecasting). Overall, the XGB models performed the best for all diseases and, in general, tree-based ML models performed the best when looking at data splits. There were a few instances where the statistical or DL models had minutely smaller error metrics for specific subsets of typhoid, which is a disease with very low case counts. Feature importance per disease was measured by using four tree-based ML models (i.e., XGB and RF with and without region name as a feature). The most important feature groups included previous case counts, region name, population counts and density, mortality causes of neonatal to under 5 years of age, sanitation factors, and elevation. This study demonstrates the power of ML approaches to incorporate a wide range of factors to forecast various diseases, regardless of location, more accurately than traditional statistical approaches.

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS2022

SatNet: A Benchmark for Satellite Scheduling Optimization

Satellites provide essential services such as networking and weather tracking, and the number of near-earth and deep space satellites are expected to grow rapidly in the coming years. Communications with terrestrial ground stations is one of the critical functionalities of any space mission. Satellite scheduling is a problem that has been scientifically investigated since the 1970s. A central aspect of this problem is the need to consider resource contention and satellite visibility constraints as they require line of sight. Due to the combinatorial nature of the problem, prior solutions such as linear programs and evolutionary algorithms require extensive compute capabilities to output a feasible schedule for each scenario. Machine learning based scheduling can provide an alternative solution by training a model with historical data and generating a schedule quickly with model inference. We present SatNet, a benchmark for satellite scheduling optimization based on historical data from the NASA Deep Space Network. We propose formulation of the satellite scheduling problem as a Markov Decision Process and use reinforcement learning (RL) policies to generate schedules. The nature of constraints imposed by SatNet differ from other combinatorial optimization problems such as vehicle routing studied in prior literature. Our initial results indicate that RL is an alternative optimization approach that can generate candidate solutions of comparable quality to existing state-of-the-practice results. However, we also find that RL policies overfit to the training dataset and do not generalize well to new data, thereby necessitating continued research on reusable and generalizable agents.

Wilson, Brian↗
NASA NTRSDate not supplied

A Quantitative Analysis on the Use of Supervised Machine Learning in Earth Science

Recent review papers (Ball et al., 2017; Reichstein et al., 2019) have investigated the opportunities and challenges in applying supervised machine learning (ML) techniques to Earth science problems. A common challenge is the lack of training (or labeled) data. Supervised ML, and especially deep learning (DL), require large training datasets. While there are large, open access Earth science archives, the data typically require preprocessing in preparation for supervised ML, frequently including manual labeling. Our objective is to understand the landscape of supervised ML in the Earth sciences, including which research communities have most rapidly adopted supervised ML, which algorithms are applied, and what data are used to train these algorithms. We conducted a literature survey of Earth science papers published during the last 10 years in journals from the American Geophysical Union (AGU), American Meteorological Society (AMS), the Institute of Electrical and Electronics Engineers(IEEE), and the Society of Photo-Optical Instrumentation Engineers (SPIE). We identified papers containing the terms ML, DL, or the names of individual supervised ML algorithms. "Earth science" is an additional required search term for IEEE and SPIE. We investigate trends in supervised ML usage during the 10-year study period, and manually analyzed AGU papers from 2018-2019 to enable deep-dive statistics.

Katrina S Virts↗
DOE OSTI2021

Scalable Plug-and-Play ADMM with Convergence Guarantees

Plug-and-play priors (PnP) is a broadly applicable methodology for solving inverse problems by exploiting statistical priors specified as denoisers. Recent work has reported the state-of-the-art performance of PnP algorithms using pre-trained deep neural nets as denoisers in a number of imaging applications. However, current PnP algorithms are impractical in large-scale settings due to their heavy computational and memory requirements. This work addresses this issue by proposing an incremental variant of the widely used PnP-ADMM algorithm, making it scalable to problems involving a large number measurements. Here, we theoretically analyze the convergence of the algorithm under a set of explicit assumptions, extending recent theoretical results in the area. Additionally, we show the effectiveness of our algorithm with nonsmooth data-fidelity terms and deep neural net priors, its fast convergence compared to existing PnP algorithms, and its scalability in terms of speed and memory.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2006

Deep Space Test Bed for Radiation Studies

A key factor affecting the technical feasibility and cost of missions to Mars or the Moon is the need to protect the crew from ionizing radiation in space. Some analyses indicate that large amounts of spacecraft shielding may be necessary for crew safety. The shielding requirements are driven by the need to protect the crew from Galactic cosmic rays (GCR). Recent research activities aimed at enabling manned exploration have included shielding materials studies. A major goal of this research is to develop accurate radiation transport codes to calculate the shielding effectiveness of materials and to develop effective shielding strategies for spacecraft design. Validation of these models and calculations must be addressed in a relevant radiation environment to assure their technical readiness and accuracy. Test data obtained in the deep space radiation environment can provide definitive benchmarks and yield uncertainty estimates of the radiation transport codes. The two approaches presently used for code validation are ground based testing at particle accelerators and flight tests in high-inclination low-earth orbits provided by the shuttle, free-flyer platforms, or polar-orbiting satellites. These approaches have limitations in addressing all the radiation-shielding issues of deep space missions in both technical and practical areas. An approach based on long duration high altitude polar balloon flights provides exposure to the galactic cosmic ray composition and spectra encountered in deep space at a lower cost and with easier and more frequent access than afforded with spaceflight opportunities. This approach also results in shorter development times than spaceflight experiments, which is important for addressing changing program goals and requirements.

Adams, James H.↗
DOE OSTI2025

In situ Detection of Plasma Induced Surface Interaction based on Deep Learning based Visual Diagnostics (Technical Report)

It is characteristic for many plasma devices to undergo plasma-material interaction leading to surface erosion. These processes, often not easily detectable, lead to changes in device performance and lifespan. State-of-the-art lifetime tests and wear experiments require over 1000s hours. A self-consistent model for accurately predicting the erosion's effects is not available. In situ detection of these processes is not a trivial task since the surface variations at the early stages have a micron scale. Such limitations not only restrict testing and prediction capabilities but also slow the development of new thrusters and limit mission duration. To address these challenges, an in-situ diagnostic for real-time erosion assessment has been developed, aiming to expedite lifetime testing and broaden experimental campaigns. Several works were dedicated to real-time and in situ monitoring of material erosion during plasma exposure using laser holography, microscopy, and with telemicroscopes. However, the applicability of these approaches is limited due to complexity, cost and less flexibility as they often require placing diagnostic equipment inside the vacuum chamber. In collaboration with Princeton Collaborative Research Facility (PCRF), Princeton Plasma Physics Laboratory (PPPL), a new diagnostic approach is developed, where geometry modifications to the ceramic channel walls were introduced that would result in accelerated channel erosion. We employed Long-distance microscope (LDM) imagery, combined with Deep-Learning based Shape from focus or depth from focus (DFF or SFF) approach, that provides an accessible and cost-effective solution. LDM employs focus variation techniques to continuously capture multiple images of the target object at distinct focal planes. DFF, an optical focus variation method, generates a 3D topographical surface depth map from a sequence of variably focused images. Combined with the developed diagnostic, this approach offers a controllable means to study erosion under accelerated conditions. In this work, we develop Neural Network-based DFF algorithm applicable for LDM data to quantitatively evaluate plasma induced surface modification from LDM data. Next, we develop Deep Learning-based super-resolution depth map image reconstruction technique to increase the resolution of depth maps obtained from DFF algorithm to improve the accuracy of erosion measurements. Thirdly, we develop several image processing techniques to remove noise and improve the quality of depth map image. Here we report the results of initial tests for this approach. An experimental setup designed and built in PPPL was employed that consists of a 3-cm gridded ion source that produces a neutralized argon beam with energies up to 600 eV. A hexagonal boron nitride (h-BN) ceramic target, designed based on computational predictions, was used. Tests were conducted to reconstruct the complex geometry of the target under the lighting conditions of the operated ion source.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2020

Data-Driven Day-Ahead PV Estimation Using Autoencoder-LSTM and Persistence Model

Inherent variability in photovoltaic (PV) and associated impacts on power systems is a challenging problem for both the PV owners and the grid operators. Existing statistical and machine learning algorithms typically work well for weather conditions similar to historical data. Furthermore, uncertain weather conditions pose a great challenge to the estimation accuracy of the estimation models. With the enhanced integration of intelligent electronic devices and the realization of associated automation in the power grid, renewable energy data is becoming more accessible, which can be utilized by deep learning models and improve the PV power generation estimation accuracy. In this paper, a hybrid deep learning model driven by external weather data is proposed to do day-ahead PV output forecasting at 15-minute-interval. The proposed model is motivated by the recent advancement of Long-Short-Term-Memory (LSTM) networks and AutoEncoder (AE), which estimates uncertainties in sequence while making the prediction for complex weather conditions. Meanwhile, the persistence model (PM) is used to predict continuous sunny weather conditions. The forecasting result is validated with data from multiple locations

42 ENGINEERING↗
NASA NTRS1984

Simulation and assimilation of satellite altimeter data at the oceanic mesoscale

An improved "objective analysis' technique is used along with an altimeter signal statistical model, an altimeter noise statistical model, an orbital model, and synoptic surface current maps in the POLYMODE-SDE area, to evaluate the performance of various observational strategies in catching the mesoscale variability at mid-latitudes. In particular, simulated repetitive nominal orbits of ERS-1, TOPEX, and SPOT/POSEIDON are examined. Results show the critical importance of existence of a subcycle, scanning in either direction. Moreover, long repeat cycles ( 20 days) and short cross-track distances ( 300 km) seem preferable, since they match mesoscale statistics. Another goal of the study is to prepare and discuss sea-surface height (SSH) assimilation in quasigeostrophic models. Restored SSH maps are shown to meet that purpose, if an efficient extrapolation method or deep in-situ data (floats) are used on the vertical to start and update the model.

Demay, P.↗
DOE OSTI2024

Novel candidate taxa contribute to key metabolic processes in Fennoscandian Shield deep groundwaters

The continental deep biosphere contains a vast reservoir of microorganisms, although a large proportion of its diversity remains both uncultured and undescribed. In this study, the metabolic potential (metagenomes) and activity (metatranscriptomes) of the microbial communities in Fennoscandian Shield deep subsurface groundwaters were characterized with a focus on novel taxa. DNA sequencing generated 1270 de-replicated metagenome-assembled genomes and single-amplified genomes, containing 7 novel classes, 34 orders, and 72 families. The majority of novel taxa were affiliated with Patescibacteria, whereas among novel archaea taxa, Thermoproteota and Nanoarchaeota representatives dominated. Metatranscriptomes revealed that 30 of the 112 novel taxa at the class, order, and family levels were active in at least one investigated groundwater sample, implying that novel taxa represent a partially active but hitherto uncharacterized deep biosphere component. The novel taxa genomes coded for carbon fixation predominantly via the Wood–Ljungdahl pathway, nitrogen fixation, sulfur plus hydrogen oxidation, and fermentative pathways, including acetogenesis. These metabolic processes contributed significantly to the total community’s capacity, with up to 9.9% of fermentation, 6.4% of the Wood–Ljungdahl pathway, 6.8% of sulfur plus 8.6% of hydrogen oxidation, and energy conservation via nitrate (4.4%) and sulfate (6.0%) reduction. Key novel taxa included the UBA9089 phylum, with representatives having a prominent role in carbon fixation, nitrate and sulfate reduction, and organic and inorganic electron donor oxidation. These data provided insights into deep biosphere microbial diversity and their contribution to nutrient and energy cycling in this ecosystem.

Candidatus↗
DOE OSTI2018

University of Illinois Campus Deep Direct-Use Feasibility Study - Long-Term Meteorological Data

This submission includes meteorological data recorded by National Weather Service at University of Illinois Willard Airport, Savoy IL for period 1972 to 2018. This data is for use in parameterizing the demand and life-cycle assessments associated with the project, and provides information about energy loads for the buildings being included in the DDU applications. This includes how energy demand fluctuates with seasonal changes in climate, which is used to model expected demand for the DDU system. *Note: All times are reported in local standard time. NC: Wind Chill/Heat Index do not meet the required thresholds to be calculated. cli-MATE: MRCC Application Tools Environment Generated at: 2/7/2018 8:52:33 AM CST m = missing data Date = year-month-day Time = 24 hour clock Temp_F = temperature (deg. fahrenheit) RH_pct = relative humidity (percent) Dewpt_F = dew point (deg. fahrenheit) WindSpeed_mph = wind speed (miles/hour) WindDir_deg = wind direction (deg. from north) PeakWindGust_mph = peak wind gust (miles/hour) Visibility_mi = visibility (miles) AtmPress_hPa = atmospheric pressure (hectopascals) Precip_in = precipitation (inches)

15 GEOTHERMAL ENERGY↗
NASA NTRS1977

Evaluation of DSN data processing with 7200-b/s GCF high-speed data interfaces

Test results confirm that the Deep Space Station (DSS) and Network Operations Control Center (NOCC) processing of telemetry, command, radio metric, and monitor data with the existing DSN Mark III-75 configuration will be unaffected by the recent change of the Ground Communications Facility (GCF) high-speed data subsystem to a clock rate of 7,200 bits per second.

Thorman, H. C.↗
DOE OSTI2023

Oracle-Preserving Latent Flows

A fundamental task in data science is the discovery, description, and identification of any symmetries present in the data. We developed a deep learning methodology for the simultaneous discovery of multiple non-trivial continuous symmetries across an entire labeled dataset. The symmetry transformations and the corresponding generators are modeled with fully connected neural networks trained with a specially constructed loss function, ensuring the desired symmetry properties. The two new elements in this work are the use of a reduced-dimensionality latent space and the generalization to invariant transformations with respect to high-dimensional oracles. The method is demonstrated with several examples on the MNIST digit dataset, where the oracle is provided by the 10-dimensional vector of logits of a trained classifier. We find classes of symmetries that transform each image from the dataset into new synthetic images while conserving the values of the logits. We illustrate these transformations as lines of equal probability (“flows”) in the reduced latent space. These results show that symmetries in the data can be successfully searched for and identified as interpretable non-trivial transformations in the equivalent latent space.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Calorimetry with deep learning: particle simulation and reconstruction for collider physics

Using detailed simulations of calorimeter showers as training data, we investigate the use of deep learning algorithms for the simulation and reconstruction of single isolated particles produced in high-energy physics collisions. We train neural networks on single-particle shower data at the calorimeter-cell level, and show significant improvements for simulation and reconstruction when using these networks compared to methods which rely on currently-used state-of-the-art algorithms. We define two models: an end-to-end reconstruction network which performs simultaneous particle identification and energy regression of particles when given calorimeter shower data, and a generative network which can provide reasonable modeling of calorimeter showers for different particle types at specified angles and energies. We investigate the optimization of our models with hyperparameter scans. Furthermore, we demonstrate the applicability of the reconstruction model to shower inputs from other detector geometries, specifically ATLAS-like and CMS-like geometries. These networks can serve as fast and computationally light methods for particle shower simulation and reconstruction for current and future experiments at particle colliders.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2023

Coordinate-Based Seismic Interpolation in Irregular Land Survey: A Deep Internal Learning Approach

Physical and budget constraints often result in irregular sampling, which complicates accurate subsurface imaging. Preprocessing approaches, such as missing trace or shot interpolation, are typically employed to enhance seismic data in such cases. Recently, deep learning has been used to address the trace interpolation problem at the expense of large amounts of training data to adequately represent typical seismic events. Nonetheless, most research in this area has focused on trace reconstruction, with little attention having been devoted to shot interpolation. Furthermore, existing methods assume regularly spaced receivers/sources failing in approximating seismic data from real (irregular) surveys. This work presents a novel shot gather interpolation approach which uses a continuous coordinate-based representation of the acquired seismic wavefield parameterized by a neural network. The proposed unsupervised approach, which we call coordinate-based seismic interpolation (CoBSI), enables the prediction of specific seismic characteristics in irregular land surveys without using external data during neural network training. Importantly, experimental results on real and synthetic 3-D data validate the ability of the proposed method to estimate continuous smooth seismic events in the time-space and frequency-wavenumber domains, improving sparsity or low-rank-based interpolation methods.

58 GEOSCIENCES↗
NASA NTRS1999

Radiation Environment on Mir Orbital Station During Solar Minimum

Space radiation poses a significant risk for the stay and rotation cycle of astronauts on the International Space Station (ISS). The ISS is in the same orbit as the Mir orbital station and as such, data acquired onboard the Mir station is of direct applicability to the ISS astronaut. During the seven NASA-Mir missions, data were acquired with a variety of both passive and active detectors, including measurements of astronaut doses. This paper describes these measurements and comparisons with measurements carried out by other groups. It is shown that trapped protons absorbed can be very well described by quadratic equation in In(p), where p is the atmospheric density. Similarly, the galactic cosmic ray absorbed dose is nearly exponentially related to the deceleration potential. The average radiation quality factor with the ICRP-60 definition is about 2.44. Using the measured quality factor, absorbed crew doses, and estimates of neutron dose equivalent, leads to crew stay times as short as 9 months during a deep solar minimum. The data are compared with in vivo dose estimates using chromosome aberrations (simple translocations and total exchange) on same astronauts.

Badhwar, Gautam D.↗
NASA NTRS2008

Orbit Determination Processes for the Navigation of the Cassini-Huygens Mission

Deep space navigation, particularly the Orbit Determination (OD) operations of Cassini at Saturn, cannot easily be automated due to the complex dynamical environment in which the spacecraft flies; however several sub-processes are automated. The Cassini OD operations are often faced with unique challenges that require more than routine procedures. The OD Team is staffed appropriately to meet the demanding schedules and allow some level of flexibility. This paper will discuss how the OD processes are developed and the seven-member OD team is scheduled to support efficient and accurate Cassini navigation operations. Also discussed will be the requirements of the radio-metric Doppler and range tracking data acquired via the Deep Space Network and the optical navigation images of the satellites to support the daily OD operations. Furthermore, the reliability of the OD solutions, which is ensured within the framework of the OD processes, will be explained.

Antreasian, P.G.↗
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↗