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 1,243 records · Page 69
All sourcesNASA NTRSDOE OSTI
NASA NTRS1994

Phytoplankton production in the Sargasso Sea as determined using optical mooring data

Optical measurements from an untended mooring provide high-frequency observations of in-water optical properties and permit the estimation of important biological parameters continuously as a function of time. A 9-month time series, composed of three separate deployments, of optical data from the BIOWATT 1987 deep-sea mooring located in the oligotrophic waters of the Sargasso Sea at 34 deg N, 70 deg W are presented. These data have been tested using several bio-optical models for the purpose of providing a continuous estimate of phytoplankton productivity. The data are discussed in the context of contemporaneous shipboard observations and for future ocean color satellite observations. We present a continuous estimation of phytoplankton productivity for the 9-month time series. Results from the first 70-day deployment are emphasized to demonstrate the utility of optical observations as proxy measures of biological parameters, to present preliminary analysis, and to compare our bio-optical observations with concurrent physical observations. The bio-optical features show variation in response to physical forcings including diel variations of incident solar irradiance, episodic changes corresponding to wind forcing, variability caused by advective mesoscale eddy events in the vicinity of the mooring, and seasonal variability corresponding to changes in solar radiation, shoaling of the mixed layer depth, and succession of phytoplankton populations.

Waters, K. J.↗
DOE OSTI2023

Particle size influences decay rates of environmental DNA in aquatic systems

Abstract Environmental DNA (eDNA) analysis is a powerful tool for remote detection of target organisms. However, obtaining quantitative and longitudinal information from eDNA data is challenging, requiring a deep understanding of eDNA ecology. Notably, if the various size components of eDNA decay at different rates, and we can separate them within a sample, their changing proportions could be used to obtain longitudinal dynamics information on targets. To test this possibility, we conducted an aquatic mesocosm experiment in which we separated fish‐derived eDNA components using sequential filtration to evaluate the decay rate and changing proportion of various eDNA particle sizes over time. We then fit four alternative mathematical decay models to the data, building towards a predictive framework to interpret eDNA data from various particle sizes. We found that medium‐sized particles (1–10 μm) decayed more slowly than other size classes (i.e., <1 and > 10 μm), and thus made up an increasing proportion of eDNA particles over time. We also observed distinct eDNA particle size distribution (PSD) between our Common carp and Rainbow trout samples, suggesting that target‐specific assays are required to determine starting eDNA PSDs. Additionally, we found evidence that different sizes of eDNA particles do not decay independently, with particle size conversion replenishing smaller particles over time. Nonetheless, a parsimonious mathematical model where particle sizes decay independently best explained the data. Given these results, we suggest a framework to discern target distance and abundance with eDNA data by applying sequential filtration, which theoretically has both metabarcoding and single‐target applications.

Brandão‐Dias, Pedro F. P.↗
DOE OSTI2021

Processed Lab Data for Neural Network-Based Shear Stress Level Prediction

Machine learning can be used to predict fault properties such as shear stress, friction, and time to failure using continuous records of fault zone acoustic emissions. The files are extracted features and labels from lab data (experiment p4679). The features are extracted with a non-overlapping window from the original acoustic data. The first column is the time of the window. The second and third columns are the mean and the variance of the acoustic data in this window, respectively. The 4th-11th column is the the power spectrum density ranging from low to high frequency. And the last column is the corresponding label (shear stress level). The name of the file means which driving velocity the sequence is generated from. Data were generated from laboratory friction experiments conducted with a biaxial shear apparatus. Experiments were conducted in the double direct shear configuration in which two fault zones are sheared between three rigid forcing blocks. Our samples consisted of two 5-mm-thick layers of simulated fault gouge with a nominal contact area of 10 by 10 cm^2. Gouge material consisted of soda-lime glass beads with initial particle size between 105 and 149 micrometers. Prior to shearing, we impose a constant fault normal stress of 2 MPa using a servo-controlled load-feedback mechanism and allow the sample to compact. Once the sample has reached a constant layer thickness, the central block is driven down at constant rate of 10 micrometers per second. In tandem, we collect an AE signal continuously at 4 MHz from a piezoceramic sensor embedded in a steel forcing block about 22 mm from the gouge layer The data from this experiment can be used with the deep learning algorithm to train it for future fault property prediction.

15 GEOTHERMAL ENERGY↗
DOE OSTI2016

WISE × SuperCOSMOS photometric Redshift catalog: 20 million galaxies over 3π steradians

We cross-match the two currently largest all-sky photometric catalogs—mid-infrared Wide-field Infrared Survey Explorer and SuperCOSMOS scans of UKST/POSS-II photographic plates—to obtain a new galaxy sample that covers 3π steradians. In order to characterize and purify the extragalactic data set, we use external GAMA and Sloan Digital Sky Survey spectroscopic information to define quasar and star loci in multicolor space, aiding the removal of contamination from our extended source catalog. After appropriate data cleaning, we obtain a deep wide-angle galaxy sample that is approximately 95% pure and 90% complete at high Galactic latitudes. The catalog contains close to 20 million galaxies over almost 70% of the sky, outside the Zone of Avoidance and other confused regions, with a mean surface density of more than 650 sources per square degree. Using multiwavelength information from two optical and two mid-IR photometric bands, we derive photometric redshifts for all the galaxies in the catalog, using the ANNz framework trained on the final GAMA-II spectroscopic data. Our sample has a median redshift of z{sub med}=0.2, with a broad dN/dz reaching up to z > 0.4. The photometric redshifts have a mean bias of |δz|∼10{sup −3}, a normalized scatter of σ {sub z} = 0.033, and less than 3% outliers beyond 3σ {sub z}. Comparison with external data sets shows no significant variation of photo-z quality with sky position. Together with the overall statistics, we also provide a more detailed analysis of photometric redshift accuracy as a function of magnitudes and colors. The final catalog is appropriate for “all-sky” three-dimensional (3D) cosmology to unprecedented depths, in particular through cross-correlations with other large-area surveys. It should also be useful for source preselection and identification in forthcoming surveys, such as TAIPAN or WALLABY.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

Do Machine Learning Approaches Offer Skill Improvement for Short-Term Forecasting of Wind Gust Occurrence and Magnitude?

Abstract Wind gusts, and in particular intense gusts, are societally relevant but extremely challenging to forecast. This study systematically assesses the skill enhancement that can be achieved using artificial neural networks (ANNs) for forecasting of wind gust occurrence and magnitude. Geophysical predictors from the ERA5 reanalysis are used in conjunction with an autoregressive term in regression and ANN models with different predictors, and varying model complexity. Models are derived and assessed for the warm (April–September) and cold (October–March) seasons for three high passenger volume airports in the United States. Model uncertainty is assessed by deriving models for 1000 different randomly selected training (70%) and testing (30%) subsets. Gust prediction fidelity in independent test samples is critically dependent on inclusion of an autoregressive term. Gust occurrence probabilities derived using five-layer ANNs exhibit consistently higher fidelity than those from regression models and shallower ANNs. Inclusion of the autoregressive term and increasing the number of hidden layers in ANNs from 1 to 5 also improve the model performance for gust magnitudes (lower RMSE, increased correlation, and model standard deviations that more closely approximate observed values). Deeper ANNs (e.g., 20 hidden layers) exhibit higher skill in forecasting strong (17–25.7 m s −1 ) and damaging (≥25.7 m s −1 ) wind gusts. However, such deep networks exhibit evidence of overfitting and still substantially underestimate (by 50%) the frequency of strong and damaging wind gusts at the three airports considered herein. Significance Statement Improved short-term forecasting of wind gusts will enhance aviation safety and logistics and may offer other societal benefits. Here we present a rigorous investigation of the relative skill of models of wind gust occurrence and magnitude that employ different statistical methods. It is shown that artificial neural networks (ANNs) offer considerable skill enhancement over regression methods, particularly for strong and damaging wind gusts. For wind gust magnitudes in particular, application of deeper learning networks (e.g., five or more hidden layers) offers tangible improvements in forecast accuracy. However, deeper networks are vulnerable to overfitting and exhibit substantial variability with the specific training and testing data subset used. Also, even deep ANNs reproduce only half of strong and damaging wind gusts. These results indicate the need for future work to elucidate the dynamical mechanisms of intense wind gusts and advance solutions to their prediction.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2019

Deep-inelastic and quasielastic electron scattering from A = 3 nuclei

We perform a combined analysis of inclusive electron scattering data from $A=3$ nuclei in the deep-inelastic and quasielastic scattering regions, using Monte Carlo analysis methods and the nuclear weak binding approximation to establish the range over which the data can be described within the same theoretical framework. Comparison with quasielastic $^3$He cross sections from SLAC and Jefferson Lab suggests that most features of the $x \gtrsim 1$ data can be reasonably well described in the impulse approximation with finite-$Q^2$ nuclear smearing functions for momentum transfers $Q^2 \gtrsim 1$~GeV$^2$. For the DIS region, we analyze the recent $^3$He to deuterium cross section ratio from the Jefferson Lab E03-103 experiment to explore the possible isospin dependence of the nuclear effects. We discuss the implications of this for the MARATHON experiment, and outline how a Bayesian analysis of $^3$He, $^3$H and deuterium data can robustly determine the free neutron structure function.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2026

L-VISP: LSTM Visualization for Interpretable Symptom Prediction in Patient Cohorts

Symptom modelling in head and neck cancer is challenged by the complexity of heterogeneous patient data, leading to an interest in deep learning approaches. Although Long Short-Term Memory Networks (LSTMs) have shown great results in patient risk prediction, their low interpretability requires data modellers to collaborate with clinical experts to validate the results. We present L-VISP, a human–machine solution that uses visual analytics for LSTM modelling in clinical research. L-VISP uses custom visual encodings to make multiple LSTM variants interpretable, supporting a full range of analysis, from understanding model operations and evaluating performance to interpreting results in a clinical context. We evaluate L-VISP with data modellers and a clinical oncologist and present the takeaways from this multidisciplinary collaboration.

LSTM modeling↗
DOE OSTI2024

Integrating multi-modal remote sensing, deep learning, and attention mechanisms for yield prediction in plant breeding experiments

In both plant breeding and crop management, interpretability plays a crucial role in instilling trust in AI-driven approaches and enabling the provision of actionable insights. The primary objective of this research is to explore and evaluate the potential contributions of deep learning network architectures that employ stacked LSTM for end-of-season maize grain yield prediction. A secondary aim is to expand the capabilities of these networks by adapting them to better accommodate and leverage the multi-modality properties of remote sensing data. In this study, a multi-modal deep learning architecture that assimilates inputs from heterogeneous data streams, including high-resolution hyperspectral imagery, LiDAR point clouds, and environmental data, is proposed to forecast maize crop yields. The architecture includes attention mechanisms that assign varying levels of importance to different modalities and temporal features that, reflect the dynamics of plant growth and environmental interactions. The interpretability of the attention weights is investigated in multi-modal networks that seek to both improve predictions and attribute crop yield outcomes to genetic and environmental variables. This approach also contributes to increased interpretability of the model's predictions. The temporal attention weight distributions highlighted relevant factors and critical growth stages that contribute to the predictions. The results of this study affirm that the attention weights are consistent with recognized biological growth stages, thereby substantiating the network's capability to learn biologically interpretable features. Accuracies of the model's predictions of yield ranged from 0.82-0.93 R 2 ref in this genetics-focused study, further highlighting the potential of attention-based models. Further, this research facilitates understanding of how multi-modality remote sensing aligns with the physiological stages of maize. The proposed architecture shows promise in improving predictions and offering interpretable insights into the factors affecting maize crop yields, while demonstrating the impact of data collection by different modalities through the growing season. By identifying relevant factors and critical growth stages, the model's attention weights provide valuable information that can be used in both plant breeding and crop management. The consistency of attention weights with biological growth stages reinforces the potential of deep learning networks in agricultural applications, particularly in leveraging remote sensing data for yield prediction. To the best of our knowledge, this is the first study that investigates the use of hyperspectral and LiDAR UAV time series data for explaining/interpreting plant growth stages within deep learning networks and forecasting plot-level maize grain yield using late fusion modalities with attention mechanisms.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Deeply learning deep inelastic scattering kinematics

We study the use of deep learning techniques to reconstruct the kinematics of the neutral current deep inelastic scattering (DIS) process in electron–proton collisions. In particular, we use simulated data from the ZEUS experiment at the HERA accelerator facility, and train deep neural networks to reconstruct the kinematic variables Q 2 and x. Our approach is based on the information used in the classical construction methods, the measurements of the scattered lepton, and the hadronic final state in the detector, but is enhanced through correlations and patterns revealed with the simulated data sets. We show that, with the appropriate selection of a training set, the neural networks sufficiently surpass all classical reconstruction methods on most of the kinematic range considered. Rapid access to large samples of simulated data and the ability of neural networks to effectively extract information from large data sets, both suggest that deep learning techniques to reconstruct DIS kinematics can serve as a rigorous method to combine and outperform the classical reconstruction methods.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2020

Geothermal Deep Direct Use for Turbine Inlet Cooling in East Texas

The National Renewable Energy Laboratory (NREL), the Southern Methodist University Geothermal Laboratory (SMU), Eastman Chemical (Longview, TX), and TAS (Houston, TX) evaluated the feasibility of using geothermal heat to improve the performance of a natural-gas power plant in East Texas. The area of interest is the Eastman Chemical plant in Longview, Texas, which is on the northwestern margin of a geologic region known as the Sabine Uplift. The feasibility study focused on determining the potential for accessing a subsurface hot-water geothermal resource within a 10-km radius of the site to provide thermal energy for absorption chillers. Wells within a 20-km radius are included for broader geological comparison to determine the heat flow, temperature-at-depth, field porosity and permeability. The lithologies of most interest are the Lower Cretaceous Trinity Group and Upper Jurassic Cotton Valley Group. The deeper Cotton Valley formations are hotter (averaging 117 to 130°C), yet permeability and porosity are low. The shallower Trinity Group contains more variability in permeability and porosity and lower temperatures averaging about 98 to 117°C. The shallower formations are considered despite the lower temperature because of increased ability to produce larger volumes of water and extract enough heat before reinjection. The complete SMU analysis is available in the National Geothermal Data System (NGDS). Tapping such deep geothermal sources for direct heating (as opposed to power generation) is known as geothermal deep direct use (DDU). Geothermal DDU has potential across a wide swath of the United States but is underutilized due to challenging project economics associated with developing a deep geothermal resource for what are typically small-scale, variable-demand projects. This project examines the feasibility of geothermal energy integration in a natural-gas combined cycle power station in East Texas. The DDU resource is tapped to drive absorption chillers (24/7) for production of chilled water at 5-10°C (41-50°F). This chilled water is stored until needed, which allows for continuous operation with a relatively small-capacity geothermal/absorption chiller system. When conditions are favorable, the chilled water is dispatched to cool the air entering the compressor stage of a gas combustion turbine. This process, known as turbine inlet cooling (TIC), boosts power production during periods of high temperature and high-power demand. Such systems can enhance grid reliability and reduce the cost for peak-demand power. A simulation model of the power plant was developed in IPSEpro software and validated against operational data from the plant. This model allowed the team to estimate the additional power that could be produced by applying TIC under different operating and ambient conditions. Absorption chiller performance was estimated from vendor sources to determine the production rate of chilled water from the geothermal resource. Geothermal drilling and development costs were estimated using NREL's GEOPHIRES 2.0. The expected lower drilling costs in this region led to an estimated cost of geothermal heat of about $4/MMBtu (1.4 cents/kWh t ). The estimated cost for the absorption chillers and TIC hardware were obtained from literature sources and project partners. Hourly data were obtained for weather, natural gas and electricity prices, and plant operating state for 2017, which served as a representative year. NREL estimated the capital cost, operating cost, and additional electricity production and revenue for different combinations of geothermal capacity, chiller capacity, and water storage-tank size. The analysis drove toward smaller geothermal and chiller systems to reduce equipment cost. A relatively low-cost water storage tank accumulated the near-continuous chilled water output for later use when TIC was most valued.

15 GEOTHERMAL ENERGY↗
DOE OSTI2016

The grism lens-amplified survey from space (glass). VI. Comparing the mass and light in MACS J0416.1-2403 using frontier field imaging and glass spectroscopy

We present a model using both strong and weak gravitational lensing of the galaxy cluster MACS J0416.1-2403, constrained using spectroscopy from the Grism Lens-Amplified Survey from Space (GLASS) and Hubble Frontier Fields (HFF) imaging data. We search for emission lines in known multiply imaged sources in the GLASS spectra, obtaining secure spectroscopic redshifts of 30 multiple images belonging to 15 distinct source galaxies. The GLASS spectra provide the first spectroscopic measurements for five of the source galaxies. The weak lensing signal is acquired from 884 galaxies in the F606W HFF image. By combining the weak lensing constraints with 15 multiple image systems with spectroscopic redshifts and nine multiple image systems with photometric redshifts, we reconstruct the gravitational potential of the cluster on an adaptive grid. The resulting map of total mass density is compared with a map of stellar mass density obtained from the deep Spitzer Frontier Fields imaging data to study the relative distribution of stellar and total mass in the cluster. We find that the projected stellar mass to total mass ratio, f {sub ⋆}, varies considerably with the stellar surface mass density. The mean projected stellar mass to total mass ratio is 〈f{sub ⋆}〉=0.009±0.003 (stat.), but with a systematic error as large as 0.004–0.005, dominated by the choice of the initial mass function. We find agreement with several recent measurements of f {sub ⋆} in massive cluster environments. The lensing maps of convergence, shear, and magnification are made available to the broader community in the standard HFF format.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2024

Transfer learning for metamaterial design and simulation

Abstract We demonstrate transfer learning as a tool to improve the efficacy of training deep learning models based on residual neural networks (ResNets). Specifically, we examine its use for study of multi-scale electrically large metasurface arrays under open boundary conditions in electromagnetic metamaterials. Our aim is to assess the efficiency of transfer learning across a range of problem domains that vary in their resemblance to the original base problem for which the ResNet model was initially trained. We use a quasi-analytical discrete dipole approximation (DDA) method to simulate electrically large metasurface arrays to obtain ground truth data for training and testing of our deep neural network. Our approach can save significant time for examining novel metasurface designs by harnessing the power of transfer learning, as it effectively mitigates the pervasive data bottleneck issue commonly encountered in deep learning. We demonstrate that for the best case when the transfer task is sufficiently similar to the target task, a new task can be effectively trained using only a few data points yet still achieve a test mean absolute relative error of 3 % with a pre-trained neural network, realizing data reduction by a factor of 1000.

Peng, Rixi↗
NASA NTRS2013

Enhanced Deep Blue Aerosol Retrieval Algorithm: The Second Generation

The aerosol products retrieved using the MODIS collection 5.1 Deep Blue algorithm have provided useful information about aerosol properties over bright-reflecting land surfaces, such as desert, semi-arid, and urban regions. However, many components of the C5.1 retrieval algorithm needed to be improved; for example, the use of a static surface database to estimate surface reflectances. This is particularly important over regions of mixed vegetated and non- vegetated surfaces, which may undergo strong seasonal changes in land cover. In order to address this issue, we develop a hybrid approach, which takes advantage of the combination of pre-calculated surface reflectance database and normalized difference vegetation index in determining the surface reflectance for aerosol retrievals. As a result, the spatial coverage of aerosol data generated by the enhanced Deep Blue algorithm has been extended from the arid and semi-arid regions to the entire land areas.

Deep Blue↗
DOE OSTI2018

A Deep End-to-End Model for Transient Stability Assessment With PMU Data

Accurate transient stability assessment (TSA) is a fundamental requirement for ensuring secure and stable operation of power systems. Tremendous efforts have been made to apply artificial intelligence approaches for TSA with phasor measurement unit data. However, many previous approaches may be failed to provide favorable accuracy due to the shallow architectures and error-prone hand-crafting features. This paper proposed a model for TSA, which is termed multi-branch stacked denoising autoencoder (MSDAE). This model is a unified framework integrating multiple stacked denoising autoencoders (SDAEs), one fusion layer, and one logistic regression (LR) layer. Initially, the SDAEs at the bottom of MSDAE extract features from multiple kinds of measurements respectively. Then, the extracted features are encoded into unified fusion features by the fusion layer. Finally, the LR layer performs TSA by using the fusion features. The depth of the architecture contributes to the remarkable ability for feature learning, while the width of the architecture (i.e., the multiple branches) enables MSDAE to deal with different kinds of measurements by a reasonable mechanism. In this way, MSDAE achieves feature extraction and classification intrinsically and simultaneously, namely, achieves TSA in an end-to-end manner. The results of experiments on IEEE 50-machine system demonstrate the superiority of the proposed model over the prior methods.

42 ENGINEERING↗
NASA NTRS1986

Communicating from the edge of the solar system

Communication technology for deep-space scientific missions is surveyed, with a focus on systems being developed for Galileo, a NASA orbiter/probe mission to Jupiter. The problems faced in designing the links from the probe (descending into the Jovian atmosphere) to the orbiter and from the orbiter to earth are examined; the technological solutions adopted for Galileo are discussed; the expansion of the Deep Space Network for the mission is described; the advantages and limitations of cm-band communication systems being considered to meet the data-rate requirements of future deep-space missions are outlined; and the potential of optical communication for the 21st century is indicated. Also included are tables listing past and planned deep-space missions and a brief description of the use of spacecraft radio signals by radio and planetary scientists to probe solar-system plasmas and gravitational fields.

Posner, E. C.↗
NASA NTRS2006

Exponential Sum Absorption Coefficients of Phosphine from 2750 to 3550/cm for Application to Radiative Transfer Analyses on Jupiter and Saturn

PH3 exponential sum k coefficients were computed between 2750 and 3550/cm (2.82-3.64 (microns), in view of future application to radiative transfer analyses of Jupiter and Saturn in a phosphine absorption band near 3 microns. The temperature and pressure of this data set cover the ranges from 80 to 350 K and from 10 (exp -3)to 10(exp 1) bars, respectively. Transmission uncertainty incurred by the use of the k coefficients is smaller than a few percent as long as the radiation is confined above an altitude of a few bars in the giant planets. In spectral regions of weak absorption at high pressures close to 10 bars, contributions from far wings of strong absorption lines must be carefully taken into account. Our data set helps map the three-dimensional distribution of PH3 on the giant planets, revealing their global atmospheric dynamics extending down to the deep interior. The complete k coefficient data set of this work is available at the Web site of the NASA Planetary Data System Atmospheres Node.

phosphine↗