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 613 records · Page 34

Developing Confidence in Machine Learning Results

As the field of deep learning has emerged in recent years, the amount of knowledge and expertise that data scientists are expected to absorb and maintain has correspondingly increased. One of the challenges experienced by data scientists working with deep learning models is developing confidence in the accuracy of their approach and the resulting findings. In this study, we conducted semi-structured interviews with data scientists at a National Laboratory to understand the processes that data scientists use when attempting to develop their models and the ways that they gain confidence that the results they obtained were accurate. These interviews were analysed to provide an overview of the techniques currently used when working with machine learning (ML) models and opportunities for collaboration with human factors researchers to develop new tools are identified.

Baweja, Jessica A.↗

Demonstration of object location, classification, and characterization by developed deep learning dust ablation trail analysis code package using plasma jets

Based on deep learning, a Dust Ablation Trail Analysis (DATA) code package is developed to detect dust ablation trails in tokamaks, which is intended to analyze a large amount data of tokamak dusts. To validate and benchmark the DATA code package, 2440 plasma jet images are exploited for the training and test of the deep learning DATA code package, since plasma jets resemble the shape and size of dust ablation clouds in tokamaks. After being trained by 1920 plasma jet images, the DATA code package is able to locate 100% plasma jets, classify plasma jets with the accuracy of >99.9%, and output image skeleton information for classified plasma jets. The DATA code package trained by the plasma jet images is also used to analyze the dust ablation trails captured in the Experimental Advanced Superconducting (EAST) tokamak with the satisfactory performance, further verifying its applicability in the fusion dust ablation investigation. Based on its excellent performance presented here, it is demonstrated that our DATA code package is able to automatically identify and analyze dust ablation trails in tokamaks, which can be used for further detailed investigations, such as the three-dimensional reconstruction of dusts and their ablation trails.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Pathways to a Sustainable Aviation Ecosystem: Flight DNA: An Anonymized Aviation Data Tool and Repository

The National Renewable Energy Laboratory (NREL) has deep experience developing secure, national data repositories, which it augments with analysis, technology and market expertise, high-performance computing, and innovative data visualization. By adapting the architecture of existing mobility databases (i.e., Fleet DNA, the Transportation Secure Data Center, the National Fuel Cell Technology Evaluation Center), NREL can build a powerful aviation data clearinghouse - Flight DNA - that helps stakeholders navigate the web of pitfalls and possibilities generated by new aviation technologies.

aviation↗

A data-independent acquisition-based global phosphoproteomics system enables deep profiling

Phosphoproteomics can provide insights into cellular signaling dynamics. To achieve deep and robust quantitative phosphoproteomics profiling for minute amounts of sample, we here develop a global phosphoproteomics strategy based on data-independent acquisition (DIA) mass spectrometry and hybrid spectral libraries derived from data-dependent acquisition (DDA) and DIA data. Benchmarking the method using 166 synthetic phosphopeptides shows high sensitivity (<0.1 ng), accurate site localization and reproducible quantification (~5% median coefficient of variation). As a proof-of-concept, we use lung cancer cell lines and patient-derived tissue to construct a hybrid phosphoproteome spectral library covering 159,524 phosphopeptides (88,107 phosphosites). Based on this library, our single-shot streamlined DIA workflow quantifies 36,350 phosphosites (19,755 class 1) in cell line samples within two hours. Application to drug-resistant cells and patient-derived lung cancer tissues delineates site-specific phosphorylation events associated with resistance and tumor progression, showing that our workflow enables the characterization of phosphorylation signaling with deep coverage, high sensitivity and low between-run missing values.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Utah FORGE: Stress Logging Data

This spreadsheet consist of data and graphs from deep well 58-32 stress testing from 6900 - 7500 ft depth. Measured stress data were used to correct logging predictions of in situ stress. Stress plots shows pore pressure (measured during the injection testing), the total vertical in situ stress (determined from the density logging) and the total maximum and minimum horizontal stresses. The horizontal stresses were determined from the DSI (Dipole Sonic Imager) and corrected to match the direct measurements.

15 GEOTHERMAL ENERGY↗

Deep Learning Predicts Stress–Strain Relations of Granular Materials Based on Triaxial Testing Data

This study presents an AI-based constitutive modelling framework wherein the prediction model directly learns from triaxial testing data by combining discrete element modelling (DEM) and deep learning. A constitutive learning strategy is proposed based on the generally accepted frame-indifference assumption in constructing material constitutive models. The low-dimensional principal stress-strain sequence pairs, measured from discrete element modelling of triaxial testing, are used to train recurrent neural networks, and then the predicted principal stress sequence is augmented to other high-dimensional or general stress tensor via coordinate transformation. Through detailed hyperparameter investigations, it is found that long short-term memory (LSTM) and gated recurrent unit (GRU) networks have similar prediction performance in constitutive modelling problems, and both satisfactorily predict the stress responses of granular materials subjected to a given unseen strain path. Furthermore, the unique merits and ongoing challenges of data-driven constitutive models for granular materials are discussed.

42 ENGINEERING↗

Big Data Analytics on Fiber-Optical Distributed Acoustic Sensing with Rayleigh Enhancements

his paper presents a technique to use deep neural network on data analysis of distributed acoustic sensing (DAS) system built by phase-sensitive optical time-domain reflectometry (&straightphi;-OTDR) with Rayleigh enhancement. Rayleigh backscattering is enhanced by ultrafast laser direct writing technique that promise the excellent sensitivity. And the use of artificial intelligence (AI) drastically improve the efficiency of data pattern recognition.

Peng, Zhaoqiang↗

Active Pacific meridional overturning circulation (PMOC) during the warm Pliocene

An essential element of modern ocean circulation and climate is the Atlantic meridional overturning circulation (AMOC), which includes deep-water formation in the subarctic North Atlantic. However, a comparable overturning circulation is absent in the Pacific, theworld’s largest ocean,where relatively fresh surface waters inhibitNorth Pacific deep convection. We present complementary measurement and modeling evidence that the warm, ~400–ppmv (parts per million by volume) CO 2 world of the Pliocene supported subarctic North Pacific deep-water formation and a Pacific meridional overturning circulation (PMOC) cell. In Pliocene subarctic North Pacific sediments, we report orbitally paced maxima in calcium carbonate accumulation rate, with accompanying pigment and total organic carbon measurements supporting deep-ocean ventilation-driven preservation as their cause. Together with high accumulation rates of biogenic opal, these findings require vigorous bidirectional communication between surface waters and interior waters down to ~3 km in the western subarctic North Pacific, implying deep convection. Redoxsensitive trace metal data provide further evidence of higher Pliocene deep-ocean ventilation before the 2.73-Ma (million years) transition. This observational analysis is supported by climate modeling results, demonstrating that atmospheric moisture transport changes, in response to the reduced meridional sea surface temperature gradients of the Pliocene, were capable of eroding the halocline, leading to deep-water formation in the western subarctic Pacific and a strong PMOC. This second Northern Hemisphere overturning cell has important implications for heat transport, the ocean/atmosphere cycle of carbon, and potentially the equilibrium response of the Pacific to global warming.

54 ENVIRONMENTAL SCIENCES↗

Secure Data Logging and Processing with Blockchain and Machine Learning (Final Report)

Secure Data Logging and Processing with Blockchain and Machine Learning (ML) research is focused on the development of a platform to securely log and process sensor data in fossil power plants. The platform integrates two emerging technologies, blockchain and ML, and incorporates several innovative mechanisms to ensure the integrity, reliability, and resiliency of power systems. The goal is to protect the power plant from various cyberattacks such as false data injection and denial of service attacks using these technologies. The research goal was enabled by the following Research Project Objectives: 1) Secure authentication and identity verification of sensor nodes, actuators, and other equipment within a network. 2) Development of mechanisms that ensure only data sent by legitimate sensors are accepted and stored in the data repository. 3) Development of data aggregation methodologies using ML / Deep Learning (DL) algorithms to minimize noise / faulty data. 4) Implementation of the blockchain technologies to provide data security using secured IOTA framework & nodes.

20 FOSSIL-FUELED POWER PLANTS↗

Deep Learning Denoising Applied to Regional Distance Seismic Data in Utah

Seismic waveform data are generally contaminated by noise from various sources. Suppressing this noise effectively so that the remaining signal of interest can be successfully exploited remains a fundamental problem for the seismological community. To date, the most common noise suppression methods have been based on frequency filtering. These methods, however, are less effective when the signal of interest and noise share similar frequency bands. Inspired by source separation studies in the field of music information retrieval (Jansson et al., 2017) and a recent study in seismology (Zhu et al., 2019), we implemented a seismic denoising method that uses a trained deep convolutional neural network (CNN) model to decompose an input waveform into a signal of interest and noise. In our approach, the CNN provides a signal mask and a noise mask for an input signal. The short-time Fourier transform (STFT) of the estimated signal is obtained by multiplying the signal mask with the STFT of the input signal. To build and test the denoiser, we used carefully compiled signal and noise datasets of seismograms recorded by the University of Utah Seismograph Stations network. Results of test runs involving more than 9000 constructed waveforms suggest that on average the denoiser improves the signal-to-noise ratios (SNRs) by ~5 db, and that most of the recovered signal waveforms have high similarity with respect to the target waveforms (average correlation coefficient of ~0.80) and suffer little distortion. Application to real data suggests that our denoiser achieves on average a factor of up to ~2-5 improvement in SNR over band-pass filtering and can suppress many types of noise that band-pass filtering cannot. For individual waveforms, the improvement can be as high as ~15 db.

58 GEOSCIENCES↗

Optimization of the deep neural network parameters for generating homogenized fuel assembly data for nodal codes

Homogenized fuel assembly (FA) data is a typical input data for nodal codes. Generating that data, however, could be time-consuming. One of promising ways to mitigate the computational burden of generating macroscopic cross-sections is to use trained artificial neural network (ANN) models for predicting nuclear data. However, there is a challenge to make the model support variable FA geometry. In this work, two most common types of FA were combined in one ANN model. Since there could be multiple ways of converting 2-dimensional FA data into 1-dimensional input vector for ANN, three different approaches of data flattening were evaluated. The input parameters included each fuel pin enrichment, fuel temperature, moderator temperature and boron concentration. The output parameters were 2-group macroscopic cross-sections (XS) and pin power distribution (HFF). A fully connected deep neural network (DNN) model was trained and tested using pre-generated data obtained with lattice physics code STREAM. The results of this study showed no statistically significant difference in the accuracy of XS and HFF generation for all 3 tested input vector orders. This means that fully connected DNN for XS generation demonstrated input sequence invariance. Results of comparing predicted XS data with reference solutions were found sufficiently close considering the reduction of computation time offered by ANN. Mean relative difference (MRD) for all output XS parameters was found below 0.7%, while HFF MRD was found higher compared to XS values, in some cases slightly exceeding 1%, mostly near guide tube locations. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Non-intrusive reduced order modeling of natural convection in porous media using convolutional autoencoders: Comparison with linear subspace techniques

Natural convection in porous media is a highly nonlinear multiphysical problem relevant to many engineering applications (e.g., the process of CO 2 sequestration). Here, we extend and present a non-intrusive reduced order model of natural convection in porous media employing deep convolutional autoencoders for the compression and reconstruction and either radial basis function (RBF) interpolation or artificial neural networks (ANNs) for mapping parameters of partial differential equations (PDEs) on the corresponding nonlinear manifolds. To benchmark our approach, we also describe linear compression and reconstruction processes relying on proper orthogonal decomposition (POD) and ANNs. Further, we present comprehensive comparisons among different models through three benchmark problems. The reduced order models, linear and nonlinear approaches, are much faster than the finite element model, obtaining a maximum speed-up of 7 × 10 6 because our framework is not bound by the Courant–Friedrichs–Lewy condition; hence, it could deliver quantities of interest at any given time contrary to the finite element model. Our model’s accuracy still lies within a relative error of 7% in the worst-case scenario. We illustrate that, in specific settings, the nonlinear approach outperforms its linear counterpart and vice versa. We hypothesize that a visual comparison between principal component analysis (PCA) and t-Distributed Stochastic Neighbor Embedding (t-SNE) could indicate which method will perform better prior to employing any specific compression strategy.

97 MATHEMATICS AND COMPUTING↗

Deep residual networks for crystallography trained on synthetic data

The use of artificial intelligence to process diffraction images is challenged by the need to assemble large and precisely designed training data sets. To address this, a codebase called Resonet was developed for synthesizing diffraction data and training residual neural networks on these data. Here, two per-pattern capabilities of Resonet are demonstrated: (i) interpretation of crystal resolution and (ii) identification of overlapping lattices. Resonet was tested across a compilation of diffraction images from synchrotron experiments and X-ray free-electron laser experiments. Crucially, these models readily execute on graphics processing units and can thus significantly outperform conventional algorithms. While Resonet is currently utilized to provide real-time feedback for macromolecular crystallography users at the Stanford Synchrotron Radiation Lightsource, its simple Python-based interface makes it easy to embed in other processing frameworks. This work highlights the utility of physics-based simulation for training deep neural networks and lays the groundwork for the development of additional models to enhance diffraction collection and analysis.

36 MATERIALS SCIENCE↗

Deep learning-based spatio-temporal estimate of greenhouse gas emissions using satellite data

Accurate estimation of greenhouse gases (GHGs) emissions is very important for developing mitigation strategies to climate change by controlling and reducing GHG emissions. This project aims to develop multiple deep learning approaches to estimate anthropogenic greenhouse gas emissions using multiple types of satellite data. NO2 concentration is chosen as an example of GHGs to evaluate the proposed approach. Two sentinel satellites (sentinel-2 and sentinel-5P) provide multiscale observations of GHGs from 10-60m resolution (sentinel-2) to ~kilometer scale resolution (sentinel-5P). Among multiple deep learning (DL) architectures evaluated, two best DL models demonstrate that key features of spatio-temporal satellite data and additional information (e.g., observation times and/or coordinates of ground stations) can be extracted using convolutional neural networks and feed forward neural networks, respectively. In particular, irregular time series data from different NO 2 observation stations limit the flexibility of long short-term memory architecture, requiring zero-padding to fill in missing data. However, deep neural operator (DNO) architecture can stack time-series data as input, providing the flexibility of input structure without zero-padding. As a result, the DNO outperformed other deep learning architectures to account for time-varying features. Overall, temporal patterns with smooth seasonal variations were predicted very well, while frequent fluctuation patterns were not predicted well. In addition, uncertainty quantification using conformal inference method is performed to account for prediction ranges. Overall, this research will lead to a new groundwork for estimating greenhouse gas concentrations using multiple satellite data to enhance our capability of tracking the cause of climate change and developing mitigation strategies.

54 ENVIRONMENTAL SCIENCES↗

Hydraulic Modeling of Induced and Propagated Fractures: Analysis of Flow and Pressure Data From Hydromechanical Experiments in the COSC-1 Deep Borehole in Crystalline Rock Near Åre, Sweden

To characterize the coupled hydromechanical behavior of rock fractures, the step-rate injection method for fracture in-situ properties (SIMFIP) was conducted with a specialized downhole probe developed by Guglielmi et.al. In June 2019, a field campaign was carried out near Åre, Sweden, where the SIMFIP probe was applied in the Collisional Orogeny in the Scandinavian Caledonides-1 scientific borehole to understand the dynamics of injection-induced fracture initiation, fracture opening, and shearing due to water injection-withdrawal in a borehole interval isolated by two packers. Three intervals were investigated at ~500 m depth: (a) an unfractured section (intact rock), (b) a section with non-conductive fractures, and (c) a section with hydraulically conductive fractures. Pressure, injection flow rate, and borehole wall displacement were simultaneously measured during the tests. In the present study, the geometry of the induced fracture and deformation of existing fractures at different time stages of the tests are determined based on a hydrologic model by using the measured pressure and flow data during each time stage of the experiment. A numerical model for the fluid flow within the fracture and the packed-off borehole interval is implemented within COMSOL Multiphysics. By matching model simulations with observed data for all three sections, estimates of the induced and propagated fractures' radius and aperture at successive time stages have been obtained in each case. We could also determine the non-linear relationship between fracture aperture and pressure for values above fracture opening pressures. The model results provide insights for the understanding of pressure-induced fracture initiation and propagation in crystalline rock.

58 GEOSCIENCES↗

A giant umbrella-like stellar stream around the tidal ring galaxy NGC 922

Tidal ring galaxies (TRGs) are rarely observed in the local universe due to their intrinsically transient nature. The tidal ring structures are the result of strong interactions between gas-rich stellar disks and smaller galactic systems, and do not last longer than ~500 Myr. Therefore, these are perfect scenarios in which to look for the debris of recently accreted dwarf galactic systems. Our goal is to study the low surface brightness stellar structures around the TRG NGC 922 and to revise the hypothesis of its formation in light of these new data. We present new deep images of the TRG NGC 922 and its surroundings from the DESI Legacy survey data and from our observations with an amateur telescope. These observations are compared with results from high-resolution N-body simulations that were designed to reproduce an alternative formation scenario for this peculiar galaxy. Our new observations unveil that the low surface brightness stellar tidal structures around NGC 922 are much more complex than reported in previous works. In particular, the formerly detected tidal spike-like structure at the north-east of the central galaxy disk is not connected with the dwarf companion galaxy PGC 3080368, which has been suggested as the intruder triggering the ring formation of NGC 922. The deep images reveal that this tidal structure mainly has a fainter giant umbrella-like shape, and thus it was formed from the tidal disruption of a different satellite. Using the broad-band g, r, and z DESI LS images, we measured the photometric properties of this stellar stream, estimating a total absolute magnitude in the r band of M r = -17.0 ± 0.03 mag and a total stellar mass for the stream of between 6.9 and 8.5×10 8 M ⊙ . We performed a set of N-body simulations to reproduce the observed NGC922-intruder interaction, suggesting a new scenario for the formation of its tidal ring from the infall of a gas-rich satellite around 150 Myr ago. Finally, our deep images also reveal a tidal shell around the dwarf galaxy PGC 3080368, a possible fossil of a recent merger with a smaller satellite, which may suggest it is in its first infall towards NGC 922.

79 ASTRONOMY AND ASTROPHYSICS↗

Data-driven, Interpretable Photometric Redshifts Trained on Heterogeneous and Unrepresentative Data

We present a new method for inferring photometric redshifts in deep galaxy and quasar surveys, based on a data-driven model of latent spectral energy distributions (SEDs) and a physical model of photometric fluxes as a function of redshift. This conceptually novel approach combines the advantages of both machine learning methods and template fitting methods by building template SEDs directly from the spectroscopic training data. This is made computationally tractable with Gaussian processes operating in flux–redshift space, encoding the physics of redshifts and the projection of galaxy SEDs onto photometric bandpasses. This method alleviates the need to acquire representative training data or to construct detailed galaxy SED models; it requires only that the photometric bandpasses and calibrations be known or have parameterized unknowns. The training data can consist of a combination of spectroscopic and deep many-band photometric data with reliable redshifts, which do not need to entirely spatially overlap with the target survey of interest or even involve the same photometric bands. We showcase the method on the i -magnitude-selected, spectroscopically confirmed galaxies in the COSMOS field. The model is trained on the deepest bands (from SUBARU and HST ) and photometric redshifts are derived using the shallower SDSS optical bands only. We demonstrate that we obtain accurate redshift point estimates and probability distributions despite the training and target sets having very different redshift distributions, noise properties, and even photometric bands. Our model can also be used to predict missing photometric fluxes or to simulate populations of galaxies with realistic fluxes and redshifts, for example.

79 ASTRONOMY AND ASTROPHYSICS↗

Uncertainty due to quark energy loss in determining the nuclear sea quark distribution from nuclear Drell-Yan data

By means of two different parametrizations of quark energy loss and the nuclear parton distributions determined only with lepton-nuclear deep inelastic scattering experimental data, a leading order phenomenological analysis is performed on the nuclear Drell-Yan differential cross section ratios for E772 experimental data. Uncertainty due to the quark energy loss effect is quantified in determining the nuclear sea quark distribution by using nuclear Drell-Yan data. It is found that the quark energy loss effect on nuclear Drell-Yan cross section ratios becomes greater with the increase of quark momentum fraction in the target nuclei. The uncertainty from the quark energy loss becomes bigger as the nucleus A becomes heavier. The Drell-Yan data on proton incident middle and heavy nuclei versus deuterium would result in an overestimate for nuclear modification in the sea quark distribution with neglecting the quark energy loss.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗