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 487 records · Page 27
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Evaluating Modern GPU Interconnect: PCIe, NVLink, NV-SLI, NVSwitch and GPUDirect

High performance multi-GPU computing becomes an inevitable trend due to the ever-increasing demand on computation capability in emerging domains such as deep learning, big data and planet-scale simulations. However, the lack of deep understanding on how modern GPUs can be connected and the real impact of state-of-the-art interconnect technology on multi-GPU application performance become a hurdle. In this paper, we fill the gap by conducting a thorough evaluation on five latest types of modern GPU interconnects: PCIe, NVLink-V1, NVLink-V2, NVLink-SLI and NVSwitch, from six high-end servers and HPC platforms: NVIDIA P100-DGX-1, V100-DGX-1, DGX-2, OLCF’s SummitDev and Summit supercomputers, as well as an SLI-linked system with two NVIDIA Turing RTX-2080 GPUs. Based on the empirical evaluation, we have observed four new types of GPU communication network NUMA effects: three are triggered by NVLink’s topology, connectivity and routing, while one is caused by PCIe chipset design issue. These observations indicate that, for a multi-GPU application running in a multi-GPU node, choosing the right GPU combination can impose considerable impact on GPU communication efficiency, as well as an application’s overall performance. Our evaluation can be leveraged in building practical multi-GPU performance models, which are vital for GPU task allocation, scheduling and migration in a shared environment (e.g., AI cloud and HPC centers), as well as communication-oriented performance tuning.

Performance Evaluation, GPU, Interconnect, NUMA, P↗
DOE OSTI2020

Predictive Skill of Deep Learning Models Trained on Limited Sequence Data

In this report we investigate the utility of one-dimensional convolutional neural network (CNN) models in epidemiological forecasting. Deep learning models, especially variants of recurrent neural networks (RNNs) have been studied for influenza forecasting, and have achieved higher forecasting skill compared to conventional models such as ARIMA models. In this study, we adapt two neural networks that employ one-dimensional temporal convolutional layers as a primary building block temporal convolutional networks and simple neural attentive meta-learner for epidemiological forecasting and test them with influenza data from the US collected over 2010-2019. We find that epidemiological forecasting with CNNs is feasible, and their forecasting skill is comparable to, and at times, superior to, RNNs. Thus CNNs and RNNs bring the power of nonlinear transformations to purely data-driven epidemiological models, a capability that heretofore has been limited to more elaborate mechanistic/compartmental disease models.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2021

A physics-informed and hierarchically regularized data-driven model for predicting fluid flow through porous media

This paper presents a new deep learning data-driven model for predicting structure dependent pore-fluid velocity fields in rock. The model is based on a Convolutional Auto-Encoder (CAE) artificial neural network capable of learning from image data generated by direct numerical simulations of fluid flow through pore-structures, such as by Lattice Boltzmann or molecular dynamics methods. The main novelty of the model in comparison to previous CAE-based data-driven approaches consists of three parts. The first is a methodology for decomposing the full-domain of the porous media into sub-regions, or “sub-domains”, in order to reduce the overall size of the CAE, batch process the sub-domains in parallel, and enable the CAE to learn local and generalizable nonlinear mappings of pore-fluid velocities. The second consists of embedding the finite difference solutions of the incompressible Navier-Stokes and continuity equations into convolutional layers prior to the CAE in order to provide the CAE with knowledge of fluid dynamics physics (PhyFlow). The third main novelty is that the training of the CAE is regularized with a hierarchical loss function that encourages the learning of fluid flow patterns (in a way similar to ranked modes in principal component analysis), ranking from most to least important. This is shown to increase the stability in learning, reduce over-fitting, and promote interpretability of the CAE neural network layers (HierCAE). The comprehensive new data-driven model, which we call the PhyFlow-HierCAE model, is shown to exhibit improved accuracy and generalizability of flow field predictions over conventional CAE models, attributable to the embedded physical knowledge and the hierarchical regularization, as well as realize orders of magnitude speed-ups in computation times as a surrogate for the direct numerical simulations. Examples of training and forward predictions on unseen pore-structures are provided and evaluated for data from Lattice Boltzmann and molecular dynamics simulations of pore-fluid flow. The model is shown to be a fast and accurate emulator (or “surrogate”) for predicting effective permeability of unseen pore-structures based on learning from relatively small direct numerical simulation datasets.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2021

Deep Learning Based Approach to Integrate MyShake's Trigger Data with ShakeAlert for Faster and Robust EEW Alerts

Earthquake Early Warning (EEW) systems depend on the dense seismic network to make fast and accurate earthquake detections to issue useful early alerts. The recent development and implementation of the ShakeAlert system is relying on the west coast seismic network to detect and estimate the earthquake parameters in real-time. While working on making improvements on the current system, one potential approach is to include more seismic recordings from various sources, such as the low-cost smartphone seismic network, such as the MyShake network, or the Google Android smartphones, since these smartphone seismic networks have much more portable stations (phones) to potentially provide useful data to the system. This report summarizes the initial exploration of using a deep learning approach to combine the data from both traditional seismic stations and the smartphone data in California. Due to the heterogeneity nature of the data, we aggregate data from the phones (using simulation data), as well as that from traditional seismic stations to grid cells. By generating real-time triggering ratio grid cell maps, the designed deep learning algorithm can process the data from multiple sources and detect the earthquake faster than only using that from a traditional seismic network.

58 GEOSCIENCES↗
DOE OSTI2017

UVUDF: UV Luminosity Functions at the Cosmic High Noon

We present the rest-1500 Å UV luminosity functions (LF) for star-forming galaxies during the cosmic high noon—the peak of cosmic star formation rate at 1.5<z<3. We use deep NUV imaging data obtained as part of the Hubble Ultra-Violet Ultra Deep Field (UVUDF) program, along with existing deep optical and NIR coverage on the HUDF. We select F225W, F275W, and F336W dropout samples using the Lyman break technique, along with samples in the corresponding redshift ranges selected using photometric redshifts, and measure the rest-frame UV LF at z∼1.7,2.2,3.0, respectively, using the modified maximum likelihood estimator. We perform simulations to quantify the survey and sample incompleteness for the UVUDF samples to correct the effective volume calculations for the LF. We select galaxies down to M{sub UV}=−15.9,−16.3,−16.8 and fit a faint-end slope of α=−1.20{sub −0.13}{sup +0.10},−1.32{sub −0.14}{sup +0.10},−1.39{sub −0.12}{sup +0.08} at 1.4<z<1.9, 1.8<z<2.6, and 2.4<z<3.6, respectively. We compare the star formation properties of z∼2 galaxies from these UV observations with results from Hα and UV+IR observations. We find a lack of high-SFR sources in the UV LF compared to the Hα and UV+IR, likely due to dusty SFGs not being properly accounted for by the generic IRX--β relation used to correct for dust. We compute a volume-averaged UV-to-Hα ratio by abundance matching the rest-frame UV LF and Hα LF. We find an increasing UV-to-Hα ratio toward low-mass galaxies (M{sub ⋆}≲5×10{sup 9} M{sub ⊙}). We conclude that this could be due to a larger contribution from starbursting galaxies compared to the high-mass end.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRS1994

Cosmic ray transverse gradient for a Hale cycle

We have used neutron monitor data obtained at Deep River and Huancayo as well as the vertical underground telescope data obtained at Embudo to compute the cosmic ray transverse gradient (G(sub theta)) for the 1965 to 1990 period. The computed mean value of G(sub theta) for a given qA epoch, changes sign with the change in the solar magnetic polairty in accordance with the predictions of some contemporary hypotheses. Also, we find that the magnitude of G(sub theta) undergoes a significant time variation during a given polarity epoch. It has the largest value near the solar polar field reversal epoch boundaries, when magnetic polarity in the solar northern hemisphere is positive (qA greater than O). For each of the three solar polar field reversals, the change in the magnitude of G(sub theta) is steeper across the epoch boundaries. There is a good correlation between G(sub theta) and the tilt angle of the helisopheric neutral current sheet (HNCS). Our results are in agreement with the reported piecemeal measurements of the latitudinal gradient made by spacecrafts, at different times, at lower primary energies, at far off distances from Earth's orbit. As such, their global significace is appreciable. Even so, it is not clear yet how these findings reflect upon the drift hypothesis in its present form. However, they do affirm the important role played by the tilt angle of HNCS in the modulation processes.

Ahluwalia, H. S.↗
DOE OSTI2023

The disCO2ver Platform: Curating Data and Tools for Geologic Carbon Sequestration and Deep Subsurface Research Systems

The U.S. DOE National Energy Technology Laboratory has invested 12+ years of development into the data repository and digital laboratory, the Energy Data eXchange (EDX, edx.netl.doe.gov). Supporting a variety of research areas across the DOE Office of Fossil Energy and Carbon Management, the platform has successfully curated and preserved thousands of data products from DOE research. The Carbon Storage Program has successfully supported data curation, upload, and publishing of data products on EDX for many years, demonstrating a success story of how resources like EDX can effectively help with long term preservation and publishing of DOE data products. EDX continues to shift towards cloud-supported infrastructure, taking a hybrid approach combining on-premises compute and storage integrated with cloud-hosted services. The integration of cloud compute and hybrid architecture enables the development of EDX-hosted platforms that tailor the data and tools hosted on them to a specific community, enables implementation of machine learning tools for data discovery and filtering, and enables the hosting of virtual (online user interface) tools. Geologic carbon sequestration (GCS) research continues to scale up in response to the current administration goals to reduce greenhouse gas emissions and transition the energy economy. Over the last year, EDX’s disCO2ver platform has been developed in response to the need for access to data products and tools to support the scaling up of GCS research. disCO2ver provides access to data resources and tools, produced by DOE and outside authoritative external resources. The platform also provides a user-access control component for the virtualization and cloud hosting of tools. Tools that need to be virtualized, to eliminate the need for users to download the tool and use local compute resources, is essential to supporting big-data analysis and machine learning that is becoming common place in carbon storage modeling, risk analysis, and data publishing practices. This talk will review the EDX’s disCO2ver platform and the current work ongoing to curate data and tools to support GCS and deep subsurface systems research.

Morkner, Paige↗
DOE OSTI2024

Deep Learning for Fish Identification from Sonar Data (CRADA 481 Final Report)

In eastern regions of the United States, the American eel is a species of management and regulatory concern because of significant population declines, despite the species’ previous abundance in all tributaries of rivers flowing into the Atlantic Ocean. The American eel is also a candidate for listing under the U.S. Endangered Species Act. While hydropower construction and operation are only one of several factors contributing to this population decline, such a listing could impose additional regulatory challenges for a large number of hydropower projects. In this CRADA project, we improved technologies for identifying migrating eels with the goal of reducing the cost and time required for future American eel hydropower impact assessment and mitigation studies, while maintaining accuracy. We built on results from a previous FOA project (FOA# DE-FOA-0001662), led by the Electric Power Research Institute (EPRI), which developed a highly accurate, deep-learning method for identifying migrating eels from imaging sonar data. The current study aimed to further optimize this deep-learning model, originally designed for image classification, and to develop an object detection software capable of identifying fish from sonar videos in real time, enabling the detection of events like fish migrations and specific species, such as the American eel, at hydropower dams. The data conversion algorithms were packaged as software with a graphical user interface, and the software is evaluated by external collaborators. We focused on the American eel in this project and explored the transferability of the developed deep learning models to the sea lamprey, given the similar body shape and swimming behavior between the two species.

13 HYDRO ENERGY↗
NASA NTRS2022

GNSS-RO Deep Refraction Signals from Moist Marine Atmospheric Boundary Layer (MABL)

The marine atmospheric boundary layer (MABL) has a profound impact on sensible heat and moisture exchanges between the surface and the free troposphere. The goal of this study is to develop an alternative technique for retrieving MABL-specific humidity (q) using GNSS-RO data in deep-refracted signals. The GNSS-RO signal amplitude (i.e., signal-to-noise ratio or SNR) at the deep straight-line height (H(SL)) was been found to be strongly impacted by water vapor within the MABL. This study presents a statistical analysis to empirically relate the normalized SNR (S(RO)) at deep HSL to the MABL q at 950 hPa (~400 m). When compared to the ERA5 reanalysis data, a good linear q–S(RO) relationship is found with the deep H(SL) S(RO) data, but careful treatments of receiver noise, SNR normalization, and receiver orbital altitude are required. We attribute the good q–S(RO) correlation to the strong refraction from a uniform, horizontally stratiform and dynamically quiet MABL water vapor layer. Ducting and diffraction/interference by this layer help to enhance the S(RO) amplitude at deep H(SL). Potential MABL water vapor retrieval can be further developed to take advantage of a higher number of S(RO) measurements in the MABL compared to the Level-2 products. A better sampled diurnal variation of the MABL q is demonstrated with the S(RO) data over the Southeast Pacific (SEP) and the Northeast Pacific (NEP) regions, which appear to be consistent with the low cloud amount variations reported in previous studies.

diurnal variation↗
DOE OSTI2018

Deep CFHT Y-band Imaging of VVDS-F22 Field. II. Quasar Selection and Quasar Luminosity Function

We report the results of a faint quasar survey in a one-square-degree field. The aim is to test the Y−K/g−z and J−K/i−Y color selection criteria for quasars at faint magnitudes to obtain a complete sample of quasars based on deep optical and near-infrared color–color selection and to measure the faint end of the quasar luminosity function (QLF) over a wide redshift range. We carried out a quasar survey based on the Y−K/g−z and J−K/i−Y quasar selection criteria, using the deep Y-band data obtained from our CFHT/WIRCam Y-band images in a two-degree field within the F22 field of the VIMOS VLT deep survey, optical co-added data from Sloan Digital Sky Survey Stripe 82 and deep near-infrared data from the UKIDSS Deep Extragalactic Survey in the same field. We discovered 25 new quasars at 0.5 2.5.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2024

Deep Learning-based Parameterization of Complex 3D CO2 Saturation Data in Large-scale Geological Carbon Storage

In deep learning (DL), dimension reduction plays a pivotal role in improving training efficiency and minimizing overfitting, especially when working with complex datasets like three-dimensional (3D) saturation data. In the context of geological carbon storage (GCS), 3D saturation data introduces unique challenges due to its sparse nature and sharp transitions at plume boundaries, known as shock fronts. To tackle these challenges, we developed a novel DL framework that combines dimension reduction with advanced 3D reconstruction techniques. Our approach utilizes latent variables derived from 2D average saturation fields to efficiently capture the essential features of high-dimensional data while reducing the number of variables. This enhances both the robustness and accuracy of DL models, making the framework more practical for real-world applications. By offering a tailored solution for modeling complex 3D saturation dynamics, this framework holds significant potential for environmental monitoring, energy storage, and other geological applications.

Wang, Hongsheng [University of Texas at Austin]↗
DOE OSTI2022

Deep structural clustering for single-cell RNA-seq data jointly through autoencoder and graph neural network

Abstract Single-cell RNA sequencing (scRNA-seq) permits researchers to study the complex mechanisms of cell heterogeneity and diversity. Unsupervised clustering is of central importance for the analysis of the scRNA-seq data, as it can be used to identify putative cell types. However, due to noise impacts, high dimensionality and pervasive dropout events, clustering analysis of scRNA-seq data remains a computational challenge. Here, we propose a new deep structural clustering method for scRNA-seq data, named scDSC, which integrate the structural information into deep clustering of single cells. The proposed scDSC consists of a Zero-Inflated Negative Binomial (ZINB) model-based autoencoder, a graph neural network (GNN) module and a mutual-supervised module. To learn the data representation from the sparse and zero-inflated scRNA-seq data, we add a ZINB model to the basic autoencoder. The GNN module is introduced to capture the structural information among cells. By joining the ZINB-based autoencoder with the GNN module, the model transfers the data representation learned by autoencoder to the corresponding GNN layer. Furthermore, we adopt a mutual supervised strategy to unify these two different deep neural architectures and to guide the clustering task. Extensive experimental results on six real scRNA-seq datasets demonstrate that scDSC outperforms state-of-the-art methods in terms of clustering accuracy and scalability. Our method scDSC is implemented in Python using the Pytorch machine-learning library, and it is freely available at https://github.com/DHUDBlab/scDSC.

Gan, Yanglan↗
DOE OSTI2019

Data-Driven Day-Ahead PV Estimation Using Hybrid Deep Learning

Ongoing smart grid activities and associated automation resulted in rich set of data. Here, these data can be utilized for monitoring and estimation of real time photovoltaic (PV) generation. Inherent variability in PV and related impact on power systems is a challenging problem. Improving the accuracy of PV generation estimation is beneficial for both the PV owners and the grid operators. Recently, deep learning algorithms possible by the availability of data have shown its advantages for time series estimation; however, its application on PV generation estimation is still in the early stage. In this paper, a hybrid estimation model with a combination of long-short-term-memory network (LSTM) and persistence model (PM) is developed to provide day-ahead PV estimation at 15-minute time interval with high accuracy and robustness. Simulation results show the superior performance of the proposed method over existing methods for most of the test cases.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2020

Hawthorne Nevada Deep Direct-Use Feasibility Study - Data Used for Geothermal Resource Conceptual Modeling and Power Capacity Estimates

This data submission includes several data components that were used to develop a conceptual model and power capacity-estimates of two low-temperature geothermal resources that define geothermal prospect A at Hawthorne, Nevada. Data are sourced from a combination of legacy publicly-available data and more recent data acquisition conducted by the US Navy Geothermal Program Office (2008-2013) and the Great Basin Center for Geothermal Energy at the University of Nevada, Reno (2008-2010). Data sets include compiled fluid geochemistry data, down-hole temperature logs for wells in the vicinity of prospect A, 2 meter temperature survey data, temperature-spinner logs acquired in well HWAAD-2A, fracture picks from image log data acquired in wells HWAAD-2 and HWAAD-3, and X-Ray Diffraction (XRD) analyses on cuttings from wells HWAAD-2A and HWAAD-3. These data have been reviewed for errors and inconsistencies, but it is possible that few errors could still remain. The resource conceptual model and power capacity estimates are included in the final report to the US Department of Energy, and are presented in a manuscript by Ayling and Hinz. A link to the manuscript published in Geothermics is linked below in this submission.

15 GEOTHERMAL ENERGY↗
DOE OSTI2022

Deep Learning categorization of infrasound array data

An analyst review created a labelled catalog of pseudo-ground truth data with almost 9,000 examples spanning four categories: transient signals, persistent signals, signals from moving sources, and noise.

42 ENGINEERING↗