Search NASA⌕ Search

SEARCH · Search NASA

Results for “deep”

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 73 records · Page 4
All sourcesNASA NTRSDOE OSTI
DOE OSTI2019

Bandgap prediction by deep learning in configurationally hybridized graphene and boron nitride

Abstract It is well-known that the atomic-scale and nano-scale configuration of dopants can play a crucial role in determining the electronic properties of materials. However, predicting such effects is challenging due to the large range of atomic configurations that are possible. Here, we present a case study of how deep learning algorithms can enable bandgap prediction in hybridized boron–nitrogen graphene with arbitrary supercell configurations. A material descriptor that enables correlation of structure and bandgap was developed for convolutional neural networks. Bandgaps calculated by ab initio calculations, and corresponding structures, were used as training datasets. The trained networks were then used to predict bandgaps of systems with various configurations. For 4 × 4 and 5 × 5 supercells they accurately predict bandgaps, with a R 2 of >90% and root-mean-square error of ~0.1 eV. The transfer learning was performed by leveraging data generated from small supercells to improve the prediction accuracy for 6 × 6 supercells. This work will pave a route to future investigation of configurationally hybridized graphene and other 2D materials. Moreover, given the ubiquitous existence of configurations in materials, this work may stimulate interest in applying deep learning algorithms for the configurational design of materials across different length scales.

Dong, Yuan↗
DOE OSTI2021

DeepMerge – II. Building robust deep learning algorithms for merging galaxy identification across domains

In astronomy, neural networks are often trained on simulation data with the prospect of being used on telescope observations. Unfortunately, training a model on simulation data and then applying it to instrument data leads to a substantial and potentially even detrimental decrease in model accuracy on the new target dataset. Simulated and instrument data represent different data domains, and for an algorithm to work in both, domain-invariant learning is necessary. Here we employ domain adaptation techniques— Maximum Mean Discrepancy (MMD) as an additional transfer loss and Domain Adversarial Neural Networks (DANNs)— and demonstrate their viability to extract domain-invariant features within the astronomical context of classifying merging and non-merging galaxies. Additionally, we explore the use of Fisher loss and entropy minimization to enforce better in-domain class discriminability. We show that the addition of each domain adaptation technique improves the performance of a classifier when compared to conventional deep learning algorithms. We demonstrate this on two examples: between two Illustris-1 simulated datasets of distant merging galaxies, and between Illustris-1 simulated data of nearby merging galaxies and observed data from the Sloan Digital Sky Survey. The use of domain adaptation techniques in our experiments leads to an increase of target domain classification accuracy of up to ~20%. With further development, these techniques will allow astronomers to successfully implement neural network models trained on simulation data to efficiently detect and study astrophysical objects in current and future large-scale astronomical surveys.

galaxies: interactions↗
DOE OSTI2023

Deep-Learning Electron Diffractive Imaging

Here, we report the development of deep-learning coherent electron diffractive imaging at subangstrom resolution using convolutional neural networks (CNNs) trained with only simulated data. We experimentally demonstrate this method by applying the trained CNNs to recover the phase images from electron diffraction patterns of twisted hexagonal boron nitride, monolayer graphene, and a gold nanoparticle with comparable quality to those reconstructed by a conventional ptychographic algorithm. Fourier ring correlation between the CNN and ptychographic images indicates the achievement of a resolution in the range of 0.70 and 0.55 Å. We further develop CNNs to recover the probe function from the experimental data. The ability to replace iterative algorithms with CNNs and perform real-time atomic imaging from coherent diffraction patterns is expected to find applications in the physical and biological sciences.

47 OTHER INSTRUMENTATION↗
DOE OSTI2018

DeepHyper: Asynchronous Hyperparameter Search for Deep Neural Networks

Hyperparameters employed by deep learning (DL) methods play a substantial role in the performance and reliability of these methods in practice. Unfortunately, finding performance-optimizing hyperparameter settings is a notoriously difficult task. Hyperparameter search methods typically have limited production-strength implementations or do not target scalability within a highly parallel machine, portability across different machines, experimental comparison between different methods, and tighter integration with workflow systems. In this paper, we present DeepHyper, a Python package that provides a common interface for the implementation and study of scalable hyperparameter search methods. It adopts the Balsam workflow system to hide the complexities of running large numbers of hyperparameter configurations in parallel on high-performance computing (HPC) systems. We implement and study asynchronous model-based search methods that consist of sampling a small number of input hyperparameter configurations and progressively fitting surrogate models over the input-output space until exhausting a user-defined budget of evaluations. We evaluate the efficacy of these methods relative to approaches such as random search, genetic algorithms, Bayesian optimization, and hyperband on DL benchmarks on CPU- and GPU-based HPC systems.

Balaprakash, Prasanna↗
DOE OSTI2019

Deep Learning for Vertex Reconstruction of Neutrino-nucleus Interaction Events with Combined Energy and Time Data

We present a deep learning approach for vertex reconstruction of neutrino-nucleus interaction events, a problem in the domain of high energy physics. In this approach, we combine both energy and timing data that are collected in the MIN-ERvA detector to perform classification and regression tasks. We show that the resulting network achieves higher accuracy than previous results while requiring a smaller model size and less training time. In particular, the proposed model outperforms the state-of-the-art by 4.00% on classification accuracy. For the regression task, our model achieves 0.9919 on the coefficient of determination, higher than the previous work (0.96).

Song, Linghao↗
DOE OSTI2017

Scaling deep learning workloads: NVIDIA DGX-1/Pascal and Intel Knights Landing

Deep Learning (DL) algorithms have become ubiquitous in data analytics. As a result, major computing vendors --- including NVIDIA, Intel, AMD, and IBM --- have architectural road-maps influenced by DL workloads. Furthermore, several vendors have recently advertised new computing products as accelerating large DL workloads. Unfortunately, it is difficult for data scientists to quantify the potential of these different products. This paper provides a performance and power analysis of important DL workloads on two major parallel architectures: NVIDIA DGX-1 (eight Pascal P100 GPUs interconnected with NVLink) and Intel Knights Landing (KNL) CPUs interconnected with Intel Omni-Path or Cray Aries. Our evaluation consists of a cross section of convolutional neural net workloads: CifarNet, AlexNet, GoogLeNet, and ResNet50 topologies using the Cifar10 and ImageNet datasets. The workloads are vendor-optimized for each architecture. Our analysis indicates that although GPUs provide the highest overall performance, the gap can close for some convolutional networks; and the KNL can be competitive in performance/watt. We find that NVLink facilitates scaling efficiency on GPUs. However, its importance is heavily dependent on neural network architecture. Furthermore, for weak-scaling --- sometimes encouraged by restricted GPU memory --- NVLink is less important.

Gawande, Nitin A.↗
DOE OSTI2022

LeTID-Affected Cells from a Utility-Scale Photovoltaic System Characterized by Deep Level Transient Spectroscopy

Photovoltaic modules from a utility-scale field experienced power loss by light- and elevated temperature-induced degradation (LeTID). Samples of one of the affected monocrystalline silicon cells were cored and extracted from the module packaging and encapsulation. One of the cell fragments was processed using a regeneration cycle of applying short-circuit-rated current in forward bias at 85 degrees C for 2 weeks, while the other fragment was kept in its outdoor-degraded LeTID state. Both samples were scribed to form 2-mm diameter isolated areas using a femtosecond-pulse-width laser micromachining system. Both isolated areas contained front grid line segments which were wire bonded to larger contact pads, and the samples were probed in a cryostat linked to a deep-level transient spectroscopy (DLTS) system. Using DLTS, a majority-carrier, hole-trap defect was detected on each sample with an activation energy of 0.42 eV. The LeTID-degraded sample, however, had a larger signal corresponding to a trap density of 1.1x10^13 cm-3, which was about five times larger than the 2.1x10^12 cm-3 trap density of the regenerated sample.

charge carrier lifetime↗
DOE OSTI2023

A Novel Spatial-Temporal Variational Quantum Circuit to Enable Deep Learning on NISQ Devices

Quantum computing presents a promising approach for machine learning with its capability for extremely parallel computation in high-dimension through superposition and entanglement. Despite its potential, existing quantum learning algorithms, such as Variational Quantum Circuits (VQCs), face challenges in handling more complex datasets, particularly those that are not linearly separable. What’s more, it encounters the deployability issue, making the learning models suffer a drastic accuracy drop after deploying them to the actual quantum devices. To overcome these limitations, this paper proposes a novel spatial-temporal design, namely “ST-VQC”, to integrate nonlinearity in quantum learning and improve the robustness of the learning model to noise. Specifically, ST-VQC can extract spatial features via a novel block-based encoding quantum sub-circuit coupled with a layer-wise computation quantum sub-circuit to enable temporal-wise deep learning. Additionally, a SWAP-Free physical circuit design is devised to improve robustness. These designs bring a number of hyperparameters. After a systematic analysis of the design space for each design component, an automated optimization framework is proposed to generate the ST-VQC quantum circuit. The proposed ST-VQC has been evaluated on two IBM quantum processors, ibm-cairo with 27 qubits and ibmq-lima with 7 qubits to assess its effectiveness. The results of the evaluation on the standard dataset for binary classification show that ST-VQC can achieve over 30% accuracy improvement compared with existing VQCs on actual quantum computers. Moreover, on a non-linear synthetic dataset, the STVQC outperforms a linear classifier by 27.9%, while the linear classifier using classical computing outperforms the existing VQC by 15.58%.

Li, Jinyang↗
DOE OSTI2017

A laboratory nanoseismological study on deep-focus earthquake micromechanics

Global earthquake occurring rate displays an exponential decay down to ~300 km and then peaks around 550 to 600 km before terminating abruptly near 700 km. How fractures initiate, nucleate, and propagate at these depths remains one of the greatest puzzles in earth science, as increasing pressure inhibits fracture propagation. We report nanoseismological analysis on high-resolution acoustic emission (AE) records obtained during ruptures triggered by partial transformation from olivine to spinel in Mg 2 GeO 4 , an analog to the dominant mineral (Mg,Fe) 2 SiO 4 olivine in the upper mantle, using state-of-the-art seismological techniques, in the laboratory. AEs’ focal mechanisms, as well as their distribution in both space and time during deformation, are carefully analyzed. Microstructure analysis shows that AEs are produced by the dynamic propagation of shear bands consisting of nanograined spinel. These nanoshear bands have a near constant thickness (~100 nm) but varying lengths and self-organize during deformation. This precursory seismic process leads to ultimate macroscopic failure of the samples. Several source parameters of AE events were extracted from the recorded waveforms, allowing close tracking of event initiation, clustering, and propagation throughout the deformation/transformation process. AEs follow the Gutenberg-Richter statistics with a well-defined b value of 1.5 over three orders of moment magnitudes, suggesting that laboratory failure processes are self-affine. The seismic relation between magnitude and rupture area correctly predicts AE magnitude at millimeter scales. A rupture propagation model based on strain localization theory is proposed. Future numerical analyses may help resolve scaling issues between laboratory AE events and deep-focus earthquakes.

58 GEOSCIENCES↗
DOE OSTI2026

Dependence of Deep Convective Cell Properties on Meteorological and Aerosol Conditions during TRACER

Deep convective cells significantly influence Earth’s energy balance and water cycle. However, their accurate representation in numerical models remains challenging due to their small spatiotemporal scales and limited observational constraints. This study examines over ∼400 deep convective cells near Houston, observed by a dual-polarization C-band radar during the Tracking Aerosol Convection Interactions Experiment (TRACER) intensive observation period (June–September 2022). Cells are categorized by lifetime into short-lived (<40 min), intermediate-lived (40–80 min), and long-lived (80+ min) groups. Long-lived cells were broader (∼13.2 km at 2–4-km height) and deeper (∼11.4 km) than short-lived cells (∼6.4-km width, ∼7.31-km height). Using random forest (RF) modeling and correlation analyses, precipitable water vapor (PWV), 2–6-km lapse rate, 0–8-km bulk shear, and fine aerosol mass concentration (Mass_f) are identified as key predictors of cell lifetime. Higher PWV is associated with significantly longer convective cell lifetimes compared to the low-PWV group, particularly within low 2–6-km temperature lapse rate (LR_26km), moderate-to-higher 0–8-km bulk shear (BS_08km), and low-to-moderate Mass_f environments. RF analysis also identifies low-level (0–2 km) equivalent potential temperature, PWV, Mass_f, and surface latent heat flux as key predictors for cell width and height. Short-lived cells have higher aerosol number concentrations (500–1000-nm size range), linked to onshore wind conditions and marine aerosols; however, their low concentration suggests the sensitivity may reflect associated meteorological regimes rather than a direct aerosol effect. Long-lived cells have higher concentrations of organic and sulfate aerosols, while short-lived cells exhibit higher black carbon concentrations. These results highlight the intricate dependence of convective cell lifetimes and structure on environmental moisture, thermodynamics, wind shear, and aerosol characteristics.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

High power picosecond green and deep ultraviolet generations with an all-fiberized MOPA

We demonstrate high power picosecond green and deep ultraviolet (DUV) lasers based on an all-fiberized master oscillator power amplifier (MOPA). The main power amplifier is fabricated with a highly Yb-doped large mode area (LMA) silicate glass fiber. It delivers 75.2-W laser output at 1029 nm with a pulse repetition rate of 10 MHz and a pulse duration of 70 ps. With a lithium triborate (LBO) crystal, a 43.0-W green output at 514.5 nm has been achieved with a pulse duration of 55 ps. With a caesium lithium borate (CLBO) crystal, a 14.5-W picosecond DUV output at 257 nm has been generated, which is the highest power for the all-fiber based DUV laser, to the best of our knowledge.

Pan, Lei (ORCID:0000000288896117)↗
DOE OSTI2020

Physics-Informed Deep Neural Network Method for Limited Observability State Estimation

The precise knowledge regarding the state of the power grid is important in order to ensure optimal and reliable grid operation. Specifically, knowing the state of the distribution grid becomes increasingly important as more renewable energy sources are connected directly into the distribution network, increasing the fluctuations of the injected power. In this paper, we consider the case when the distribution grid becomes partially observable, due to for example cyber attacks, and the state estimation problem is under-determined. We present a new methodology that leverages a deep neural network (DNN) to estimate the grid state. The standard DNN training method is modified to explicitly incorporate the physical information of the grid topology and line/shunt admittance. We show that our method leads to a superior accuracy of the estimation when compared to the case when no physical information is provided. Finally, we compare the performance of our method to the standard state estimation approach, which is based on the weighted least squares with pseudo-measurements, and show that our method performs significantly better with respect to the estimation accuracy.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2017

Deep Full-sky Coadds from Three Years of WISE and NEOWISE Observations

We have reprocessed over 100 terabytes of single-exposure Wide-field Infrared Survey Explorer ( WISE )/NEOWISE images to create the deepest ever full-sky maps at 3–5 microns. We include all publicly available W1 and W2 imaging—a total of ∼8 million exposures in each band—from ∼37 months of observations spanning 2010 January to 2015 December. Our coadds preserve the native WISE resolution and typically incorporate ∼3× more input frames than those of the AllWISE Atlas stacks. Our coadds are designed to enable deep forced photometry, in particular for the Dark Energy Camera Legacy Survey (DECaLS) and Mayall z-Band Legacy Survey (MzLS), both of which are being used to select targets for the Dark Energy Spectroscopic Instrument. We describe newly introduced processing steps aimed at leveraging added redundancy to remove artifacts, with the intent of facilitating uniform target selection and searches for rare/exotic objects (e.g., high-redshift quasars and distant galaxy clusters). Forced photometry depths achieved with these coadds extend 0.56 (0.46) magnitudes deeper in W1 (W2) than is possible with only pre-hibernation WISE imaging.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRS1982

The Deep Space Network. An instrument for radio navigation of deep space probes

The Deep Space Network (DSN) network configurations used to generate the navigation observables and the basic process of deep space spacecraft navigation, from data generation through flight path determination and correction are described. Special emphasis is placed on the DSN Systems which generate the navigation data: the DSN Tracking and VLBI Systems. In addition, auxiliary navigational support functions are described.

Renzetti, N. A.↗
NASA NTRS1983

The Deep Space Network: A Radio Communications Instrument for Deep Space Exploration

The primary purpose of the Deep Space Network (DSN) is to serve as a communications instrument for deep space exploration, providing communications between the spacecraft and the ground facilities. The uplink communications channel provides instructions or commands to the spacecraft. The downlink communications channel provides command verification and spacecraft engineering and science instrument payload data.

Renzetti, N. A.↗
NASA NTRS1991

Interference prediction for deep space spacecraft from ground stations - Interference to the Galileo deep space spacecraft from the GOMS geostationary network

A technique for predicting the interference power spectral density from a ground station to a spacecraft in deep space is described. The interference prediction throughout the complete mission is simulated, and distance between the ground station and the deep space spacecraft is calculated. A power spectral density from the GOMS satellite network to the Galileo spacecraft receiver is computed using the thermal noise density level at the Galileo spacecraft as the interference criterion. Data obtained indicate that all three GOMS stations cause at least 30 minutes of interference during Galileo earth flyby number one, and two GOMS ground stations cause at least four minutes of interference during Galileo earth flyby number.

Bishop, Dennis F.↗
NASA NTRS2012

Preliminary Results of a U.S. Deep South Warm Season Deep Convective Initiation Modeling Experiment using NASA SPoRT Initialization Datasets for Operational National Weather Service Local Model Runs

The initiation of deep convection during the warm season is a forecast challenge in the relative high instability and low wind shear environment of the U.S. Deep South. Despite improved knowledge of the character of well known mesoscale features such as local sea-, bay- and land-breezes, observations show the evolution of these features fall well short in fully describing the location of first initiates. A joint collaborative modeling effort among the NWS offices in Mobile, AL, and Houston, TX, and NASA s Short-term Prediction Research and Transition (SPoRT) Center was undertaken during the 2012 warm season to examine the impact of certain NASA produced products on the Weather Research and Forecasting Environmental Modeling System. The NASA products were: a 4-km Land Information System data, a 1-km sea surface temperature analysis, and a 4-km greenness vegetation fraction analysis. Similar domains were established over the southeast Texas and Alabama coastlines, each with a 9 km outer grid spacing and a 3 km inner nest spacing. The model was run at each NWS office once per day out to 24 hours from 0600 UTC, using the NCEP Global Forecast System for initial and boundary conditions. Control runs without the NASA products were made at the NASA SPoRT Center. The NCAR Model Evaluation Tools verification package was used to evaluate both the forecast timing and location of the first initiates, with a focus on the impacts of the NASA products on the model forecasts. Select case studies will be presented to highlight the influence of the products.

Medlin, Jeffrey M.↗