SEARCH · Engineering Papers

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 469 records · Page 26

All sources NASA NTRS DOE OSTI

DOE OSTI2022

Survival analysis of localized prostate cancer with deep learning

In recent years, data-driven, deep-learning-based models have shown great promise in medical risk prediction. By utilizing the large-scale Electronic Health Record data found in the U.S. Department of Veterans Affairs, the largest integrated healthcare system in the United States, we have developed an automated, personalized risk prediction model to support the clinical decision-making process for localized prostate cancer patients. This method combines the representative power of deep learning and the analytical interpretability of parametric regression models and can implement both time-dependent and static input data. To collect a comprehensive evaluation of model performances, we calculate time-dependent C-statistics C td over 2-, 5-, and 10-year time horizons using either a composite outcome or prostate cancer mortality as the target event. The composite outcome combines the Prostate-Specific Antigen (PSA) test, metastasis, and prostate cancer mortality. Our longitudinal model Recurrent Deep Survival Machine (RDSM) achieved C td 0.85 (0.83), 0.80 (0.83), and 0.76 (0.81), while the cross-sectional model Deep Survival Machine (DSM) attained C td 0.85 (0.82), 0.80 (0.82), and 0.76 (0.79) for the 2-, 5-, and 10-year composite (mortality) outcomes, respectively. In addition to estimating the survival probability, our method can quantify the uncertainty associated with the prediction. The uncertainty scores show a consistent correlation with the prediction accuracy. We find PSA and prostate cancer stage information are the most important indicators in risk prediction. Our work demonstrates the utility of the data-driven machine learning model in prostate cancer risk prediction, which can play a critical role in the clinical decision system.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2021

Deep ocean metagenomes provide insight into the metabolic architecture of bathypelagic microbial communities

The deep sea, the largest ocean’s compartment, drives planetary-scale biogeochemical cycling. Yet, the functional exploration of its microbial communities lags far behind other environments. Here we analyze 58 metagenomes from tropical and subtropical deep oceans to generate the Malaspina Gene Database. Free-living or particle-attached lifestyles drive functional differences in bathypelagic prokaryotic communities, regardless of their biogeography. Ammonia and CO oxidation pathways are enriched in the free-living microbial communities and dissimilatory nitrate reduction to ammonium and H 2 oxidation pathways in the particle-attached, while the Calvin Benson-Bassham cycle is the most prevalent inorganic carbon fixation pathway in both size fractions. Reconstruction of the Malaspina Deep Metagenome-Assembled Genomes reveals unique non-cyanobacterial diazotrophic bacteria and chemolithoautotrophic prokaryotes. The widespread potential to grow both autotrophically and heterotrophically suggests that mixotrophy is an ecologically relevant trait in the deep ocean. These results expand our understanding of the functional microbial structure and metabolic capabilities of the largest Earth aquatic ecosystem.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2025

Deep Koopman operators for causal discovery

Causal discovery aims to identify cause-effect mechanisms for better scientific understanding, explainable decision-making, and more accurate modeling. Standard statistical frameworks, such as Granger causality, lack the ability to quantify causal relationships in nonlinear dynamics due to the presence of complex feedback mechanisms, timescale mixing, and nonstationarity. Thus, applying these methods to study causal dynamics in real-world systems, such as the Earth, is a major challenge. Addressing this shortcoming, we leverage deep learning and a Koopman operator-theoretic formalism to present a class of causal discovery algorithms. Kausal uses deep Koopman operator methods to approximate nonlinear dynamics in a linearized vector space in which traditional causal inference methods such as Granger causality can be more easily applied. Our idealized experiments demonstrate Kausal’s superior ability in discovering and characterizing causal signals compared to existing deep learning and non-deep learning state-of-the-art approaches. Finally, the successful identification of major El Niño and La Niña events in observations showcases Kausal’s skill to handle real-world applications.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2024

Adding labile carbon to peatland soils triggers deep carbon breakdown

Peatlands store vast amounts of carbon, with deep peat carbon remaining stable due to limited thermodynamic energy and transport. However, climate change-induced increases in labile carbon inputs could destabilize these stores. Here, we combined DNA stable isotope probing with stable isotope-assisted metabolomics employing a multi-platform approach to investigate microbial dynamics driving deep peat carbon degradation upon labile carbon (e.g., glucose) amendment. Our findings highlight the vulnerability of deep peat carbon, as glucose addition triggers the breakdown of older organic matter. By uniquely integrating these techniques, we identified active glucose metabolizers to specific microbial populations and mapped carbon flow through microbial networks, elucidating their role in priming recalcitrant carbon mineralization. This multi-omics approach offers crucial insights into how changing resources reshape the peatland microbiome, enhancing our understanding of deep carbon processing, and refining model parameterization to predict microbial responses and carbon cycle feedbacks under global change pressures.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2021

Accelerating End-to-End Deep Learning for Particle Reconstruction using CMS open data

Machine learning algorithms are gaining ground in high energy physics for applications in particle and event identification, physics analysis, detector reconstruction, simulation and trigger. Currently, most data-analysis tasks at LHC experiments benefit from the use of machine learning. Incorporating these computational tools in the experimental framework presents new challenges. This paper reports on the implementation of the end-to-end deep learning with the CMS software framework and the scaling of the end-to-end deep learning with multiple GPUs. The end-to-end deep learning technique combines deep learning algorithms and low-level detector representation for particle and event identification. We demonstrate the end-to-end implementation on a top quark benchmark and perform studies with various hardware architectures including single and multiple GPUs and Google TPU.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2014

Tunnel-injection quantum dot deep-ultraviolet light-emitting diodes with polarization-induced doping in III-nitride heterostructures

Efficient semiconductor optical emitters in the deep-ultraviolet spectral window are encountering some of the most deep rooted problems of semiconductor physics. In III-Nitride heterostructures, obtaining short-wavelength photon emission requires the use of wide bandgap high Al composition AlGaN active regions. High conductivity electron (n-) and hole (p-) injection layers of even higher bandgaps are necessary for electrical carrier injection. This approach requires the activation of very deep dopants in very wide bandgap semiconductors, which is a difficult task. In this work, an approach is proposed and experimentally demonstrated to counter the challenges. The active region of the heterostructure light emitting diode uses ultrasmall epitaxially grown GaN quantum dots. Remarkably, the optical emission energy from GaN is pushed from 365 nm (3.4 eV, the bulk bandgap) to below 240 nm (>5.2 eV) because of extreme quantum confinement in the dots. This is possible because of the peculiar bandstructure and band alignments in the GaN/AlN system. This active region design crucially enables two further innovations for efficient carrier injection: Tunnel injection of carriers and polarization-induced p-type doping. The combination of these three advances results in major boosts in electroluminescence in deep-ultraviolet light emitting diodes and lays the groundwork for electrically pumped short-wavelength lasers.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DOE OSTI2014

The effects of deep level traps on the electrical properties of semi-insulating CdZnTe

Deep level traps have considerable effects on the electrical properties and radiation detection performance of high resistivity CdZnTe. A deep-trap model for high resistivity CdZnTe was proposed in this paper. The high resistivity mechanism and the electrical properties were analyzed based on this model. High resistivity CdZnTe with high trap ionization energy E{sub t} can withstand high bias voltages. The leakage current is dependent on both the deep traps and the shallow impurities. The performance of a CdZnTe radiation detector will deteriorate at low temperatures, and the way in which sub-bandgap light excitation could improve the low temperature performance can be explained using the deep trap model.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2014

Hydride vapor phase GaN films with reduced density of residual electrons and deep traps

Electrical properties and deep electron and hole traps spectra are compared for undoped n-GaN films grown by hydride vapor phase epitaxy (HVPE) in the regular process (standard HVPE samples) and in HVPE process optimized for decreasing the concentration of residual donor impurities (improved HVPE samples). It is shown that the residual donor density can be reduced by optimization from ∼10{sup 17} cm{sup −3} to (2–5) × 10{sup 14} cm{sup −3}. The density of deep hole traps and deep electron traps decreases with decreased donor density, so that the concentration of deep hole traps in the improved samples is reduced to ∼5 × 10{sup 13} cm{sup −3} versus 2.9 × 10{sup 16} cm{sup −3} in the standard samples, with a similar decrease in the electron traps concentration.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

DOE OSTI2015

A servo controlled gradient loading triaxial model test system for deep-buried cavern

A servo controlled gradient loading model test system is developed to simulate the gradient geostress in deep-buried cavern. This system consists of the gradient loading apparatus, the digital servo control device, and the measurement system. Among them, the gradient loading apparatus is the main component which is used for exerting load onto the model. This loading apparatus is placed inside the counterforce wall/beam and is divided to several different loading zones, with each loading zone independently controlled. This design enables the gradient loading. Hence, the “real” geostress field surrounding the deep-buried cavern can be simulated. The loading or unloading process can be controlled by the human-computer interaction machines, i.e., the digital servo control system. It realizes the automation and visualization of model loading/unloading. In addition, this digital servo could control and regulate hydraulic loading instantaneously, which stabilizes the geostress onto the model over a long term. During the loading procedure, the collision between two adjacent loading platens is also eliminated by developing a guide frame. This collision phenomenon is induced by the volume shrinkage of the model when compressed in true 3D state. In addition, several accurate measurements, including the optical and grating-based method, are adopted to monitor the small deformation of the model. Hence, the distortion of the model could be accurately measured. In order to validate the performance of this innovative model test system, a 3D geomechanical test was conducted on a simulated deep-buried underground reservoir. The result shows that the radial convergence increases rapidly with the release of the stress in the reservoir. Moreover, the deformation increases with the increase of the gas production rate. This observation is consistence with field observation in petroleum engineering. The system is therefore capable of testing deep-buried engineering structures.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2018

Iron and intrinsic deep level states in Ga 2 O 3

In this study, using a combination of deep level transient spectroscopy, secondary ion mass spectrometry, proton irradiation, and hybrid functional calculations, we identify two similar deep levels that are associated with Fe impurities and intrinsic defects in bulk crystals and molecular beam epitaxy and hydride vapor phase epitaxi-grown epilayers of β-Ga 2 O 3 . First, our results indicate that Fe Ga , and not an intrinsic defect, acts as the deep acceptor responsible for the often dominating E2 level at ~0.78 eV below the conduction band minimum. Second, by provoking additional intrinsic defect generation via proton irradiation, we identified the emergence of a new level, labeled as E2*, having the ionization energy very close to that of E2, but exhibiting an order of magnitude larger capture cross section. Importantly, the properties of E2* are found to be consistent with its intrinsic origin. As such, contradictory opinions of a long standing literature debate on either extrinsic or intrinsic origin of the deep acceptor in question converge accounting for possible contributions from E2 and E2* in different experimental conditions.

36 MATERIALS SCIENCE↗

DOE OSTI2019

Deep acceptors and their diffusion in Ga 2 O 3

β–Ga2O 3 is a wide-bandgap material with promising applications in high-power electronics. While n-type doping is straightforward, p-type doping is elusive, with only deep acceptors available. We explore the properties of these acceptors, from the point of view of achieving stable semi-insulating layers, which are essential in many device structures. Using hybrid density functional theory, we obtain the comprehensive first-principles results for a variety of deep-acceptor impurities in Ga 2 O 3 . Among the impurities examined, nitrogen on an oxygen site and magnesium on a gallium site have particularly low formation energies, making them prime candidates for acceptor doping. Closer inspection of various configurations shows that Mg can incorporate not only on Ga sites (where it acts as a deep acceptor under n-type conditions) but also on O sites, where it acts as a deep donor. Mg interstitials adopt a split-interstitial configuration, sharing a site with a host Ga atom. Similarly, N substituting on an O site acts as a compensating center, but N can also incorporate on the Ga site. We evaluate the diffusivities of these species in the crystal by calculating migration barriers and considering which native defects assist in diffusion. We find that diffusion of N is dominantly assisted by O vacancies, while Mg diffusion is assisted by gallium interstitials. Diffusion of Mg proceeds with significantly lower activation energies than diffusion of N. Our results can be used to assess activation energies and diffusion mechanisms for other impurities in Ga 2 O 3 .

36 MATERIALS SCIENCE↗

DOE OSTI2024

Native point defects in HgCdTe infrared detector material: Identifying deep centers from first principles

We investigate the native point defects in the long-wavelength infrared (LWIR) detector material Hg0.75Cd0.25Te using a dielectric-dependent hybrid density functional combined with spin–orbit coupling. Characterizing these point defects is essential as they are responsible for intrinsic doping and nonradiative recombination centers in the detector material. The dielectric-dependent hybrid functional allows for an accurate description of the bandgap (Eg) for Hg1−xCdxTe (MCT) over the entire compositional range, a level of accuracy challenging with standard hybrid functionals. Our comprehensive examination of the native point defects confirms that cation vacancies VHg(Cd) are the primary sources of p-type conductivity in the LWIR material given their low defect formation energies and the presence of a shallow acceptor level (−/0) near the valence-band maximum. In addition to the shallow acceptor level, the cation vacancies exhibit a deep charge transition level (2−/−) situated near the midgap, characteristic of nonradiative recombination centers. Our results indicate that Hg interstitial could also be a deep center in the LWIR MCT through a metastable configuration under the Hg-rich growth conditions. While an isolated Te antisite does not show deep levels, the formation of VHg–TeHg defect complex introduces a deep acceptor level within the bandgap.

Physics↗

DOE OSTI2020

Application of deep neural networks to improve diagnostic accuracy of rheumatoid arthritis using diffuse optical tomography

A set of deep neural network models for rheumatoid arthritis (RA) classification using a highway network, a convolutional neural network and a residual network is proposed based on the data of diffuse optical tomography (DOT) utilising near-infrared light, which ensures early diagnosis of pathophysiological changes resulting from inflammation. A numerical model of the finger is used to generate images to overcome the inherent problem of insufficient clinical DOT images available. The proposed deep neural network models are applied to automatically classify simulated DOT images of inflamed and non-inflamed joints and transfer learning is also used to improve the performance of the classification. The results demonstrate that all three deep neural network methods improve the diagnostic accuracy as compared to the widely applied support vector machine (SVM), especially for high inter-subject variability databases. In cases of distinct modelled severity of disease, residual network achieved the highest accuracy (> 99 %), and both of highway and convolutional neural networks reached 99 %, respectively. However, as the severity of the modelled disease is reduced, this accuracy is reduced to 75.2 % for residual networks. The results indicate that transfer learning can improve the performance of deep neural network methods on RA classification from DOT data and highlight their potential as a computer aided tool in DOT diagnostic systems. (paper)

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2014

A molecular line scan in the Hubble deep field north

We present a molecular line scan in the Hubble Deep Field North (HDF-N) that covers the entire 3 mm window (79-115 GHz) using the IRAM Plateau de Bure Interferometer. Our CO redshift coverage spans z ≲ 0.45, 1 ≲ z ≲ 1.9 and all z ≳ 2. We reach a CO detection limit that is deep enough to detect essentially all z > 1 CO lines reported in the literature so far. We have developed and applied different line-searching algorithms, resulting in the discovery of 17 line candidates. We estimate that the rate of false positive line detections is ∼2/17. We identify optical/NIR counterparts from the deep ancillary database of the HDF-N for seven of these candidates and investigate their available spectral energy distributions. Two secure CO detections in our scan are identified with star-forming galaxies at z = 1.784 and at z = 2.047. These galaxies have colors consistent with the 'BzK' color selection and they show relatively bright CO emission compared with galaxies of similar dust continuum luminosity. We also detect two spectral lines in the submillimeter galaxy HDF 850.1 at z = 5.183. We consider an additional nine line candidates as high quality. Our observations also provide a deep 3 mm continuum map (1σ noise level = 8.6 μJy beam{sup –1}). Via a stacking approach, we find that optical/MIR bright galaxies contribute only to <50% of the star formation rate density at 1 < z < 3, unless high dust temperatures are invoked. The present study represents a first, fundamental step toward an unbiased census of molecular gas in 'normal' galaxies at high-z, a crucial goal of extragalactic astronomy in the ALMA era.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2013

THE 2012 HUBBLE ULTRA DEEP FIELD (UDF12): OBSERVATIONAL OVERVIEW

We present the 2012 Hubble Ultra Deep Field campaign (UDF12), a large 128 orbit Cycle 19 Hubble Space Telescope program aimed at extending previous Wide Field Camera 3 (WFC3)/IR observations of the UDF by quadrupling the exposure time in the F105W filter, imaging in an additional F140W filter, and extending the F160W exposure time by 50%, as well as adding an extremely deep parallel field with the Advanced Camera for Surveys (ACS) in the F814W filter with a total exposure time of 128 orbits. The principal scientific goal of this project is to determine whether galaxies reionized the universe; our observations are designed to provide a robust determination of the star formation density at z ∼> 8, improve measurements of the ultraviolet continuum slope at z ∼ 7-8, facilitate the construction of new samples of z ∼ 9-10 candidates, and enable the detection of sources up to z ∼ 12. For this project we committed to combining these and other WFC3/IR imaging observations of the UDF area into a single homogeneous dataset to provide the deepest near-infrared observations of the sky. In this paper we present the observational overview of the project and describe the procedures used in reducing the data as well as the final products that were produced. We present the details of several special procedures that we implemented to correct calibration issues in the data for both the WFC3/IR observations of the main UDF field and our deep 128 orbit ACS/WFC F814W parallel field image, including treatment for persistence, correction for time-variable sky backgrounds, and astrometric alignment to an accuracy of a few milliarcseconds. We release the full, combined mosaics comprising a single, unified set of mosaics of the UDF, providing the deepest near-infrared blank-field view of the universe currently achievable, reaching magnitudes as deep as AB ∼ 30 mag in the near-infrared, and yielding a legacy dataset on this field.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2023

Deep neural network uncertainty quantification for LArTPC reconstruction

We evaluate uncertainty quantification (UQ) methods for deep learning applied to liquid argon time projection chamber (LArTPC) physics analysis tasks. As deep learning applications enter widespread usage among physics data analysis, neural networks with reliable estimates of prediction uncertainty and robust performance against overconfidence and out-of-distribution (OOD) samples are critical for their full deployment in analyzing experimental data. While numerous UQ methods have been tested on simple datasets, performance evaluations for more complex tasks and datasets are scarce. Here we assess the application of selected deep learning UQ methods on the task of particle classification using the PiLArNet monte carlo 3D LArTPC point cloud dataset. We observe that UQ methods not only allow for better rejection of prediction mistakes and OOD detection, but also generally achieve higher overall accuracy across different task settings. We assess the precision of uncertainty quantification using different evaluation metrics, such as distributional separation of prediction entropy across correctly and incorrectly identified samples, receiver operating characteristic curves (ROCs), and expected calibration error from observed empirical accuracy. We conclude that ensembling methods can obtain well calibrated classification probabilities and generally perform better than other existing methods in deep learning UQ literature.

47 OTHER INSTRUMENTATION↗

DOE OSTI2013

A PILOT FOR A VERY LARGE ARRAY H I DEEP FIELD

High-resolution 21 cm H I deep fields provide spatially and kinematically resolved images of neutral hydrogen at different redshifts, which are key to understanding galaxy evolution across cosmic time and testing predictions of cosmological simulations. Here we present results from a pilot for an H I deep field done with the Karl G. Jansky Very Large Array (VLA). We take advantage of the newly expanded capabilities of the telescope to probe the redshift interval 0 < z < 0.193 in one observation. We observe the COSMOS field for 50 hr, which contains 413 galaxies with optical spectroscopic redshifts in the imaged field of 34' Multiplication-Sign 34' and the observed redshift interval. We have detected neutral hydrogen gas in 33 galaxies in different environments spanning the probed redshift range, including three without a previously known spectroscopic redshift. The detections have a range of H I and stellar masses, indicating the diversity of galaxies we are probing. We discuss the observations, data reduction, results, and highlight interesting detections. We find that the VLA's B-array is the ideal configuration for H I deep fields since its long spacings mitigate radio frequency interference. This pilot shows that the VLA is ready to carry out such a survey, and serves as a test for future H I deep fields planned with other Square Kilometer Array pathfinders.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2021

Improving deep learning-based protein distance prediction in CASP14

Abstract Motivation Accurate prediction of residue–residue distances is important for protein structure prediction. We developed several protein distance predictors based on a deep learning distance prediction method and blindly tested them in the 14th Critical Assessment of Protein Structure Prediction (CASP14). The prediction method uses deep residual neural networks with the channel-wise attention mechanism to classify the distance between every two residues into multiple distance intervals. The input features for the deep learning method include co-evolutionary features as well as other sequence-based features derived from multiple sequence alignments (MSAs). Three alignment methods are used with multiple protein sequence/profile databases to generate MSAs for input feature generation. Based on different configurations and training strategies of the deep learning method, five MULTICOM distance predictors were created to participate in the CASP14 experiment. Results Benchmarked on 37 hard CASP14 domains, the best performing MULTICOM predictor is ranked 5th out of 30 automated CASP14 distance prediction servers in terms of precision of top L/5 long-range contact predictions [i.e. classifying distances between two residues into two categories: in contact (<8 Angstrom) and not in contact otherwise] and performs better than the best CASP13 distance prediction method. The best performing MULTICOM predictor is also ranked 6th among automated server predictors in classifying inter-residue distances into 10 distance intervals defined by CASP14 according to the precision of distance classification. The results show that the quality and depth of MSAs depend on alignment methods and sequence databases and have a significant impact on the accuracy of distance prediction. Using larger training datasets and multiple complementary features improves prediction accuracy. However, the number of effective sequences in MSAs is only a weak indicator of the quality of MSAs and the accuracy of predicted distance maps. In contrast, there is a strong correlation between the accuracy of contact/distance predictions and the average probability of the predicted contacts, which can therefore be more effectively used to estimate the confidence of distance predictions and select predicted distance maps. Availability and implementation The software package, source code and data of DeepDist2 are freely available at https://github.com/multicom-toolbox/deepdist and https://zenodo.org/record/4712084#.YIIM13VKhQM. Supplementary information Supplementary data are available at Bioinformatics online.

59 BASIC BIOLOGICAL SCIENCES↗