Engineering Papers⌕ Search

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.

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

At least 1,243 records · Page 69

Optical characterization of deep-level defects in n-type Al x In y Ga 1- x - y P for the development of solid-state photomultiplier analogs

Characterizing intrinsic defects is an essential step in evaluating materials for novel optoelectronic device applications. For photomultipliers, suppressing dark currents is critical, but a tradeoff is present between maximizing the band gap while remaining sensitive to the wavelength of interest and minimizing the incorporation of fresh defects by growing not-yet-optimized alloys. We present a series of capacitance-based measurements, including deep-level optical spectroscopy, steady-state photocapacitance, and illuminated capacitance-voltage, on photodiodes with lightly n-type Al x In y Ga 1−x−y P absorber regions. Several deep levels are identified, including one near the midgap. Although the inclusion of aluminum increases each trap density by approximately 10×, the hole capture cross-section also appears to decrease, suggesting that Shockley–Read–Hall dark currents may be suppressed. These materials may be good candidates for the development into silicon photomultiplier analogs with a wider bandgap for scintillator applications.

III–V↗

Augmented signal processing in Liquid Argon Time Projection Chambers with a deep neural network

The Liquid Argon Time Projection Chamber (LArTPC) is an advanced neutrino detector technology widely used in recent and upcoming accelerator neutrino experiments. It features a low energy threshold and high spatial resolution that allow for comprehensive reconstruction of event topologies. In current-generation LArTPCs, the recorded data consist of digitized waveforms on wires produced by induced signal on wires of drifting ionization electrons, which can also be viewed as two-dimensional (2D) (time versus wire) projection images of charged-particle trajectories. For such an imaging detector, one critical step is the signal processing that reconstructs the original charge projections from the recorded 2D images. For the first time, we introduce a deep neural network in LArTPC signal processing to improve the signal region of interest detection. By combining domain knowledge (e.g., matching information from multiple wire planes) and deep learning, this method shows significant improvements over traditional methods. This work details the method, software tools, and performance evaluated with realistic detector simulations.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

GPU coprocessors as a service for deep learning inference in high energy physics

In the next decade, the demands for computing in large scientific experiments are expected to grow tremendously. During the same time period, CPU performance increases will be limited. At the CERN Large Hadron Collider (LHC), these two issues will confront one another as the collider is upgraded for high luminosity running. Alternative processors such as graphics processing units (GPUs) can resolve this confrontation provided that algorithms can be sufficiently accelerated. In many cases, algorithmic speedups are found to be largest through the adoption of deep learning algorithms. We present a comprehensive exploration of the use of GPU-based hardware acceleration for deep learning inference within the data reconstruction workflow of high energy physics. We present several realistic examples and discuss a strategy for the seamless integration of coprocessors so that the LHC can maintain, if not exceed, its current performance throughout its running.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Statistically-informed deep learning for gravitational wave parameter estimation

We introduce deep learning models to estimate the masses of the binary components of black hole mergers, $(m_1,m_2)$, and three astrophysical properties of the post-merger compact remnant, namely, the final spin, $a_\mathrm f$, and the frequency and damping time of the ringdown oscillations of the fundamental $\ell = m = 2$ bar mode, $(\omega_\mathrm R, \omega_\mathrm I)$. Our neural networks combine a modified WaveNet architecture with contrastive learning and normalizing flow. We validate these models against a Gaussian conjugate prior family whose posterior distribution is described by a closed analytical expression. Upon confirming that our models produce statistically consistent results, we used them to estimate the astrophysical parameters $(m_1,m_2, a_\mathrm f, \omega_\mathrm R, \omega_\mathrm I)$ of five binary black holes: GW150914, GW170104, GW170814, GW190521 and GW190630. We use PyCBC Inference to directly compare traditional Bayesian methodologies for parameter estimation with our deep learning based posterior distributions. Our results show that our neural network models predict posterior distributions that encode physical correlations, and that our data-driven median results and 90% confidence intervals are similar to those produced with gravitational wave Bayesian analyses. This methodology requires a single V100 NVIDIA GPU to produce median values and posterior distributions within two milliseconds for each event. Furthermore, this neural network, and a tutorial for its use, are available at the Data and Learning Hub for Science.

79 ASTRONOMY AND ASTROPHYSICS↗

Deep kernel methods learn better: from cards to process optimization

Abstract The ability of deep learning methods to perform classification and regression tasks relies heavily on their capacity to uncover manifolds in high-dimensional data spaces and project them into low-dimensional representation spaces. In this study, we investigate the structure and character of the manifolds generated by classical variational autoencoder (VAE) approaches and deep kernel learning (DKL). In the former case, the structure of the latent space is determined by the properties of the input data alone, while in the latter, the latent manifold forms as a result of an active learning process that balances the data distribution and target functionalities. We show that DKL with active learning can produce a more compact and smooth latent space which is more conducive to optimization compared to previously reported methods, such as the VAE. We demonstrate this behavior using a simple cards dataset and extend it to the optimization of domain-generated trajectories in physical systems. Our findings suggest that latent manifolds constructed through active learning have a more beneficial structure for optimization problems, especially in feature-rich target-poor scenarios that are common in domain sciences, such as materials synthesis, energy storage, and molecular discovery. The Jupyter Notebooks that encapsulate the complete analysis accompany the article.

97 MATHEMATICS AND COMPUTING↗

Integrating AlphaFold and deep learning for atomistic interpretation of cryo-EM maps

Abstract Interpretation of cryo-electron microscopy (cryo-EM) maps requires building and fitting 3D atomic models of biological molecules. AlphaFold-predicted models generate initial 3D coordinates; however, model inaccuracy and conformational heterogeneity often necessitate labor-intensive manual model building and fitting into cryo-EM maps. In this work, we designed a protein model-building workflow, which combines a deep-learning cryo-EM map feature enhancement tool, CryoFEM (Cryo-EM Feature Enhancement Model) and AlphaFold. A benchmark test using 36 cryo-EM maps shows that CryoFEM achieves state-of-the-art performance in optimizing the Fourier Shell Correlations between the maps and the ground truth models. Furthermore, in a subset of 17 datasets where the initial AlphaFold predictions are less accurate, the workflow significantly improves their model accuracy. Our work demonstrates that the integration of modern deep learning image enhancement and AlphaFold may lead to automated model building and fitting for the atomistic interpretation of cryo-EM maps.

59 BASIC BIOLOGICAL SCIENCES↗

A deep learning approach to identify missing is-a relations in SNOMED CT

Abstract Objective SNOMED CT is the largest clinical terminology worldwide. Quality assurance of SNOMED CT is of utmost importance to ensure that it provides accurate domain knowledge to various SNOMED CT-based applications. In this work, we introduce a deep learning-based approach to uncover missing is-a relations in SNOMED CT. Materials and Methods Our focus is to identify missing is-a relations between concept-pairs exhibiting a containment pattern (ie, the set of words of one concept being a proper subset of that of the other concept). We use hierarchically related containment concept-pairs as positive instances and hierarchically unrelated containment concept-pairs as negative instances to train a model predicting whether an is-a relation exists between 2 concepts with containment pattern. The model is a binary classifier leveraging concept name features, hierarchical features, enriched lexical attribute features, and logical definition features. We introduce a cross-validation inspired approach to identify missing is-a relations among all hierarchically unrelated containment concept-pairs. Results We trained and applied our model on the Clinical finding subhierarchy of SNOMED CT (September 2019 US edition). Our model (based on the validation sets) achieved a precision of 0.8164, recall of 0.8397, and F1 score of 0.8279. Applying the model to predict actual missing is-a relations, we obtained a total of 1661 potential candidates. Domain experts performed evaluation on randomly selected 230 samples and verified that 192 (83.48%) are valid. Conclusions The results showed that our deep learning approach is effective in uncovering missing is-a relations between containment concept-pairs in SNOMED CT.

97 MATHEMATICS AND COMPUTING↗

Learning and discovering multiple solutions using physics-informed neural networks with random initialization and deep ensemble

In this work we explore the capability of physics-informed neural networks (PINNs) to discover multiple solutions. Many real-world phenomena governed by nonlinear differential equations (DEs), such as fluid flow, exhibit multiple solutions under the same conditions, yet capturing this solution multiplicity remains a significant challenge. A key difficulty lies in providing appropriate initial conditions or guesses, as widely used time-marching schemes and Newton’s method are highly sensitive to these choices when solving complex computational problems. While machine learning models, particularly PINNs, have shown promise in solving DEs, their ability to capture multiple solutions remains underexplored. In this work, we propose a simple and practical approach using PINNs to learn and discover multiple solutions. We first demonstrate that PINNs, when combined with random initialization and deep ensemble method—originally developed for uncertainty quantification—can effectively uncover multiple solutions to nonlinear ordinary and partial DEs. Although training large ensembles of PINNs may appear computationally demanding, this can be done efficiently using vectorization techniques supported by modern deep learning frameworks, allowing many networks to be trained simultaneously. Our approach highlights the critical role of initialization in shaping solution diversity, addressing an often-overlooked aspect of machine learning for scientific computing. Furthermore, we propose utilizing PINN-generated solutions as initial conditions or initial guesses for conventional numerical solvers to enhance accuracy and efficiency in capturing multiple solutions. Extensive numerical experiments, including the Allen–Cahn equation and cavity flow, where our approach successfully identifies both stable and unstable solutions, validate the effectiveness of our method. These findings establish a general and efficient framework for addressing solution multiplicity in nonlinear DEs.

97 MATHEMATICS AND COMPUTING↗

Deep exclusive meson production as a probe to the puzzle of Λ hyperon polarization

In the 1970s, an unexpected transverse Λ polarization in unpolarized proton-beryllium collisions was discovered, which initiated extensive studies on spin phenomena in high-energy physics. Over the past five decades, similar transverse Λ polarization has been observed across various collision systems, including lepton-hadron deep-inelastic scattering, hadron-hadron collisions, and electron-positron collisions. Despite numerous promising theoretical models, the fundamental mechanism underlying this polarization phenomenon remains inconclusive to this day. However, in both longitudinally and transversely polarized lepton-hadron and hadron-hadron collisions, it is found that the Λ hyperon is polarized with respect to the initial parton spin direction. How the Λ hyperon acquires its spin has become one of the most crucial questions to address in order to resolve this puzzle. In this paper, I propose to use an exclusive process that can be measured at the Electron-Ion Collider, the deep exclusive meson production, to explicitly test the mechanism of Λ polarization. The outcomes of this experimental measurement are anticipated to unveil the dominant mechanism by which Λ obtains its spin, eliminating many of the ambiguities that have been encountered in previous studies. Finally, experimental challenges and requirements are discussed. Published by the American Physical Society 2024

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Semi-inclusive deep-inelastic scattering off few-nucleon systems: Tagging the EMC effect and hadronization mechanisms with detection of slow recoiling nuclei

The semi-inclusive deep-inelastic scattering of electrons off {sup 2}H and {sup 3}He with detection of slow protons and deuterons, respectively, i.e., the processes {sup 2}H(e,e{sup '}p)X and {sup 3}He(e,e{sup '}d)X, are calculated within the spectator mechanism, taking into account the final state interaction of the nucleon debris with the detected protons and deuterons. It is shown that by a proper choice of the kinematics the origin of the EMC effect and the details of the interaction between the hadronizing quark and the nuclear medium can be investigated at a level which cannot be reached by inclusive deep-inelastic scattering. A comparison of the results of our calculations, containing no adjustable parameters, with recently available experimental data on the process {sup 2}H(e,e{sup '}p)X shows a good agreement in the backward hemisphere of the emitted nucleons. Theoretical predictions at energies that will be available at the upgraded Thomas Jefferson National Accelerator Facility are presented, and the possibility to investigate the proposed semi-inclusive processes at electron-ion colliders is briefly discussed.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Polarized deep inelastic and elastic scattering from gauge/string duality

In this paper, we investigate deep inelastic and elastic scattering on a polarized spin-(1/2) hadron using gauge/string duality. This spin-(1/2) hadron corresponds to a supergravity mode of the dilatino. The polarized deep inelastic structure functions are computed in the supergravity approximation at large t' Hooft coupling {lambda} and finite x with {lambda}{sup -1/2}<<x<1. Furthermore, we discuss the moments of all structure functions, and propose an interesting sum rule 0({integral}(1))dxg{sub 2}(x,q{sup 2})=0 for the g{sub 2} structure function which is known as the Burkhardt-Cottingham sum rule in QCD. In the end, the elastic scattering is studied and elastic form factors of the spin-(1/2) hadron are calculated within the same framework.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Polarized deep inelastic scattering off the neutron from gauge/string duality

We investigate deep inelastic scattering off the polarized 'neutron' using gauge/string duality. The 'neutron' corresponds to a supergravity mode of the neutral dilatino. Through introducing the Pauli interaction term into the action in AdS{sub 5} space, we calculate the polarized deep inelastic structure functions of the 'neutron' in supergravity approximation at large t' Hooft coupling {lambda} and finite x with {lambda}{sup -1/2}<<x<1. In comparison with the charged dilatino-''proton,'' which has been obtained in the previous work by Gao and Xiao, we find the structure functions of the 'neutron' are power suppressed at the same order as the ones of the ''proton.'' Especially, we find the Burkhardt-Cottingham-like sum rule, which is satisfied in the work by Gao and Xiao, is broken due to the Pauli interaction term. We also illustrate how such a Pauli interaction term can arise naturally from higher dimensional fermion-graviton coupling through the usual Kaluza-Klein reduction.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

QCD rescattering mechanism for diffractive deep inelastic scattering

We present a QCD-based model where rescattering between final state partons in deep inelastic scattering leads to events with large rapidity gaps and a leading proton. In the framework of this model the amplitude for multiple gluon exchanges is calculated in the eikonal approximation to all orders in perturbation theory. Both large and small invariant mass M{sub X} limits are considered. The model successfully describes the precise HERA data on the diffractive deep inelastic cross section in the whole available kinematical range and gives new insight into the density of gluons at very small momentum fractions in the proton.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

AdS Black Disk Model for Small-x Deep Inelastic Scattering

Using the approximate conformal invariance of QCD at high energies we consider a simple anti-de Sitter black disk model to describe saturation in deep inelastic scattering. Deep inside saturation the structure functions have the same power law scaling, F{sub T}{approx}F{sub L}{approx}x{sup -{omega}}, where {omega} is related to the expansion rate of the black disk with energy. Furthermore, the ratio F{sub L}/F{sub T} is given by the universal value (1+{omega}/3+{omega}), independently of the target. For {gamma}*-{gamma}* scattering at high energies we obtain explicit expressions and ratios for the total cross sections of transverse and longitudinal photons in terms of the single parameter {omega}.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Nuclear Corrections in Neutrino-Nucleus Deep Inelastic Scattering and their Compatibility with Global Nuclear Parton-Distribution-Function Analyses

We perform a global {chi}{sup 2} analysis of nuclear parton distribution functions using data from charged current neutrino-nucleus ({nu}A) deep-inelastic scattering (DIS), charged-lepton-nucleus (l{sup {+-}A}) DIS, and the Drell-Yan (DY) process. We show that the nuclear corrections in {nu}A DIS are not compatible with the predictions derived from l{sup {+-}A} DIS and DY data. We quantify this result using a hypothesis-testing criterion based on the {chi}{sup 2} distribution which we apply to the total {chi}{sup 2} as well as to the {chi}{sup 2} of the individual data sets. We find that it is not possible to accommodate the data from {nu}A and l{sup {+-}A} DIS by an acceptable combined fit. Our result has strong implications for the extraction of both nuclear and proton parton distribution functions using combined neutrino and charged-lepton data sets.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Deep learning-based spatio-temporal fusion for high-fidelity ultra-high-speed X-ray radiography

Full-field ultra-high-speed (UHS) X-ray imaging experiments have been well established to characterize various processes and phenomena. However, the potential of UHS experiments through the joint acquisition of X-ray videos with distinct configurations has not been fully exploited. In this paper, we investigate the use of a deep learning-based spatio-temporal fusion (STF) framework to fuse two complementary sequences of X-ray images and reconstruct the target image sequence with high spatial resolution, high frame rate and high fidelity. We applied a transfer learning strategy to train the model and compared the peak signal-to-noise ratio (PSNR), average absolute difference (AAD) and structural similarity (SSIM) of the proposed framework on two independent X-ray data sets with those obtained from a baseline deep learning model, a Bayesian fusion framework and the bicubic interpolation method. The proposed framework outperformed the other methods with various configurations of the input frame separations and image noise levels. With three subsequent images from the low-resolution (LR) sequence of a four times lower spatial resolution and another two images from the high-resolution (HR) sequence of a 20 times lower frame rate, the proposed approach achieved average PSNRs of 37.57 dB and 35.15 dB, respectively. When coupled with the appropriate combination of high-speed cameras, the proposed approach will enhance the performance and therefore the scientific value of UHS X-ray imaging experiments.

deep learning↗

Deep-learning methods for contrast enhancement and artifact reduction in cryo-electron tomography: a systematic analysis of the state of the art and proposed improvements

Cryo-electron tomography (cryo-ET) has emerged as the preferred technique for visualizing the organization of macromolecular complexes in situ and resolving their structures at subnanometre resolution [Tegunov et al. (2021)View full citation, Nat. Methods, 18, 186–193]. Despite improvements in data quality as a result of advances in detector technology, microscope stability and stage precision, the analysis and interpretation of tomograms remains challenging due to a low signal-to-noise ratio and reconstruction artifacts stemming from experimental constraints in specimen tilt during data collection resulting in a missing wedge in the Fourier space. Recently, self-supervised deep-learning methods have been proposed for contrast enhancement and reduction of resolution anisotropy in reconstructed tomograms. Here, we evaluate several state-of-the-art deep-learning methods which aim to improve the interpretability of cryo-ET reconstructions, with a focus on their performance on downstream tasks of template matching, sub­tomogram averaging and segmentation. We propose new training architectures and a loss function based on Fourier shell correlation that show improved performance over the standard U-Net with L1/L2 losses. We demonstrate our analysis on four diverse experimental datasets: purified 80S ribosomes, in situ Chlamydomonas reinhardtii, immature HIV-1 virus-like particles and INS-1E cells.

contrast enhancement↗

Deep Learning for Enhancing Fault Tolerant Capabilities of Scientific Workflows

Deep Learning for Enhancing Fault TolerantCapabilities of Scientific WorkflowsAlok Singh, Ilkay AltintasSan Diego Supercomputer Center, UCSDLa Jolla, CA, USA{a1singh, ialtintas}@ucsd.eduMalachi Schram, Nathan TallentPacific Northwestern National LaboratoryRichland, WA, USA{malachi.schram, nathan.tallent}@pnnl.govAbstract-In the history of Computer Science, the act of ‘delegation’ has been the greatest multiplier of society’s problem-solving ability. A scientist working on detecting anomalies in a phenomenon, does not need to re-invent matrix multiplication techniques to solve her problem. Scientific workflows provide ultimate ‘delegation’ mechanism -where a domain scientist can completely forget the specifics of ‘how’ her program will execute on a large cluster in an efficient and cost-effective manner and can instead focus on the mathematical formulation and theoretical robustness of her solution. We present here an approach that directly aims to make the execution of Scientific Workflows more reliable, robust and efficient. We aim that the work presented in this paper will propel the larger effort, from the scientific workflow community, of making scientific workflow execution as simple, efficient and robust as a JOIN operation in a modern database. Specifically, we apply Deep Learning techniques to develop a mechanism that forecasts the final state (success or failure) of a dynamic job in a large-scale particle physics experiment, with minimal data gathering, and as early as possible in job’s life cycle. The key advantage of having a predictive mechanism to identify and anticipate failure-prone jobs is the potential for designing intelligent Fault Tolerance mechanisms to handle anomalous events. We achieve a 14% improvement in computational resources utilization, and an overall classification accuracy of 85% on real tasks executed in a High Energy Physics Computing workflow.To the best of our knowledge, this is the most exhaustive and first of its kind study of neural network architectures in context of a real-dataset profiled from a large-scalescientific workflow.

deep learning↗