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 919 records · Page 51

Computationally Efficient Training of Deep Neural Networks via Transfer Learning

Transfer learning is a highly successful approach to train deep neural networks for customized image recognition tasks. Transfer learning leverages deep learning models that are previously trained on massive datasets and re-trains the network for a novel image recognition dataset. Typically, the advantage of transfer learning has been measured in sample efficiency, but instead, we investigate the computational efficiency of transfer learning. A good pre-trained model provides features that can be used as input to a new classifier (usually the top layers of a neural network). We show that if a good pre-trained model is selected, that training a new classifier can be much more computationally efficient than training a deep neural network without transfer learning. The first step in transfer learning is to select a pre-trained model to use as a feed-forward network for generating features. Here this selection process either uses human intuition/convenience or a methodical but computationally intensive validation loop. Instead, we would prefer a method to select the pre-trained model that will produce the best transfer results for the least amount of computation. To this end, we provide a computationally efficient metric for the fit between a pre-trained model and a novel image recognition task. The better the fit, the less computation will be needed to re-train the pre-trained model for the novel task. As machine learning becomes ubiquitous, highly-accurate trained models will proliferate and computationally efficient transfer learning methods will enable rapid development of new image recognition models.

97 MATHEMATICS AND COMPUTING↗

Optimizing transmit field inhomogeneity of parallel RF transmit design in 7T MRI using deep learning

Ultrahigh field (UHF) Magnetic Resonance Imaging (MRI) provides a higher signal-to-noise ratio and, thereby, higher spatial resolution. However, UHF MRI introduces challenges such as transmit radiofrequency (RF) field (B+1) inhomogeneities, leading to uneven flip angles and image intensity anomalies. These issues can significantly degrade imaging quality and its medical applications. This study addresses B+1 field homogeneity through a novel deep learning-based strategy. Traditional methods like Magnitude Least Squares (MLS) optimization have been effective but are time-consuming and dependent on the patient’s presence. Recent machine learning approaches, such as RF Shim Prediction by Iteratively Projected Ridge Regression and deep learning frameworks, have shown promise but face limitations like extensive training times and oversimplified architectures. We propose a two-step deep learning strategy. First, we obtain the desired reference RF shimming weights from multi-channel B+1 fields using random-initialized Adaptive Moment Estimation. Then, we employ Residual Networks (ResNets) to train a model that maps B+1 fields to target RF shimming outputs. Our approach does not rely on pre-calculated reference optimizations for the testing process and efficiently learns residual functions. Comparative studies with traditional MLS optimization demonstrate our method’s advantages in terms of speed and accuracy. The proposed strategy achieves a faster and more efficient RF shimming design, significantly improving imaging quality at UHF. This advancement holds potential for broader applications in medical imaging and diagnostics.

Lu, Zhengyi [Vanderbilt University]↗

Deep-learning-based domain adaptation for cavity fault prediction at Jefferson Laboratory

Superconducting radio-frequency (SRF) cavities are the core components of the Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab, providing high-power electron beams for nuclear physics experiments. The facility comprises 418 SRF cavities, and any fault in these cavities can lead to interruptions in the electron beam supply. Cavity faults are the leading cause of beam trips in CEBAF. Predicting and mitigating those faults before onset can help maintain normal operation. Existing models face challenges in distinguishing between normal and fault signals when changes occur in the underlying time-series data, from changes in control software, operational parameters, or the environment. This work proposes a deep learning domain adaptation model that leverages transfer learning to address fault prediction challenges by improving accuracy. The model is trained and fine-tuned using a dataset collected for faulty and normal operation using a data acquisition system in CEBAF. Our deep learning-based domain adaptation model achieves a prediction accuracy of 89.61% of the fault and normal signals. The developed model effectively predicts normal running signals compared to the baseline approach without domain adaptation. This capacity is essential for the fault prediction task in the CEBAF because of heavily imbalanced data containing vast amounts of normal signals. The model performs well for predicting faults several hundred milliseconds before the fault onset compared to other models where no adaptation is applied. Incorporating deep learning-based domain adaptation techniques will significantly improve the fault prediction performance.

Rahman, Md Monibor [Old Dominion Univ., Norfolk, V↗

SU-F-T-318: Sensitivity and Stability of OSLDs with Filled Deep Electron/hole Traps Under Pre-Irradiation and Bleaching Conditions

Purpose: This work evaluated the characteristics of optically stimulated luminescence dosimeters (OSLDs) with fully filled deep electron/hole traps (OSLDfull) with the bleaching conditions according to the accumulated dose. Methods: The OSLDs were first pre-irradiated with a Co-60 gamma ray at more than 5 kGy, so as to fill the deep electron and hole traps. Using a 6-MV beam, the OSLDfull characteristics were investigated in terms of the full bleaching, fading, dose linearity, and dose sensitivity obtained in response to the accumulated dose values. To facilitate a comparison of the dose sensitivity, OSLDs with un-filled deep electron/hole traps (OSLDempty) were investigated in the same manner. A long-pass filter was used to exclude bleaching-source wavelengths of less than 520 nm. Various bleaching time and wavelength combinations were used in order to determine the optimal bleaching conditions for the OSLD full. Results: The fading for the OSLDfull exhibited stable signals after 8 min, for both 1- and 10-Gy. For 4-h bleaching time and an unfiltered bleaching device, the supralinear index values for the OSLDfull were 1.003, 1.002, 0.999, and 1.001 for doses of 2, 4, 7, and 10 Gy, respectively. For a 65-Gy accumulated dose with a 5-Gy fraction, no variation in dose sensitivity was obtained for the OSLDfull, within a standard deviation of 0.85%, whereas the OSLDempty dose sensitivity decreased by approximately 2.3% per 10 Gy. The filtered bleaching device yielded a highly stable sensitivity for OSLDfull, independent of bleaching time and within a standard deviation of 0.71%, whereas the OSLDempty dose sensitivity decreased by approximately 4.2% per 10 Gy for an accumulated dose of 25 Gy with a 5-Gy fraction. Conclusion: Under the bleaching conditions determined in this study, clinical dosimetry with OSLDfull is highly stable, having an accuracy of 1% with no change in dose sensitivity or linearity at clinical doses. This work was supported by a National Research Foundation of Korea (NRF) grant, funded by the Korea government (MISP) (No. 2014M2B2A4031164), and by the Korea Health Technology R&D Project through the Korea Health Industry Development Institute (KHIDI), funded by the Ministry of Health & Welfare, Republic of Korea (HI14C3459).

60 APPLIED LIFE SCIENCES↗

When Is a Microbial Culture “Pure”? Persistent Cryptic Contaminant Escapes Detection Even with Deep Genome Sequencing

Geobacter sulfurreducens strain KN400 was recovered in previous studies in which a culture of the DL1 strain of G. sulfurreducens served as the inoculum in investigations of microbial current production at low anode potentials (-400 mV versus Ag/AgCl). Differences in the genome sequences of KN400 and DL1 were too great to have arisen from adaptive evolution during growth on the anode. Previous deep sequencing (80-fold coverage) of the DL1 culture failed to detect sequences specific to KN400, suggesting that KN400 was an external contaminant inadvertently introduced into the anode culturing system. In order to evaluate this further, a portion of the gene for OmcS, a c -type cytochrome that both KN400 and DL1 possess, was amplified from the DL1 culture. HiSeq-2000 Illumina sequencing of the PCR product detected the KN400 sequence, which differs from the DL1 sequence at 14 bp, at a frequency of ca. 1 in 10 5 copies of the DL1 sequence. A similar low frequency of KN400 was detected with quantitative PCR of a KN400-specific gene. KN400 persisted at this frequency after intensive restreaking of isolated colonies from the DL1 culture. However, a culture in which KN400 could no longer be detected was obtained by serial dilution to extinction in liquid medium. The KN400-free culture could not grow on an anode poised at -400 mV. Thus, KN400 cryptically persisted in the culture dominated by DL1 for more than a decade, undetected by even deep whole-genome sequencing, and was only fortuitously uncovered by the unnatural selection pressure of growth on a low-potential electrode. IMPORTANCE: Repeated streaking of isolated colonies on solidified medium remains a common strategy for obtaining pure cultures, especially of difficult-to-cultivate microorganisms such as strict anaerobes. The results presented here demonstrate that verifying the purity of cultures obtained in this manner may be difficult because extremely rare variants can persist, undetectable with even deep genomic DNA sequencing. The only way to ensure that a culture is pure is to cultivate it from an initial single cell, which may be technically difficult for many environmentally significant microbes.

59 BASIC BIOLOGICAL SCIENCES↗

Effect of Deep Centers on Charge-Carrier Confinement in InGaN/GaN Quantum Wells and on LED Efficiency

The deep-center-assisted tunneling of carriers in p–n structures of light-emitting diodes (LEDs) with InGaN/GaN quantum wells (QWs) makes smaller the effective height of the injection barrier, but leads to a dependence of the radiation efficiency on the density and energy spectrum of defects in GaN. In the case of hopping conduction across the space charge region, the forward voltage mainly drops near the QW boundary, where the density of deep states at the quasi Fermi-level is the lowest. As a result, band bending at the boundary decreases, and, with increasing current, the direction of the electric field also changes, which leads to a weaker confinement of holes, to their non-radiative recombination in the n barrier, and to an efficiency droop. The low efficiency of green GaN LEDs is associated with the dominance of deep centers and insufficient density of shallow centers in the energy spectrum of defects in barrier layers near the boundaries with the QW. The proposed model is confirmed by the stepwise experimental dependences of the current, capacitance and efficiency of green and blue LEDs in the case of forward bias, which reflect the contribution of color centers responsible for the defect photoluminescence bands in GaN.

36 MATERIALS SCIENCE↗

Group III Acceptors with Shallow and Deep Levels in Silicon Carbide: ESR and ENDOR Studies

Results of investigations of Group III acceptors (B, Al, and Ga) in crystals of silicon carbide using the most informative electron spin resonance and electron nuclear double resonance methods are presented. Structural models of the acceptors with shallow and deep levels are considered. In addition to the data obtained earlier, studies using high-frequency magnetic resonance were obtained, which allowed revealing orthorhombic deviations from the axial symmetry for the deep acceptors; theoretical analysis explains experimentally found shifts of g factors for the deep acceptors arising due to the orthorhombic deviations, which appear probably due to the Jahn–Teller effect.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Charge Carrier Transport and Deep Levels Recharge in Avalanche S-Diodes Based on GaAs

Carrier transport and deep-level recharging in semiconductor avalanche S-diode structures have been investigated. Gallium-arsenide n{sup +}–π–ν–n structures with the diffusion distribution of deep iron acceptors have been studied. It has been found by solving the continuity and Poisson equations with the use of a commercial software that the electron injection affects the avalanche breakdown voltage and the spacecharge region broadens due to capture of avalanche holes on negative iron ions in the π-region. It is demonstrated by comparing the results of numerical calculation with the experimental data that the S-shaped I–V characteristic of the diffusion avalanche S-diodes cannot be explained within the previously proposed mechanism of capture of avalanche holes on the deep iron levels.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Towards Misregistration-Tolerant Change Detection using Deep Learning Techniques with Object-Based Image Analysis

Co-registrating is a common pre-processing step for existing change detection algorithms, but registering bi-temporal images is nontrivial. The use of image patch as input for deep learning techniques provides a natural avenue to apply them in the OBIA framework, and have shown successful performance in the object-based land cover mapping and change detection applications. Even though attempts of applying deep learning techniques for change detection applications have been made with varying success, its application under OBIA framework for change detection have not been conducted and its tolerance for misregistration among temporal images are neither known. This study performed change detection under OBIA framework using deep learning techniques for the first time, and evaluated its performance regarding their tolerance of image misregistration on training and testing dataset. Our results demonstrate the proposed change detection scheme is surprisingly robust to image misregistration on the testing dataset, while classifiers trained with the training dataset containing image misregistration errors suffer from slight decrease of overall accuracy.

Liu, Tao↗

District EnErgy Planner (DEEP) v2

The District EnErgy Planner - DEEP is an Mixed Integer Linear Programming (MILP) optimization software tool to solve district energy system, technology configuration, operation strategies, and energy retail business schemes. DEEP takes user input energy demand on heating, cooling and electricity demand. Energy loss through pipeline is calculated for heating and cooling from central plants. The optimal system configuration to minimize the district energy system life cycle cost or minimize CO2 emission is calculated based on energy balance equations and various constraints. The recent update on DEEP include a feature of waste heat utilization energy balance based optimization to take into accounts of different temperature bands of heat into account to maximize system efficiency. Another feature is to optimize district energy retail by provide optimal pricing scheme for heating, cooling and electricity to end users to incorporate district to grid demand response.

Feng, Wei↗

Deep Learning Image Segmentation for Atmospheric Rivers

Abstract The identification of atmospheric rivers (ARs) is crucial for weather and climate predictions as they are often associated with severe storm systems and extreme precipitation, which can cause large impacts on society. This study presents a deep learning model, termed ARDetect, for image segmentation of ARs using ERA5 data from 1960 to 2020 with labels obtained from the TempestExtremes tracking algorithm. ARDetect is a convolutional neural network (CNN)-based U-Net model, with its structure having been optimized using automatic hyperparameter tuning. Inputs to ARDetect were selected to be the integrated water vapor transport (IVT) and total column water (TCW) fields, as well as the AR mask from TempestExtremes from the previous time step to the one being considered. ARDetect achieved a mean intersection-over-union (mIoU) rate of 89.04% for ARs, indicating its high accuracy in identifying these weather patterns and a superior performance than most deep learning–based models for AR detection. In addition, ARDetect can be executed faster than the TempestExtremes method (seconds vs minutes) for the same period. This provides a significant benefit for online AR detection, especially for high-resolution global models. An ensemble of 10 models, each trained on the same dataset but having different starting weights, was used to further improve on the performance produced by ARDetect, thus demonstrating the importance of model diversity in improving performance. ARDetect provides an effective and fast deep learning–based model for researchers and weather forecasters to better detect and understand ARs, which have significant impacts on weather-related events such as floods and droughts.

Galea, Daniel↗

Impacts of Varying Concentrations of Cloud Condensation Nuclei on Deep Convective Cloud Updrafts—A Multimodel Assessment

Abstract This study presents results from a model intercomparison project, focusing on the range of responses in deep convective cloud updrafts to varying cloud condensation nuclei (CCN) concentrations among seven state-of-the-art cloud-resolving models. Simulations of scattered convective clouds near Houston, Texas, are conducted, after being initialized with both relatively low and high CCN concentrations. Deep convective updrafts are identified, and trends in the updraft intensity and frequency are assessed. The factors contributing to the vertical velocity tendencies are examined to identify the physical processes associated with the CCN-induced updraft changes. The models show several consistent trends. In general, the changes between the High-CCN and Low-CCN simulations in updraft magnitudes throughout the depth of the troposphere are within 15% for all of the models. All models produce stronger (~+5%–15%) mean updrafts from ~4–7 km above ground level (AGL) in the High-CCN simulations, followed by a waning response up to ~8 km AGL in most of the models. Thermal buoyancy was more sensitive than condensate loading to varying CCN concentrations in most of the models and more impactful in the mean updraft responses. However, there are also differences between the models. The change in the amount of deep convective updrafts varies significantly. Furthermore, approximately half the models demonstrate neutral-to-weaker (~−5% to 0%) updrafts above ~8 km AGL, while the other models show stronger (~+10%) updrafts in the High-CCN simulations. The combination of the CCN-induced impacts on the buoyancy and vertical perturbation pressure gradient terms better explains these middle- and upper-tropospheric updraft trends than the buoyancy terms alone.

54 ENVIRONMENTAL SCIENCES↗

Model Intercomparison of the Impacts of Varying Cloud Droplet–Nucleating Aerosols on the Life Cycle and Microphysics of Isolated Deep Convection

The microphysical impacts of aerosol particles on scattered isolated deep convective cells near Houston, Texas, on 19 June 2013, are examined using multiple cloud-resolving model (CRM) simulations initialized with vertical profiles of low and high concentrations of cloud droplet–nucleating aerosols. These simulations formed part of the Model Intercomparison Project (MIP) conducted by the Deep Convective Working Group of the Aerosol, Cloud, Precipitation and Climate (ACPC) initiative. Each CRM generated a field of convective cells representing those observed during the case study with varying degrees of accuracy. The Tracking and Object-Based Analysis of Clouds (tobac) cell-tracking algorithm was applied to each MIP CRM simulation to track relatively long-lived convective cells (20–60 min). Most of the CRMs produced similar aerosol loading impacts on the warm phase of tracked cell properties with reduced autoconversion and accretion growth of rain, increased cloud water, reduced rainfall, and reduced near-surface evaporation of rain. The sign of aerosol impacts on the warm-phase properties of the convective cells was also quite consistent over cell lifetimes with the greatest magnitude of influence in the first half of the life cycle in most CRMs. In contrast, the ice-phase response to aerosol loading was highly variable among CRMs and included increases or decreases in ice amounts at inconsistent stages of the cell life cycle and midlevel versus upper-level changes in ice. This intermodel variability in ice is indicative both of the complex indirect interactions between aerosols and ice-phase processes in deep convection and their associated parameterizations.

Aerosol-cloud interaction↗

Deep reinforcement learning to discover multi-fuel injection strategies for compression ignition engines

Over the past several decades, regulation of compression ignition engine emissions has become increasingly stringent as concern about the environmental and health implications of these emissions has grown. These changing constraints have led to a series of new, alternative fuel injection strategies that aim to maintain power output while reducing in-cylinder generated emissions by operating in the low-temperature combustion (LTC) regime. These advanced injection strategies are created and retuned for individual combinations of engine geometry, fuel, and emissions constraints. Deep reinforcement learning has been shown to be an effective alternative to traditional optimization approaches for highly combinatorial control problems, such as discovering the optimal injection schedules for compression ignition engines. In this study, we deploy a previously presented deep reinforcement learning framework to iteratively optimize a series of engine geometries over a range of increasingly strict NO x emissions regulations. We then examine the resulting injection schedules. We discuss the potential for using this deep reinforcement learning framework for fuel selection screening and for discovering unique injection strategies for different engine geometries and future emissions standards.

33 ADVANCED PROPULSION SYSTEMS↗

Machine learning and deep learning for brain tumor MRI image segmentation

Brain tumors are often fatal. Therefore, accurate brain tumor image segmentation is critical for the diagnosis, treatment, and monitoring of patients with these tumors. Magnetic resonance imaging (MRI) is a commonly used imaging technique for capturing brain images. Both machine learning and deep learning techniques are popular in analyzing MRI images. This article reviews some commonly used machine learning and deep learning techniques for brain tumor MRI image segmentation. The limitations and advantages of the reviewed machine learning and deep learning methods are discussed. Even though each of these methods has a well-established status in their individual domains, the combination of two or more techniques is currently an emerging trend.

Research & Experimental Medicine↗

Deep-ultraviolet ptychographic pocket-scope (DART): mesoscale lensless molecular imaging with label-free spectroscopic contrast

The mesoscale characterization of biological specimens has traditionally required compromises between resolution, field-of-view, depth-of-field, and molecular specificity, with most approaches relying on external labels. Here we present the Deep-ultrAviolet ptychogRaphic pockeT-scope (DART), a handheld platform that transforms label-free molecular imaging through intrinsic deep-ultraviolet spectroscopic contrast. By leveraging biomolecules’ natural absorption fingerprints and combining them with lensless ptychographic microscopy, DART resolves down to 308-nm linewidths across centimeter-scale areas while maintaining millimeter-scale depth-of-field. The system’s virtual error-bin methodology effectively eliminates artifacts from limited temporal coherence and other optical imperfections, enabling high-fidelity molecular imaging without lenses. Through differential spectroscopic imaging at deep-ultraviolet wavelengths, DART quantitatively maps nucleic acid and protein distributions with femtogram sensitivity, providing an intrinsic basis for explainable virtual staining. We demonstrate DART’s capabilities through imaging of tissue sections, cytopathology specimens, blood cells, and neural populations, revealing detailed molecular contrast without external labels. The combination of high-resolution molecular mapping and broad mesoscale imaging in a portable platform opens new possibilities from rapid clinical diagnostics, tissue analysis, to biological characterization in space exploration.

60 APPLIED LIFE SCIENCES↗

Integrating deep neural networks with full-waveform inversion: Reparameterization, regularization, and uncertainty quantification

Full-waveform inversion (FWI) is an accurate imaging approach for modeling the velocity structure by minimizing the misfit between recorded and predicted seismic waveforms. However, the strong nonlinearity of FWI resulting from fitting oscillatory waveforms can trap the optimization in local minima. We have adopted a neural-network-based full-waveform inversion (NNFWI) method that integrates deep neural networks with FWI by representing the velocity model with a generative neural network. Neural networks can naturally introduce spatial correlations as regularization to the generated velocity model, which suppresses noise in the gradients and mitigates local minima. Furthermore, the velocity model generated by neural networks is input to the same partial differential equation (PDE) solvers used in conventional FWI. The gradients of the neural networks and PDEs are calculated using automatic differentiation, which back propagates gradients through the acoustic PDEs and neural network layers to update the weights of the generative neural network. Experiments on 1D velocity models, the Marmousi model, and the 2004 BP model determine that NNFWI can mitigate local minima, especially for imaging high-contrast features such as salt bodies, and it significantly improves the inversion in the presence of noise. Adding dropout layers to the neural network model also allows analyzing the uncertainty of the inversion results through Monte Carlo dropout. NNFWI opens a new pathway to combine deep learning and FWI for exploiting the characteristics of deep neural networks and the high accuracy of PDE solvers. Because NNFWI does not require extra training data and optimization loops, it provides an attractive and straightforward alternative to conventional FWI.

58 GEOSCIENCES↗

Deep learning for accelerated all-dielectric metasurface design

Deep learning has risen to the forefront of many fields in recent years, overcoming challenges previously considered intractable with conventional means. Materials discovery and optimization is one such field, but significant challenges remain, including the requirement of large labeled datasets and one-to-many mapping that arises in solving the inverse problem. Here we demonstrate modeling of complex all-dielectric metasurface systems with deep neural networks, using both the metasurface geometry and knowledge of the underlying physics as inputs. Our deep learning network is highly accurate, achieving an average mean square error of only 1.16 × 10 -3 and is over five orders of magnitude faster than conventional electromagnetic simulation software. We further develop a novel method to solve the inverse modeling problem, termed fast forward dictionary search (FFDS), which offers tremendous controls to the designer and only requires an accurate forward neural network model. These techniques significantly increase the viability of more complex all-dielectric metasurface designs and provide opportunities for the future of tailored light matter interactions.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗