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 829 records · Page 46
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

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↗
DOE OSTI2026

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↗
DOE OSTI2021

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↗
DOE OSTI2019

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↗
DOE OSTI2022

Randomized probe imaging through deep k-learning

Randomized probe imaging (RPI) is a single-frame diffractive imaging method that uses highly randomized light to reconstruct the spatial features of a scattering object. The reconstruction process, known as phase retrieval, aims to recover a unique solution for the object without measuring the far-field phase information. Typically, reconstruction is done via time-consuming iterative algorithms. In this work, we propose a fast and efficient deep learning based method to reconstruct phase objects from RPI data. The method, which we call deep k-learning, applies the physical propagation operator to generate an approximation of the object as an input to the neural network. This way, the network no longer needs to parametrize the far-field diffraction physics, dramatically improving the results. Deep k-learning is shown to be computationally efficient and robust to Poisson noise. The advantages provided by our method may enable the analysis of far larger datasets in photon starved conditions, with important applications to the study of dynamic phenomena in physical science and biological engineering.

Guo, Zhen (ORCID:0000000213473451)↗
DOE OSTI2022

Computational microscopy for fast widefield deep-tissue fluorescence imaging using a commercial dual-cannula probe

A solid-glass cannula serves as a micro-endoscope that can deliver excitation light deep inside tissue while also collecting emitted fluorescence. Then, we utilize deep neural networks to reconstruct images from the collected intensity distributions. By using a commercially available dual-cannula probe, and training a separate deep neural network for each cannula, we effectively double the field of view compared to prior work. We demonstrated ex vivo imaging of fluorescent beads and brain slices and in vivo imaging from whole brains. We clearly resolved 4 µm beads, with FOV from each cannula of 0.2 mm (diameter), and produced images from a depth of ∼1.2 mm in the whole brain, currently limited primarily by the labeling. Since no scanning is required, fast widefield fluorescence imaging limited primarily by the brightness of the fluorophores, collection efficiency of our system, and the frame rate of the camera becomes possible.

42 ENGINEERING↗
DOE OSTI2023

Many but not all deep neural network audio models capture brain responses and exhibit correspondence between model stages and brain regions

Models that predict brain responses to stimuli provide one measure of understanding of a sensory system and have many potential applications in science and engineering. Deep artificial neural networks have emerged as the leading such predictive models of the visual system but are less explored in audition. Prior work provided examples of audio-trained neural networks that produced good predictions of auditory cortical fMRI responses and exhibited correspondence between model stages and brain regions, but left it unclear whether these results generalize to other neural network models and, thus, how to further improve models in this domain. We evaluated model-brain correspondence for publicly available audio neural network models along with in-house models trained on 4 different tasks. Most tested models outpredicted standard spectromporal filter-bank models of auditory cortex and exhibited systematic model-brain correspondence: Middle stages best predicted primary auditory cortex, while deep stages best predicted non-primary cortex. However, some state-of-the-art models produced substantially worse brain predictions. Models trained to recognize speech in background noise produced better brain predictions than models trained to recognize speech in quiet, potentially because hearing in noise imposes constraints on biological auditory representations. The training task influenced the prediction quality for specific cortical tuning properties, with best overall predictions resulting from models trained on multiple tasks. The results generally support the promise of deep neural networks as models of audition, though they also indicate that current models do not explain auditory cortical responses in their entirety.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2016

Deep Learning Automates the Quantitative Analysis of Individual Cells in Live-Cell Imaging Experiments

Live-cell imaging has opened an exciting window into the role cellular heterogeneity plays in dynamic, living systems. A major critical challenge for this class of experiments is the problem of image segmentation, or determining which parts of a microscope image correspond to which individual cells. Current approaches require many hours of manual curation and depend on approaches that are difficult to share between labs. They are also unable to robustly segment the cytoplasms of mammalian cells. Here, we show that deep convolutional neural networks, a supervised machine learning method, can solve this challenge for multiple cell types across the domains of life. We demonstrate that this approach can robustly segment fluorescent images of cell nuclei as well as phase images of the cytoplasms of individual bacterial and mammalian cells from phase contrast images without the need for a fluorescent cytoplasmic marker. These networks also enable the simultaneous segmentation and identification of different mammalian cell types grown in co-culture. A quantitative comparison with prior methods demonstrates that convolutional neural networks have improved accuracy and lead to a significant reduction in curation time. We relay our experience in designing and optimizing deep convolutional neural networks for this task and outline several design rules that we found led to robust performance. We conclude that deep convolutional neural networks are an accurate method that require less curation time, are generalizable to a multiplicity of cell types, from bacteria to mammalian cells, and expand live-cell imaging capabilities to include multi-cell type systems.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Evaluation of a parasite-density based pooled targeted amplicon deep sequencing (TADS) method for molecular surveillance of Plasmodium falciparum drug resistance genes in Haiti

Sequencing large numbers of individual samples is often needed for countrywide antimalarial drug resistance surveillance. Pooling DNA from several individual samples is an alternative cost and time saving approach for providing allele frequency (AF) estimates at a population level. Using 100 individual patient DNA samples of dried blood spots from a 2017 nationwide drug resistance surveillance study in Haiti, we compared codon coverage of drug resistance-conferring mutations in four Plasmodium falciparum genes ( crt , dhps , dhfr , and mdr1 ), for the same deep sequenced samples run individually and pooled. Samples with similar real-time PCR cycle threshold (Ct) values (+/- 1.0 Ct value) were combined with ten samples per pool. The sequencing success for samples in pools were higher at a lower parasite density than the individual samples sequence method. The median codon coverage for drug resistance-associated mutations in all four genes were greater than 3-fold higher in the pooled samples than in individual samples. The overall codon coverage distribution for pooled samples was wider than the individual samples. The sample pools with < 40 parasites/μL blood showed more discordance in AF calls for dhfr and mdr1 between the individual and pooled samples. This discordance in AF estimation may be due to low amounts of parasite DNA, which could lead to variable PCR amplification efficiencies. Grouping samples with an estimated ≥ 40 parasites/μL blood prior to pooling and deep sequencing yielded the expected population level AF. Pooling DNA samples based on estimates of > 40 parasites/μL prior to deep sequencing can be used for rapid genotyping of a large number of samples for these four genes and possibly other drug resistant markers in population-based studies. As Haiti is a low malaria transmission country with very few mixed infections and continued chloroquine sensitivity, the pooled sequencing approach can be used for routine national molecular surveillance of resistant parasites.

Louha, Swarnali (ORCID:0000000207778507)↗
DOE OSTI2025

PickerXL, A Large Deep Learning Model to Measure Arrival Times from Noisy Seismic Signals

Precisely measuring seismic arrival times is a labor-intensive task but is critical for both earthquake monitoring and subsurface imaging. Recently published deep learning models have demonstrated superior performance compared to traditional automatic approaches for picking arrival times. Although existing deep learning models have shown promising results, further advancements are necessary as their performance is not yet satisfactory especially when applied to new regions and station networks. Increasing model size has led to improved performance in other machine learning applications. Here, we aimed to investigate whether enlarging deep learning models can increase performance on accepted benchmarks. We trained three models of varying sizes, small (1X), medium (4X), and large (16X), using globally distributed local and regional earthquake signals and background noise waveforms from a benchmark dataset, Stanford Earthquake Dataset. Our results indicate that the largest model (PickerXL) outperforms both the smaller models and Seisbench implementation of the PhaseNet model, which has the same number of parameters as our small model. The PickerXL model’s enhanced capacity to extract complex patterns from seismograms contributes to its superior arrival picking abilities compared to the smaller model.

Chai, Chengping [Oak Ridge National Laboratory (OR↗
DOE OSTI2026

Phase Picking Beyond Local Distances: Where Waveform Filtering Still Matters for Deep Learning Models

Waveform filtering is a standard step in traditional seismic phase picking but often receives little attention in deep learning workflows, where models are typically trained on raw or minimally processed waveforms. Although this strategy performs well for local events, we show that performance can degrade substantially at regional distances. To address this limitation, we introduce two ways to incorporate multiband-filtered waveforms into deep learning phase pickers. The stacking approach concatenates filtered inputs along the channel dimension, while the branching approach processes each frequency band through a dedicated network branch before feature fusion. Both approaches can substantially improve performance across epicentral distances of 0° to 20°, but their effectiveness depends strongly on the selected frequency bands. Tests with multiple filter banks show that filter-bank design should be treated as part of model optimization rather than as a fixed preprocessing choice. Grad-CAM analysis of the branching model indicates that band importance varies among waveform samples and across training realizations, with only a weak overall preference for the 0.25 to 0.5 Hz band. These results show that no single filter band is consistently optimal and demonstrate that explicit feature engineering remains valuable for robust deep learning-based seismic phase picking.

58 GEOSCIENCES↗
DOE OSTI2014

Characterizing Natural Gas Hydrates in the Deep Water Gulf of Mexico: Applications for Safe Exploration and Production Activities

In 2000 Chevron began a project to learn how to characterize the natural gas hydrate deposits in the deep water portion of the Gulf of Mexico (GOM). Chevron is an active explorer and operator in the Gulf of Mexico and is aware that natural gas hydrates need to be understood to operate safely in deep water. In August 2000 Chevron worked closely with the National Energy Technology Laboratory (NETL) of the United States Department of Energy (DOE) and held a workshop in Houston, Texas to define issues concerning the characterization of natural gas hydrate deposits. Specifically, the workshop was meant to clearly show where research, the development of new technologies, and new information sources would be of benefit to the DOE and to the oil and gas industry in defining issues and solving gas hydrate problems in deep water.

03 NATURAL GAS↗
DOE OSTI2014

Deep Vadose Zone Treatability Test for the Hanford Central Plateau: Interim Post-Desiccation Monitoring Results, Fiscal Year 2014

Over decades of operation, the U.S. Department of Energy (DOE) and its predecessors have released nearly 2 trillion L (450 billion gal.) of liquid into the vadose zone at the Hanford Site. Much of this discharge of liquid waste into the vadose zone occurred in the Central Plateau, a 200 km 2 (75 mi 2 ) area that includes approximately 800 waste sites. Some of the inorganic and radionuclide contaminants in the deep vadose zone at the Hanford Site are at depths below the limit of direct exposure pathways, but may need to be remediated to protect groundwater. The Tri-Party Agencies (DOE, U.S. Environmental Protection Agency, and Washington State Department of Ecology) established Milestone M 015 50, which directed DOE to submit a treatability test plan for remediation of technetium-99 (Tc-99) and uranium in the deep vadose zone. These contaminants are mobile in the subsurface environment and have been detected at high concentrations deep in the vadose zone, and at some locations have reached groundwater. Testing technologies for remediating Tc-99 and uranium will also provide information relevant for remediating other contaminants in the vadose zone. A field test of desiccation is being conducted as an element of the DOE test plan published in March 2008 to meet Milestone M 015 50. The active desiccation portion of the test has been completed. Monitoring data have been collected at the field test site during the post-desiccation period and are reported herein. This is an interim data summary report that includes about 3 years of post-desiccation monitoring data. The DOE field test plan proscribes a total of 5 years of post-desiccation monitoring.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2014

Phase 2 Methyl Iodide Deep-Bed Adsorption Tests

Nuclear fission produces fission products (FPs) and activation products, including iodine-129, which could evolve into used fuel reprocessing facility off-gas systems, and could require off-gas control to limit air emissions to levels within acceptable emission limits. Research, demonstrations, and some reprocessing plant experience have indicated that diatomic iodine can be captured with efficiencies high enough to meet regulatory requirements. Research on the capture of organic iodides has also been performed, but to a lesser extent. Several questions remain open regarding the capture of iodine bound in organic compounds. Deep-bed methyl iodide adsorption testing has progressed according to a multi-laboratory methyl iodide adsorption test plan. This report summarizes the second phase of methyl iodide adsorption work performed according to this test plan using the deep-bed iodine adsorption test system at the Idaho National Laboratory (INL), performed during the second half of Fiscal Year (FY) 2014. Test results continue to show that methyl iodide adsorption using AgZ can achieve total iodine decontamination factors (DFs, ratios of uncontrolled and controlled total iodine levels) above 1,000, until breakthrough occurred. However, mass transfer zone depths are deeper for methyl iodide adsorption compared to diatomic iodine (I2) adsorption. Methyl iodide DFs for the Ag Aerogel test adsorption efficiencies were less than 1,000, and the methyl iodide mass transfer zone depth exceeded 8 inches. Additional deep-bed testing and analyses are recommended to (a) expand the data base for methyl iodide adsorption under various conditions specified in the methyl iodide test plan, and (b) provide more data for evaluating organic iodide reactions and reaction byproducts for different potential adsorption conditions.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2015

Handling and Emplacement Options for Deep Borehole Disposal Conceptual Design

This report presents conceptual design information for a system to handle and emplace packages containing radioactive waste, in boreholes 16,400 ft deep or possibly deeper. Its intended use is for a design selection study that compares the costs and risks associated with two emplacement methods: drill-string and wireline emplacement. The deep borehole disposal (DBD) concept calls for siting a borehole (or array of boreholes) that penetrate crystalline basement rock to a depth below surface of about 16,400 ft (5 km). Waste packages would be emplaced in the lower 6,560 ft (2 km) of the borehole, with sealing of appropriate portions of the upper 9,840 ft (3 km). A deep borehole field test (DBFT) is planned to test and refine the DBD concept. The DBFT is a scientific and engineering experiment, conducted at full-scale, in-situ, without radioactive waste. Waste handling operations are conceptualized to begin with the onsite receipt of a purpose-built Type B shipping cask, that contains a waste package. Emplacement operations begin when the cask is upended over the borehole, locked to a receiving flange or collar. The scope of emplacement includes activities to lower waste packages to total depth, and to retrieve them back to the surface when necessary for any reason. This report describes three concepts for the handling and emplacement of the waste packages: 1) a concept proposed by Woodward-Clyde Consultants in 1983; 2) an updated version of the 1983 concept developed for the DBFT; and 3) a new concept in which individual waste packages would be lowered to depth using a wireline. The systems described here could be adapted to different waste forms, but for design of waste packaging, handling, and emplacement systems the reference waste forms are DOE-owned high- level waste including Cs/Sr capsules and bulk granular HLW from fuel processing.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2015

Active Suppression of Drilling System Vibrations For Deep Drilling

The dynamic stability of deep drillstrings is challenged by an inability to impart controllability with ever-changing conditions introduced by geology, depth, structural dynamic properties and operating conditions. A multi-organizational LDRD project team at Sandia National Laboratories successfully demonstrated advanced technologies for mitigating drillstring vibrations to improve the reliability of drilling systems used for construction of deep, high-value wells. Using computational modeling and dynamic substructuring techniques, the benefit of controllable actuators at discrete locations in the drillstring is determined. Prototype downhole tools were developed and evaluated in laboratory test fixtures simulating the structural dynamic response of a deep drillstring. A laboratory-based drilling applicability demonstration was conducted to demonstrate the benefit available from deployment of an autonomous, downhole tool with self-actuation capabilities in response to the dynamic response of the host drillstring. A concept is presented for a prototype drilling tool based upon the technical advances. The technology described herein is the subject of U.S. Patent Application No. 62219481, entitled "DRILLING SYSTEM VIBRATION SUPPRESSION SYSTEMS AND METHODS", filed September 16, 2015.

Raymond, David W.↗
DOE OSTI2016

The Livermore Brain: Massive Deep Learning Networks Enabled by High Performance Computing

The proliferation of inexpensive sensor technologies like the ubiquitous digital image sensors has resulted in the collection and sharing of vast amounts of unsorted and unexploited raw data. Companies and governments who are able to collect and make sense of large datasets to help them make better decisions more rapidly will have a competitive advantage in the information era. Machine Learning technologies play a critical role for automating the data understanding process; however, to be maximally effective, useful intermediate representations of the data are required. These representations or “features” are transformations of the raw data into a form where patterns are more easily recognized. Recent breakthroughs in Deep Learning have made it possible to learn these features from large amounts of labeled data. The focus of this project is to develop and extend Deep Learning algorithms for learning features from vast amounts of unlabeled data and to develop the HPC neural network training platform to support the training of massive network models. This LDRD project succeeded in developing new unsupervised feature learning algorithms for images and video and created a scalable neural network training toolkit for HPC. Additionally, this LDRD helped create the world’s largest freely-available image and video dataset supporting open multimedia research and used this dataset for training our deep neural networks. This research helped LLNL capture several work-for-others (WFO) projects, attract new talent, and establish collaborations with leading academic and commercial partners. Finally, this project demonstrated the successful training of the largest unsupervised image neural network using HPC resources and helped establish LLNL leadership at the intersection of Machine Learning and HPC research.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2017

Deep Boreholes Seals Subjected to High P, T conditions – Preliminary Experimental Studies

The objective of this planned experimental work is to evaluate physio-chemical processes for ‘seal’ components and materials relevant to deep borehole disposal. These evaluations will encompass multi-laboratory efforts for the development of seals concepts and application of Thermal-Mechanical-Chemical (TMC) modeling work to assess barrier material interactions with subsurface fluids, their stability at high temperatures, and the implications of these processes to the evaluation of thermal limits. Deep borehole experimental work will constrain the Pressure, Temperature (P, T) conditions which “seal” material will experience in deep borehole crystalline rock repositories. The rocks of interest to this study include the silicic (granitic gneiss) end members. The experiments will systematically add components to capture discrete changes in both water and EBS component chemistries.

54 ENVIRONMENTAL SCIENCES↗