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 505 records · Page 28

A Deep Multimodal Representation Learning Framework for Accurate Molecular Properties Prediction

Drug discovery is a complex and challenging process, requiring the optimization of candidate compounds to identify those with the potential to become safe and effective drugs. Predicting molecular properties is an indispensable step in the drug discovery pipeline. Traditionally, this process is costly and time-intensive, involving multiple rounds of experiments and clinical trials, rendering it impractical for every candidate compound. Deep learning techniques have emerged as a promising approach to drug discovery to reduce the cost and time required to identify novel drugs. However, prevalent research in deep learning models focused on predicting molecular properties has primarily fixated on single-modal models, which utilize a single modality of data, neglecting the potential benefits of combining different data modalities. To overcome this limitation, we introduce MRL-Mol: a deep \textbf{M}ultimodal \textbf{R}epresentation \textbf{L}earning framework for accurate \textbf{Mol}ecular properties prediction. MRL-Mol harnesses three data modalities: sequence, graph, and image, augmenting the depth of comprehension. Leveraging a large-scale unlabeled dataset~($\sim$1M unique molecules), we pretrain MRL-Mol to extract inter- and intra-modal information. Our study demonstrates the superior performance of MRL-Mol in predicting molecular properties across six benchmark datasets, including both classification and regression tasks. Notably, MRL-Mol outperforms other state-of-the-art molecular properties prediction models. These findings suggest that by combining information from multiple data modalities, MRL-Mol can comprehend molecules better than single-modal deep learning models and identify molecular properties with better accuracy.

Yang, Yuxin↗

Research on Deformation Law of Deep Foundation Pit of Station in Core Region of Saturated Soft Loess Based on Monitoring

Saturated soft loess has a large pore structure, high compressibility, low strength, fluid plastic state, and poor engineering properties. It is still one of the key problems that engineering needs to solve. In order to study the influence of deep foundation pit excavation in the saturated soft loess area on the deformation of foundation pits, the deformation laws of ground settlement, enclosure structure, and supporting axial force were clarified based on the field tests on the deformation characteristics of deep foundation pits in areas with the high-water level in saturated soft loess, combined with geological conditions and on-site construction procedures. The results indicate the following: water supply and construction process were found to be the main factor in changing the surface settlement curve of deep foundation pits in saturated soft loess; increasing the construction speed of the pit bottom floor, inverted braces, floor frame beams, and sidewall frame beams to close the structure, which is conducive to restraining the deformation of the continuous underground wall and foundation pits in similar areas. In the initial stage of support layout, the axial force of steel support tends to increase too fast or even exceed the standard control value. Therefore, a reasonable preadding axial force is an effective means to control the deformation of the continuous underground wall and the axial force of the steel support. The current research results may provide a reference for constructing deep foundation pits in similar areas.

Wang, Xueyan↗

Deep Lynx MOOSE Adapter

The Deep Lynx MOOSE Adapter connects the Deep Lynx data warehouse with any MOOSE executable. The Adapter can receive events from Deep Lynx and will take incoming data to format a template input file for the MOOSE executable. Returns from the MOOSE run are sent back to Deep Lynx for use by other applications.

Browning, JerenM↗

HPS-RL: Hyperparameter tuning for deep RL applications (HPS-RL) v1

Genetic Algorithms meets Deep RL for Hyperparameters Hyperparameter optimization and architecture search can easily become cumbersome and finding the right hyperparameters can seriously impact the robustness of the deep RL application being developed. We use genetic algorithms to evolve optimum deep RL architectures in a scalable manner. HPS-RL is designed to work with multiple gym enviornments, allow users to test their own optimization functions and tune multi-objective parameters in multiple deep RL algorithms. HPS-RL uses multi-threading and is being extended with mpipy for distributed processing on HPC. https://arxiv.org/abs/2201.11182

Kiran, Mariam↗

Influences of Environmental Relative Humidity and Horizontal Scale of Subcloud Ascent on Deep Convective Initiation

This study examines two factors impacting initiation of moist deep convection: free-tropospheric environmental relative humidity (φ E ) and horizontal scale of subcloud ascent (R sub ), the latter exerting a dominant control on cumulus cloud width. A simple theoretical model is used to formulate a “scale selection” hypothesis: that a minimum R sub is required for moist convection to go deep, and that this minimum scale decreases with increasing φ E . Specifically, the ratio of R 2 sub to saturation deficit (1 - φ E ) must exceed a certain threshold value that depends on cloud-layer environmental lapse rate. Idealized, large-eddy simulations of moist convection forced by horizontally varying surface fluxes show strong sensitivity of maximum cumulus height to both φ E and R sub consistent with the hypothesis. Increasing R sub by only 300–400 m can lead to a large increase (>5 km) in cloud height. A passive tracer analysis shows that the bulk fractional entrainment rate decreases rapidly with R sub but depends little on φ E . However, buoyancy dilution increases as either R sub or φ E decreases; buoyancy above the level of free convection is rapidly depleted in dry environments when R sub is small. While deep convective initiation occurs with an increase in relative humidity of the near environment from moistening by earlier convection, the importance of this moisture preconditioning is inconclusive as it is accompanied by an increase in R sub . Overall, it is concluded that small changes to R sub driven by external forcing or by convection itself could be a dominant regulator of deep convective initiation.

54 ENVIRONMENTAL SCIENCES↗

The Influence of Shear on Deep Convection Initiation. Part I: Theory

Abstract This article introduces a novel hypothesis for the role of vertical wind shear (“shear”) in deep convection initiation (DCI). In this hypothesis, initial moist updrafts that exceed a width and shear threshold will “root” within a progressively deeper steering current with time, increase their low-level cloud-relative flow and inflow, widen, and subsequently reduce their susceptibility to entrainment-driven dilution, evolving toward a quasi-steady self-sustaining state. In contrast, initial updrafts that do not exceed the aforementioned thresholds experience suppressed growth by shear-induced downward pressure gradient accelerations, will not root in a deep-enough steering current to increase their inflow, will narrow with time, and will succumb to entrainment-driven dilution. In the latter case, an externally driven lifting mechanism is required to sustain deep convection, and deep convection will not persist in the absence of such lifting mechanism. A theoretical model is developed from the equations of motion to further explore this hypothesis. The model indicates that shear generally suppresses DCI, raising the initial subcloud updraft width that is necessary for it to occur. However, there is a pronounced bifurcation in updraft growth in the model after the onset of convection. Sufficiently wide initial updrafts grow and eventually achieve a steady state. In contrast, insufficiently wide initial updrafts shrink with time and eventually decay completely without external support. A sharp initial updraft radius threshold discriminates between these two outcomes. Thus, consistent with our hypothesis and observations, shear inhibits DCI in some situations, but facilitates it in others.

42 ENGINEERING↗

Environmental controls on simulated deep moist convection initiation occurring during RELAMPAGO-CACTI

This study synthesizes the results of 13 high-resolution simulations of deep convective updrafts forming over idealized terrain using environments observed during the RELAMPAGO and CACTI field projects. Using composite soundings from multiple observed cases, and variations upon them, we explore the sensitivity of updraft properties (e.g., size, buoyancy, and vertical pressure gradient forces) to influences of environmental relative humidity, wind shear, and mesoscale orographic forcing that support or suppress deep convection initiation (CI). Emphasis is placed on differentiating physical processes affecting the development of updrafts (e.g., entrainment-driven dilution of updrafts) in environments typifying observed successful and null (i.e., no CI despite affirmative operational forecasts) CI events. Thermally-induced mesoscale orographic lift favors the production of deep updrafts originating from ~1–2-km-wide boundary layer thermals. Simulations without terrain forcing required much larger ( ~5-km-wide) thermals to yield precipitating convection. CI outcome was quite sensitive to environmental relative humidity; updrafts with increased buoyancy, depth, and intensity thrived in otherwise inhospitable environments by simply increasing the free tropospheric relative humidity. This implicates the entrainment of free-tropospheric air into updrafts as a prominent governor of CI, consistent with previous studies. Sensitivity of CI to the environmental wind is manifested by: 1) low-level flow affecting the strength and depth of mesoscale convergence along the terrain, and 2) clouds encountering updraft-suppressing pressure gradient forces while interacting with vertical wind shear in the free-troposphere. Among the ensemble of thermals occurring in each simulation, the widest deep updrafts in each simulation were the most sensitive to environmental influences.

54 ENVIRONMENTAL SCIENCES↗

Low-Level Mesoscale and Cloud-Scale Interactions Promoting Deep Convection Initiation

Data from scanning radars, radiosondes, and vertical profilers deployed during three field campaigns are analyzed to study interactions between cloud-scale updrafts associated with initiating deep moist convection and the surrounding environment. Three cases are analyzed in which the radar networks permitted dual-Doppler wind retrievals in clear air preceding and during the onset of surface precipitation. These observations capture the evolution of (i) the mesoscale and boundary layer flow, and (ii) low-level updrafts associated with deep moist convection initiation (CI) events yielding sustained or short-lived precipitating storms. The elimination of convective inhibition did not distinguish between sustained and unsustained CI events, though the vertical distribution of convective available potential energy may have played a role. The clearest signal differentiating the initiation of sustained versus unsustained precipitating deep convection was the depth of the low-level horizontal wind convergence associated with the mesoscale flow feature triggering CI, a sharp surface wind shift boundary, or orographic upslope flow. The depth of the boundary layer relative to the height of the LFC failed to be a consistent indicator of CI potential. Widths of the earliest detectable low-level updrafts associated with sustained precipitating deep convection were ~3–5 km, larger than updrafts associated with surrounding boundary layer turbulence (~1–3 km wide). It is hypothesized that updrafts of this larger size are important for initiating cells to survive the destructive effects of buoyancy dilution via entrainment.

54 ENVIRONMENTAL SCIENCES↗

Time-lapse seismic data inversion for estimating reservoir parameters using deep learning

Geologic carbon sequestration involves the injection of captured carbon dioxide ([Formula: see text]) into subsurface formations for long-term storage. The movement and fate of the injected [Formula: see text] plume is of great concern to regulators because monitoring helps to identify potential leakage zones and determines the possibility of safe long-term storage. To address this concern, we design a deep-learning framework for [Formula: see text] saturation monitoring to determine the geologic controls on the storage of the injected [Formula: see text]. We use different combinations of porosities and permeabilities for a given reservoir to generate saturation and velocity models. We train the deep-learning model with a few time-lapse seismic images and their corresponding changes in saturation values for a particular [Formula: see text] injection site. The deep-learning model learns the mapping from the change in the time-lapse seismic response to the change in [Formula: see text] saturation during the training phase. We then apply the trained model to data sets comprising different time-lapse seismic image slices (corresponding to different time instances) generated using different porosity and permeability distributions that are not part of the training to estimate the [Formula: see text] saturation values along with the plume extent. Our algorithm provides a deep-learning assisted framework for the direct estimation of [Formula: see text] saturation values and plume migration in heterogeneous formations using the time-lapse seismic data. Our method improves the efficiency of time-lapse inversion by streamlining the large number of intermediate steps in the conventional time-lapse inversion workflow. This method also helps to incorporate the geologic uncertainty for a given reservoir by accounting for the statistical distribution of porosity and permeability during the training phase. Tests on different examples verify the effectiveness of our approach.

Geochemistry & Geophysics↗

Deep Neural Network Algorithm for CMC Microstructure Characterization and Variability Quantification

Microstructure characterization and variability quantification are crucial for understanding ceramic matrix composites (CMCs) mechanical behavior and deformation mechanisms across length scales. Traditionally, analyses of the micrographs obtained from microscopy are labor-intensive. However, with the vast improvement in computer vision (CV) and deep learning (DL), an automated algorithm can be designed to extract essential microstructure variability from micrographs which can then be used to construct a statistically representative volume element (SRVE). The DL-based algorithm spans the taxonomy of microstructure analyses, including semantic segmentation of microstructure constituents, secondary phases, matrix/fiber interface, and defects, and quantifying the microstructure variability in terms of probability distributions. In this work, C/SiNC and SiC/SiNC CMCs microstructures are semantically segmented through a deep convolutional neural network, followed by variability quantification through the implementation of a fully connected regression layer, hence forming a deep regression network. The deep regression network operates in a feedforward regime, in which the neuron output signal traverses through the network in a unidirectional manner. The weight tensor associated with each layer is updated through a backpropagation stochastic gradient descent approach. The input gray-scale image obtained through in-house scanning electron microscope and confocal microscope micrographs is augmented through affine transformations to increase the training set size, which is then processed through four strided convolutional layers. This compresses the image resolution by half at each layer while increasing the image depth by applying different filters (image encoding). The class activation maps (CAMs) corresponding to the applied filters highlight the key architectural features and assist with the semantic segmentation of the microstructure.

Hamza, Mohamed H.↗

Deep Borehole Disposal Research: Geological Data Evaluation Alternative Waste Forms and Borehole Seals

This report documents deep borehole disposal research during FY2014, as directed by U.S. Department of Energy (DOE) Used Fuel Disposition (UFD) Campaign. These research efforts are principally directed at advancing the deep borehole disposal project to the implementation of a full-scale Research, Development, and Demonstration (RD&D) project. Activities of particular relevance to this goal include evaluation of guidelines for selection of a deep borehole field test site, analyses of deep borehole disposal of alternative waste forms, and technical planning for borehole seals research.

Arnold, Bill W.↗

Deep Borehole Field Test Specifications

This report documents conceptual design development for the Deep Borehole Field Test (DBFT), mainly the test packages (not containing waste) and the system for demonstrating emplacement and retrieval of those packages in the Field Test Borehole (FTB). For the DBFT to have demonstration value, it must be based on conceptualization of a deep borehole disposal (DBD) system for specific waste forms. This document therefore describes a current reference DBD concept, and analyzes key design options for disposal, to guide selection of options for the DBFT. The most important of these options is the emplacement mode, i.e. whether packages are emplaced using a wireline or a string of drill pipe (with a drill rig). This choice is analyzed using cost and risk models, in Sections 5 and 6. Other emplacement mode options are also identified and discussed. The reference DBD concept and the analysis of waste packaging and emplacement options, are used to develop requirements and assumptions for the DBFT and to recommend DBFT specifications. Design issues are identified, and priorities are developed for further conceptual design development and additional engineering analysis, anticipating future design activities. Conceptual design development is part of a process that proceeds in three stages: 1) conceptual design including feasibility studies; 2) preliminary design that includes technical and cost information necessary for final design; and 3) final design sufficient for fabrication or construction. The DBFT engineering demonstration will follow such an evolution. Whereas design evolution typically begins with bench-scale and pilot-scale investigations proceeding to conceptual, preliminary, and final designs, the DBFT can proceed directly to design because of extensive previous work and published literature on scientific drilling, characterization methods, waste packaging and handling, industrial deep-hole drilling and construction, and downhole operations. Hence it is anticipated that this report will lead to completion of conceptual design, then preliminary and final design, fabrication and testing, and demonstration of waste emplacement in a deep borehole.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Deep Borehole Field Test Requirements and Controlled Assumptions.

This document presents design requirements and controlled assumptions intended for use in the engineering development and testing of: 1) prototype packages for radioactive waste disposal in deep boreholes; 2) a waste package surface handling system; and 3) a subsurface system for emplacing and retrieving packages in deep boreholes. Engineering development and testing is being performed as part of the Deep Borehole Field Test (DBFT; SNL 2014a). This document presents parallel sets of requirements for a waste disposal system and for the DBFT, showing the close relationship. In addition to design, it will also inform planning for drilling, construction, and scientific characterization activities for the DBFT. The information presented here follows typical preparations for engineering design. It includes functional and operating requirements for handling and emplacement/retrieval equipment, waste package design and emplacement requirements, borehole construction requirements, sealing requirements, and performance criteria. Assumptions are included where they could impact engineering design. Design solutions are avoided in the requirements discussion. Deep Borehole Field Test Requirements and Controlled Assumptions July 21, 2015 iv ACKNOWLEDGEMENTS This set of requirements and assumptions has benefited greatly from reviews by Gordon Appel, Geoff Freeze, Kris Kuhlman, Bob MacKinnon, Steve Pye, David Sassani, Dave Sevougian, and Jiann Su.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Task Order 22 – Engineering and Technical Support, Deep Borehole Field Test. AREVA Summary Review Report

Under Task Order 22 of the industry Advisory and Assistance Services (A&AS) Contract to the Department of Energy (DOE) DE-NE0000291, AREVA has been tasked with providing assistance with engineering, analysis, cost estimating, and design support of a system for disposal of radioactive wastes in deep boreholes (without the use of radioactive waste). As part of this task order, AREVA was requested, through a letter of technical direction, to evaluate Sandia National Laboratory’s (SNL’s) waste package borehole emplacement system concept recommendation using input from DOE and SNL. This summary review report (SRR) documents this evaluation, with its focus on the primary input document titled: “Deep Borehole Field Test Specifications/M2FT-15SN0817091” Rev. 1 [1], hereafter referred to as the “M2 report.” The M2 report focuses on the conceptual design development for the Deep Borehole Field Test (DBFT), mainly the test waste packages (WPs) and the system for demonstrating emplacement and retrieval of those packages in the Field Test Borehole (FTB). This SRR follows the same outline as the M2 report, which allows for easy correlation between AREVA’s review comments, discussion, potential proposed alternatives, and path forward with information established in the M2 report. AREVA’s assessment focused on three primary elements of the M2 report: the conceptual design of the WPs proposed for deep borehole disposal (DBD), the mode of emplacement of the WP into DBD, and the conceptual design of the DBFT. AREVA concurs with the M2 report’s selection of the wireline emplacement mode specifically over the drill-string emplacement mode and generically over alternative emplacement modes. Table 5-1 of this SRR compares the pros and cons of each emplacement mode considered viable for DBD. The primary positive characteristics of the wireline emplacement mode include: (1) considered a mature technology; (2) operations are relatively simple; (3) probability of a radiological release due to off-normal events are relatively low; (4) costs are relatively low; and (5) maintenance activities are relatively simple. The primary drawback associated with the wireline emplacement mode for DBD is the number of emplacement trips-in to the borehole, which results in a relatively higher probability for a drop event. Fortunately, the WPs can be engineered with impact limiters that will minimize the likelihood of a breach of the WP due to a drop. The WP designs presented in the M2 report appear to be focused on compatibility with the drill-string emplacement mode (e.g., the threaded connections). With the recommendation that the wireline emplacement mode be utilized for the DBFT, some changes may be warranted to these WPs. For example, the development of a WP release connection that is more reliable than the currently credited connection, which is considered to have a high failure probability, and the integration of an impact limiter into its design. The M2 report states the engineering demonstration of the DBFT will occur in the FTB over a 4-year period. AREVA recommends development and testing of the WP emplacement handling equipment occur separately (but concurrently, if not earlier) from the FTB at a mock-up facility. The separation of this activity would prevent schedule interference between the science and engineering thrusts of the project. Performing tests in a mock-up facility would allow additional control and observation compared to the FTB. The mock-up facility could also be utilized as a training facility for future operations. Terminal velocity and impact limiter testing would require the FTB for testing, since these areas would be difficult to reproduce in a limited depth mock-up. Although only at the end of the conceptual stage of design development, DBD appears to be a viable solution for some waste forms produced by the nuclear industry. However, regulatory requirements have yet to be established for pre- and post-closure performance of DBD and should be established as soon as possible. Some of the main areas of focus from a regulatory perspective include: (1) establishing acceptable performance requirements for the long-term behavior of DBD; (2) determining acceptable borehole abandonment criteria; (3) establishing retrievability requirements; (4) developing a consensus on the factor of safety (FoS) for the emplacement mode and WP; and (5) establishing safety and safeguards performance requirements for DBD. Although conservative requirements have been utilized to provide the foundation for the conceptual design of DBD, regulatory requirements and feedback are necessary to confirm recommendations made herein and to ensure the long-term performance of DBD is acceptable. The combination of the M2 report and this SRR is intended to facilitate the completion of the conceptual design for DBD for the Cs and Sr capsules and calcined waste forms. Using the conceptual design, preliminary design activities (the second stage of a three-stage process described in the M2 report) can proceed and the DBFT utilized to support, demonstrate, and confirm engineering elements of this design.

42 ENGINEERING↗

FY-2015 Methyl Iodide Deep-Bed Adsorption Test Report

Nuclear fission produces fission 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. Deep-bed methyl iodide adsorption testing has continued in Fiscal Year 2015 according to a multi-laboratory methyl iodide adsorption test plan. Updates to the deep-bed test system have also been performed to enable the inclusion of evaporated HNO 3 and increased NO 2 concentrations in future tests. This report summarizes the result of those activities. Test results showed that iodine adsorption from gaseous methyl iodide using reduced silver zeolite (AgZ) resulted in initial iodine decontamination factors (DFs, ratios of uncontrolled and controlled total iodine levels) under 1,000 for the conditions of the long-duration test performed this year (45 ppm CH3I, 1,000 ppm each NO and NO 2 , very low H 2 O levels [3 ppm] in balance air). The mass transfer zone depth exceeded the cumulative 5-inch depth of 4 bed segments, which is deeper than the 2-4 inch depth estimated for the mass transfer zone for adsorbing I 2 using AgZ in prior deep-bed tests. The maximum iodine adsorption capacity for the AgZ under the conditions of this test was 6.2% (6.2 g adsorbed I per 100 g sorbent). The maximum Ag utilization was 51%. Additional deep-bed testing and analyses are recommended to (a) expand the data base for methyl iodide adsorption and (b) provide more data for evaluating organic iodide reactions and reaction byproducts for different potential adsorption conditions.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Deep Vadose Zone Treatability Test of Soil Desiccation for the Hanford Central Plateau: Final Report

Some of the inorganic and radionuclide contaminants in the deep vadose zone at the Hanford Site are at depths where direct exposure pathways are not of concern, but may need to be remediated to protect groundwater. The Department of Energy developed a treatability test program for technologies to address Tc-99 and uranium in the deep vadose zone. These contaminants are mobile in the subsurface environment, have been detected at high concentrations deep in the vadose zone, and at some locations have reached groundwater. The treatability test of desiccation described herein was conducted as an element of the deep vadose zone treatability test program. Desiccation was shown to be a potentially effective vadose zone remediation technology to protect groundwater when used in conjunction with a surface infiltration barrier.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Large Diameter Deep Borehole (LDDB) Disposal Design Option for Vitrified High-Level Waste (HLW) and Granular Wastes

This study considers the feasibility of large diameter deep boreholes for waste disposal. The conceptual approach considers examples of deep large diameter boreholes that have been successfully drilled, and also other deep borehole designs proposed in the literature. The objective for large diameter boreholes would be disposal of waste packages with diameters of 22 to 29 inches, which could enable disposal of waste forms such as existing vitrified high level waste. A large-diameter deep borehole design option would also be amenable to other waste forms including calcine waste, treated Na-bonded and Na-bearing waste, and Cs and Sr capsules.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Large Diameter Deep Borehole (LDDB) Disposal Design Option for Vitrified High-Level Waste (HLW) and Granular Wastes

This study considers the feasibility of large diameter deep boreholes for waste disposal. The conceptual approach considers examples of deep large diameter boreholes that have been successfully drilled, and also other deep borehole designs proposed in the literature. The objective for large diameter boreholes would be disposal of waste packages with diameters of 22 to 29 inches, which could enable disposal of waste forms such as existing vitrified high level waste. A large-diameter deep borehole design option would also be amenable to other waste forms including calcine waste, treated Na-bonded and Na-bearing waste, and Cs and Sr capsules.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗