SEARCH · Engineering Papers

Results for “deep well”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

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

At least 613 records · Page 34

All sources NASA NTRS DOE OSTI

DOE OSTI2024

Deep energy-pressure regression for a thermodynamically consistent EOS model

Abstract In this paper, we aim to explore novel machine learning (ML) techniques to facilitate and accelerate the construction of universal equation-Of-State (EOS) models with a high accuracy while ensuring important thermodynamic consistency. When applying ML to fit a universal EOS model, there are two key requirements: (1) a high prediction accuracy to ensure precise estimation of relevant physics properties and (2) physical interpretability to support important physics-related downstream applications. We first identify a set of fundamental challenges from the accuracy perspective, including an extremely wide range of input/output space and highly sparse training data. We demonstrate that while a neural network (NN) model may fit the EOS data well, the black-box nature makes it difficult to provide physically interpretable results, leading to weak accountability of prediction results outside the training range and lack of guarantee to meet important thermodynamic consistency constraints. To this end, we propose a principled deep regression model that can be trained following a meta-learning style to predict the desired quantities with a high accuracy using scarce training data. We further introduce a uniquely designed kernel-based regularizer for accurate uncertainty quantification. An ensemble technique is leveraged to battle model overfitting with improved prediction stability. Auto-differentiation is conducted to verify that necessary thermodynamic consistency conditions are maintained. Our evaluation results show an excellent fit of the EOS table and the predicted values are ready to use for important physics-related tasks.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2026

Community detection robustness of graph neural networks

Graph neural networks (GNNs) are increasingly widely used for community detection in attributed networks. They combine structural topology with node attributes through message passing and pooling. However, their robustness or lack thereof with respect to different perturbations and targeted attacks in conjunction with community detection tasks is not well understood. To shed light on latent mechanisms behind GNN sensitivity on community detection tasks, we conduct a systematic computational evaluation of six widely adopted GNN architectures graph convolutional network, graph attention network, graph sample and aggregate (GraphSAGE), differentiable pooling (DiffPool), minimum cut pooling (MinCUT), and deep modularity networks (DMoN). The analysis covers three perturbation categories: node attribute manipulations, edge topology distortions, and adversarial attacks. We use element-centric similarity as the evaluation metric on synthetic benchmarks and real-world citation networks. Our findings indicate that supervised GNNs tend to achieve higher baseline accuracy, while unsupervised methods, particularly DMoN, maintain stronger resilience under targeted and adversarial perturbations. Furthermore, robustness appears to be strongly influenced by community strength, with well-defined communities reducing performance loss. Across all models, node attribute perturbations associated with targeted edge deletions and shifts in attribute distributions tend to cause the largest degradation in community recovery. These findings highlight important trade-offs between accuracy and robustness in GNN-based community detection and offer insights into selecting architectures resilient to noise and adversarial attacks.

Goel, Jaidev [Virginia Polytechnic Inst. and State↗

DOE OSTI2023

Techno-Economic Analysis for a Potential Geothermal District Heating System in Tuttle, Oklahoma

Geothermal deep direct use (DDU) has potential across a wide swath of the United States but is underutilized due to challenging project economics associated with developing a deep geothermal resource for a large-scale and variable heat demand. The National Renewable Energy Laboratory (NREL) and University of Oklahoma evaluated the feasibility of a geothermal district heating (GDH) and cooling system in two schools and 250 houses by utilizing existing oil and gas (O&G) wells in Tuttle, Oklahoma. Heating and cooling demand in the two schools and a typical single-family house were modeled using EnergyPlus building energy simulation software. The modeling results indicated that annual heating demand in two schools and 250 houses is approximately 2.61 GWhth, and cooling demand in the two schools is approximately 2.65 GWhth. In this scope, the techno-economic analysis (TEA) was conducted using the GEOPHIRES tool combined with the TOUGH2 reservoir simulator. The reservoir performance, including geothermal heat production capacity, was modeled by the reservoir simulator TOUGH2. Then, levelized cost of heat (LCOH) was calculated using GEOPHIRES version 3.0, which includes new features such as hourly heat load optimization and peak performance evaluation. Geothermal reservoir temperature was estimated as 90.5 degrees C at a total depth of 3.3 km by the regional average temperature gradient of 22.8 degrees C/km and validated by cation geothermometer calculations. Four production scenarios with two different well configurations and two different heat load profiles have been developed for well flow rates ranging between 3.1 kg/s and 9.3 kg/s. The LCOH of the district heating and cooling system was calculated between $95 and $210/MWh ($28/MMBtu to $62/MMBtu) for four different production scenarios. Typical natural gas prices for residential customers in Oklahoma have ranged from 9 to 19 $/MMBtu over the past decade, which indicates a challenge for deployment of such a GDH system.

deep direct-use↗

DOE OSTI2022

Hicks Pries, Sulman, et al 2018. In situ incubation of 13C-labeled litter in three soil pits at Blodgett Forest, CA from 2013 to 2016

Even though over half of the world's soil organic carbon (SOC) is stored in subsoils (>20 cm deep), and the old ages of subsoil OC indicate its cycling differs from surface SOC, there are few studies examining in situ decomposition processes in deep soils. The purpose of this dataset is to elucidate these processes. In this study we added 13C-labeled fine roots to 15, 55, and 95 cm depths of a well-characterized coniferous forest Alfisol and monitored the amount of root-derived C remaining over 6, 12, and 30 months. We recovered the root-derived C in microbial phospholipid fatty acids (PLFAs) after 6 months and in coarse (>2 mm) particulate, fine (<2 mm) particulate, and dense, mineral-associated pools after 6, 12, and 30 months. Overall, root decomposition in the first 6 months was similar among all depths but significantly diverged at 30 months with faster decomposition at 15 cm than at 95 cm. There were more fungal and Gram negative-associated PLFAs at 15 cm than at 95 cm, and 13C analysis revealed those microbial groups preferred the added root carbon to native SOC. Mineral-associations were not the cause of slower decomposition at depth because similar amounts of applied root C was recovered in the dense fraction at all depths. The largest difference among depths was in the amount of root C recovered in the coarse particulate fraction, which was greater at 95 cm (50%) than at 15 cm (15%). Slower decomposition of the particulate pool at depth likely contributed to the increase in C:N ratios and depletion of δ13C values below 60 cm depth in our soil profiles. Simulations of these soils using the CORPSE model, which incorporates microbial priming effects and mineral stabilization of SOC, reproduced patterns of particulate and mineral-associated SOC over both time and depth and suggested that a lack of priming by root exudates at depth could account for the slower decomposition rate of particulate root material. Decomposition of deep particulate SOC may increase if root exudation or dissolved OC transport to depth increases.This dataset includes (1) characterization of the soil pits prior to litter addition, (2) characterization of how the litter changed after 6, 12, and 30 months, and (3) the CORPSE model structure, parameterization, and output.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2021

Fuzzy Simplicial Networks: A Topology-Inspired Model to Improve Task Generalization in Few-shot Learning

Deep learning has shown great success in settings with massive amounts of data but has struggled when data is limited. Few-shot learning algorithms, which seek to address this limitation, are designed to generalize well to new tasks with limited data. Typically, models are evaluated on unseen classes and datasets that are defined by the same fundamental task as they are trained for (e.g. category membership). One can also ask how well a model can generalize to fundamentally different tasks within a fixed dataset (for example: moving from category membership to tasks that involve detecting object orientation or quantity). To formalize this kind of shift we define a notion of “independence of tasks” and identify three new sets of labels for established computer vision datasets that test a model's ability to generalize to tasks which draw on orthogonal attributes in the data. We use these datasets to investigate the failure modes of metric-based few-shot models. Based on our findings, we introduce a new few-shot model called Fuzzy Simplicial Networks (FSN) which leverages a construction from topology to more flexibly represent each class from limited data. In particular, FSN models can not only form multiple representations for a given class but can also begin to capture the low-dimensional structure which characterizes class manifolds in the encoded space of deep networks. We show that FSN outperforms state-of-the-art models on the challenging tasks we introduce in this paper while remaining competitive on standard few-shot benchmarks.

deep learning↗

DOE OSTI2023

Techno-Economic Analysis for a Potential Geothermal District Heating System in Tuttle, Oklahoma: Preprint

deep direct-use↗

DOE OSTI2024

Robust Infrasound Detection via Deep Learning (RIDDL)

RIDDL is a suite of software tools that enable AI/ML analysis of infrasound data. Methods and capabilities include construction, evaluation, and application of models for infrasound signal analysis, construction of synthetic data useful for construction and evaluation, as well as various other advanced data science tools enabling infrasound signal detection and categorization as well as downstream analysis methods such as localization and characterization of detected sources.

Blom, Philip↗

DOE OSTI2022

Investigation of enhanced CO 2 storage in deep saline aquifers by WAG and brine extraction in the Minnelusa sandstone, Wyoming

Geological CO 2 sequestration in deep saline aquifers has been extendedly investigated to reach the goal of carbon neutral as large amount of CO 2 can be reduced in a short time. Here, this study investigates the feasibility of water-alternating-gas (WAG) injection and brine extraction on enhancing CO 2 storage in a target deep saline aquifer, Minnelusa Sandstone in the Powder River Basin (PRB) of Wyoming. An integrated numerical model is developed to account for four scenarios: (1) CO 2 continuous injection (CI) through one injection well, (2) WAG injection through one injection well, (3) CO 2 CI through one injection well and brine extraction through one producer, (4) WAG injection through one injection well and brine extraction through one producer. Simulation results suggest that WAG injection and brine extraction corporately make it possible to enhance CO 2 injectivity while securing CO 2 storage safety. For instance, WAG injection considerably reduces structural trapping contribution while enhances dissolved and residual trapping contributions. As for brine extraction, it can decrease the maximum averaged reservoir pressure by 37% and 22% for CI and WAG injection, respectively. Besides, sensitive analyses of the operational parameters for the fourth scenarios are performed. Results reveal that, when the amount of total CO 2 injection has been predetermined, CO 2 injection time and rate within each period of WAG should be small whereas it is preferable to have large water injection time and rate. This is to secure desirable dissolved and residual trapping contributions (store CO 2 with safety). Sensitive degree results confirm that CO 2 injection rate, water injection time, and CO 2 injection time of WAG injection exhibit significant effects on CO 2 storage whereas the impacts of producer bottom-hole pressure (BHP), water injection rate, and CO 2 -water injection time are relatively weaker. This study not only sheds light on achieving double-win goal: enhance CO 2 injectivity and store CO 2 with safety, but also can be a critical reference for other CO 2 storage in deep saline aquifers.

58 GEOSCIENCES↗

DOE OSTI2022

Geological activity shapes the microbiome in deep-subsurface aquifers by advection

Subsurface environments host diverse microorganisms in fluid-filled fractures; however, little is known about how geological and hydrological processes shape the subterranean biosphere. Here, we sampled three flowing boreholes weekly for 10 mo in a 1478-m-deep fractured rock aquifer to study the role of fracture activity (defined as seismically or aseismically induced fracture aperture change) and advection on fluid-associated microbial community composition. We found that despite a largely stable deep-subsurface fluid microbiome, drastic community-level shifts occurred after events signifying physical changes in the permeable fracture network. The community-level shifts include the emergence of microbial families from undetected to over 50% relative abundance, as well as the replacement of the community in one borehole by the earlier community from a different borehole. Null-model analysis indicates that the observed spatial and temporal community turnover was primarily driven by stochastic processes (as opposed to deterministic processes). We, therefore, conclude that the observed community-level shifts resulted from the physical transport of distinct microbial communities from other fracture(s) that outpaced environmental selection. Given that geological activity is a major cause of fracture activity and that geological activity is ubiquitous across space and time on Earth, our findings suggest that advection induced by geological activity is a general mechanism shaping the microbial biogeography and diversity in deep-subsurface habitats across the globe.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2023

Deep generative models for vehicle speed trajectories

Generating realistic vehicle speed trajectories is a crucial component in evaluating vehicle fuel economy and in predictive control of self-driving cars. Traditional generative models rely on Markov chain methods and can produce accurate synthetic trajectories but are subject to the curse of dimensionality. They do not allow to include conditional input variables into the generation process. In this paper, we show how extensions to deep generative models allow accurate and scalable generation. Proposed architectures involve recurrent and feed-forward layers and are trained using adversarial techniques. Our models are shown to perform well on generating vehicle trajectories using a model trained on GPS data from Chicago metropolitan area.

33 ADVANCED PROPULSION SYSTEMS↗

DOE OSTI2022

Strong Upper-Plate Heterogeneity at the Hikurangi Subduction Margin (North Island, New Zealand) Imaged by Adjoint Tomography

We use earthquake-based adjoint tomography to invert for three-dimensional structure of the North Island, New Zealand, and the adjacent Hikurangi subduction zone. The study area, having a shallow depth to the plate interface below the North Island, offers a rare opportunity for imaging material properties at an active subduction zone using land-based measurements. Starting from an initial model derived using ray tomography, we perform iterative model updates using spectral element and adjoint simulations to fit waveforms with periods ranging from 4–30 s. We perform 28 model updates using an L-BFGS optimization algorithm, improving data fit and introducing P- and S-wave velocity changes of up to ±30%. Resolution analysis using point spread functions show that our measurements are most sensitive to heterogeneities in the upper 30 km. The most striking velocity changes coincide with areas related to the active Hikurangi subduction zone. Lateral velocity structures in the upper 5 km correlate well with New Zealand geology. Here, the inversion reveals increased along-strike heterogeneity on the margin. In Cook Strait we observe a low-velocity zone interpreted as deep sedimentary basins. In the central North Island, low-velocity anomalies are linked to surface geology, and we relate velocity structures at depth to crustal magmatic activity below the Taupō Volcanic Zone.

58 GEOSCIENCES↗

DOE OSTI2021

Influence of the Kuroshio Intrusion on Deep Flow Intraseasonal Variability in the Northern South China Sea

Abstract Interactions between the open ocean and marginal seas have been suggested to be critical to the redistribution and dissipation of global energy. Here, we propose a mechanism for the upper open ocean influencing the deep flow in marginal seas that hinges on the formation and propagation of topographic Rossby waves (TRWs). Observations and high‐resolution simulations suggest substantial intraseasonal variability with periods of 5–60 days associated with the deep flow over continental slopes of the northern South China Sea (NSCS). These fluctuations generally account for over 40% of the total deep kinetic energy variability and the number can reach 70% over the slopes to the west of the Luzon Strait, southwest of the Dongsha Islands, and northeast of the Xisha Islands. By examining the spatiotemporal features of the fluctuations, we demonstrate that the intraseasonal variability of the deep flow in the NSCS is closely associated with TRWs. Using a recently developed multiscale energetics analysis in combination with a ray tracing model, we show that the energy sources of TRWs can be traced back to the east of the Dongsha Islands, where the Kuroshio intrusion and related eddies energize the TRWs primarily through pressure work. These waves propagate westward across the NSCS and drive the intraseasonal variability of the deep flow over continental slopes. Our findings highlight an energy pathway from the open ocean western boundary current to the abyssal marginal sea that could modulate regional circulation as well as exchanges between major ocean basins.

Quan, Qi↗

DOE OSTI2023

An open database of computed bulk ternary transition metal dichalcogenides

Abstract We present a dataset of structural relaxations of bulk ternary transition metal dichalcogenides (TMDs) computed via plane-wave density functional theory (DFT). We examined combinations of up to two chalcogenides with seven transition metals from groups 4–6 in octahedral (1T) or trigonal prismatic (2H) coordination. The full dataset consists of 672 unique stoichiometries, with a total of 50,337 individual configurations generated during structural relaxation. Our motivations for building this dataset are (1) to develop a training set for the generation of machine and deep learning models and (2) to obtain structural minima over a range of stoichiometries to support future electronic analyses. We provide the dataset as individual VASP xml files as well as all configurations encountered during relaxations collated into an ASE database with the corresponding total energy and atomic forces. In this report, we discuss the dataset in more detail and highlight interesting structural and electronic features of the relaxed structures.

36 MATERIALS SCIENCE↗

DOE OSTI2021

Analytical WKB theory for high-harmonic generation and its application to massive Dirac electrons

Here we propose an analytical approach to high-harmonic generation (HHG) for nonperturbative low-frequency and high-intensity fields based on the (Jeffreys-)Wentzel-Kramers-Brillouin (WKB) approximation. By properly taking into account Stokes phenomena of WKB solutions, we obtain wave functions that systematically include the repetitive dynamics of production and acceleration of electron-hole pairs and quantum interference due to phase accumulation between different pair production times (Stückelberg phase). Using the obtained wave functions without relying on any phenomenological assumptions, we explicitly compute electric current (including intra- and interband contributions) as the source of HHG for a massive Dirac system in (1+1) dimensions under an ac electric field. We demonstrate that the WKB approximation agrees well with numerical results obtained by solving the time-dependent Schrödinger equation and point out that the quantum interference is important in HHG. We also predict in the deep nonperturbative regime that (1) harmonic intensities oscillate with respect to electric-field amplitude E 0 and frequency Ω with a period determined by the Stückelberg phase, (2) the cutoff order of HHG is determined by 2eE 0 ℏΩ 2 , with e being the electron charge, and that (3) noninteger harmonics, controlled by the Stückelberg phase, appear as a transient effect. Our WKB theory is particularly suited for a parameter regime, where the Keldysh parameter γ = (Δ/2)Ω/eE 0 ,with Δ being the gap size, is small. This parameter regime corresponds to intense lasers in the terahertz regime for realistic massive Dirac materials. Our analysis implies that the so-called HHG plateau can be observed at the terahertz frequency within the current technology.

36 MATERIALS SCIENCE↗

DOE OSTI2024

Spike-and-Slab Shrinkage Priors for Structurally Sparse Bayesian Neural Networks

Network complexity and computational efficiency have become increasingly significant aspects of deep learning. Sparse deep learning addresses these challenges by recovering a sparse representation of the underlying target function by reducing heavily overparameterized deep neural networks. Specifically, deep neural architectures compressed via structured sparsity (e.g., node sparsity) provide low-latency inference, higher data throughput, and reduced energy consumption. In this article, we explore two well-established shrinkage techniques, Lasso and Horseshoe, for model compression in Bayesian neural networks (BNNs). To this end, we propose structurally sparse BNNs, which systematically prune excessive nodes with the following: 1) spike-and-slab group Lasso (SS-GL) and 2) SS group Horseshoe (SS-GHS) priors, and develop computationally tractable variational inference, including continuous relaxation of Bernoulli variables. We establish the contraction rates of the variational posterior of our proposed models as a function of the network topology, layerwise node cardinalities, and bounds on the network weights. Furthermore, we empirically demonstrate the competitive performance of our models compared with the baseline models in prediction accuracy, model compression, and inference latency.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Measuring Muon Antineutrino Charged-Current Interactions Without Mesons in the Final State, in the NOvA Near Detector

NOvA is a long-baseline neutrino experiment based at Fermilab in the US, with the primary aim of measuring neutrino and antineutrino oscillations. This will enhance our understanding of electroweak interactions by measuring the neutrino mixing angles, CP-violating phase and neutrino mass ordering. To measure these oscillations, we first need to have a deep understanding of how neutrinos and antineutrinos interact with matter. Antineutrino interaction cross sections are, at present, particularly poorly constrained, and processes such as meson exchange currents are not well understood in the antineutrino sector. This analysis will develop a cross-section measurement of muon antineutrino interactions without mesons (e.g. pions or kaons) in the final state, in the NOvA near detector. A high-statistics, high-purity sample is obtained through a cut-based selection process implementing machine learning techniques. The sample is dominated by quasi-elastic and meson exchange current interactions which are sensitive to nuclear effects such as Final-State Interactions. The cross section will be extracted as a function of the incoming neutrino energy and the kinematics of the outgoing particles.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2021

Raindrop Size Spectrum in Deep Convective Regions of the Americas

This study compared drop size distribution (DSD) measurements on the surfaces, the corresponding properties, and the precipitation modes among three deep convective regions within the Americas. The measurement compilation corresponded to two sites in the midlatitudes: the U.S. Southern Great Plains and Córdoba Province in subtropical South America, as well as to one site in the tropics: Manacapuru in central Amazonia; these are all areas where intense rain-producing systems contribute to the majority of rainfall in the Americas’ largest river basins. This compilation included two types of disdrometers (Parsivel and 2D-Video Disdrometer) that were used at the midlatitude sites and one type of disdrometer (Parsivel) that was deployed at the tropical site. The distributions of physical parameters (such as rain rate R, mass-weighted mean diameter D m , and normalized droplet concentration N w ) for the raindrop spectra without rainfall mode classification seemed similar, except for the much broader N w distributions in Córdoba. The raindrop spectra were then classified into a light precipitation mode and a precipitation mode by using a cutoff at 0.5 mm h -1 based on previous studies that characterized the full drop size spectra. These segregated rain modes are potentially unique relative to previously studied terrain-influenced sites. In the light precipitation and precipitation modes, the dominant higher frequency observed in a broad distribution of N w in both types of disdrometers and the identification of shallow light precipitation in vertically pointing cloud radar data represent unique characteristics of the Córdoba site relative to the others. As a result, the co-variability between the physical parameters of the DSD indicates that the precipitation observed in Córdoba may confound existing methods of determining the rain type by using the drop size distribution.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2022

A Classification of G -invariant Shallow Neural Networks

When trying to fit a deep neural network (DNN) to a G-invariant target function with G a group, it only makes sense to constrain the DNN to be G-invariant as well. However, there can be many different ways to do this, thus raising the problem of “G-invariant neural architecture design”: What is the optimal Ginvariant architecture for a given problem? Before we can consider the optimization problem itself, we must understand the search space, the architectures in it, and how they relate to one another. In this paper, we take a first step towards this goal; we prove a theorem that gives a classification of all G-invariant single-hidden-layer or “shallow” neural network (G-SNN) architectures with ReLU activation for any finite orthogonal group G, and we prove a second theorem that characterizes the inclusion maps or “network morphisms” between the architectures that can be leveraged during neural architecture search (NAS). The proof is based on a correspondence of every G-SNN to a signed permutation representation of G acting on the hidden neurons; the classification is equivalently given in terms of the first cohomology classes of G, thus admitting a topological interpretation. The G-SNN architectures corresponding to nontrivial cohomology classes have, to our knowledge, never been explicitly identified in the literature previously. Using a code implementation, we enumerate the G-SNN architectures for some example groups G and visualize their structure. Lastly, we prove that architectures corresponding to inequivalent cohomology classes coincide in function space only when their weight matrices are zero, and we discuss the implications of this for NAS.

Agrawal, Devanshu↗