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 451 records · Page 25

All sources NASA NTRS DOE OSTI

DOE OSTI2022

Deep learning-accelerated 3D carbon storage reservoir pressure forecasting based on data assimilation using surface displacement from InSAR

Fast forecasting of the reservoir pressure distribution during geologic carbon storage (GCS) by assimilating monitoring data is a challenging problem. Due to high drilling cost, GCS projects usually have spatially sparse measurements from few wells, leading to high uncertainties in reservoir pressure prediction. To address this challenge, we use low-cost Interferometric Synthetic-Aperture Radar (InSAR) data as monitoring data to infer reservoir pressure build up. We develop a deep learning-accelerated workflow to assimilate surface displacement maps interpreted from InSAR and to forecast dynamic reservoir pressure. Employing an Ensemble Smoother Multiple Data Assimilation (ES-MDA) framework, the workflow updates three-dimensional (3D) geologic properties and predicts reservoir pressure with quantified uncertainties. We use a synthetic commercial-scale GCS model with bimodally distributed permeability and porosity to demonstrate the efficacy of the workflow. A two-step CNN-PCA approach is employed to parameterize the bimodal fields. The computational efficiency of the workflow is boosted by two residual U-Net based surrogate models for surface displacement and reservoir pressure predictions, respectively. The workflow can complete data assimilation and reservoir pressure forecasting in half an hour on a personal computer.

25 ENERGY STORAGE↗

DOE OSTI2021

Artificial Intelligence for Autonomous Molecular Design: A Perspective

Domain-aware artificial intelligence has been increasingly adopted in recent years to expedite molecular design in various applications, including drug design and discovery. Recent advances in areas such as physics-informed machine learning and reasoning, software engineering, high-end hardware development, and computing infrastructures are providing opportunities to build scalable and explainable AI molecular discovery systems. This could improve a design hypothesis through feedback analysis, data integration that can provide a basis for the introduction of end-to-end automation for compound discovery and optimization, and enable more intelligent searches of chemical space. Several state-of-the-art ML architectures are predominantly and independently used for predicting the properties of small molecules, their high throughput synthesis, and screening, iteratively identifying and optimizing lead therapeutic candidates. However, such deep learning and ML approaches also raise considerable conceptual, technical, scalability, and end-to-end error quantification challenges, as well as skepticism about the current AI hype to build automated tools. To this end, synergistically and intelligently using these individual components along with robust quantum physics-based molecular representation and data generation tools in a closed-loop holds enormous promise for accelerated therapeutic design to critically analyze the opportunities and challenges for their more widespread application. This article aims to identify the most recent technology and breakthrough achieved by each of the components and discusses how such autonomous AI and ML workflows can be integrated to radically accelerate the protein target or disease model-based probe design that can be iteratively validated experimentally. Taken together, this could significantly reduce the timeline for end-to-end therapeutic discovery and optimization upon the arrival of any novel zoonotic transmission event. Our article serves as a guide for medicinal, computational chemistry and biology, analytical chemistry, and the ML community to practice autonomous molecular design in precision medicine and drug discovery.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2020

Deep learning for in situ data compression of large turbulent flow simulations

As the size of turbulent flow simulations continues to grow, in situ data compression is becoming increasingly important for visualization, analysis, and restart checkpointing. For these applications, single-pass compression techniques with low computational and communication overhead are crucial. In this paper we present a deep-learning approach to in situ compression using an autoencoder architecture that is customized for three-dimensional turbulent flows and is well suited for contemporary heterogeneous computing resources. The autoencoder is compared against a recently introduced randomized single-pass singular value decomposition (SVD) for three different canonical turbulent flows: decaying homogeneous isotropic turbulence, a Taylor-Green vortex, and turbulent channel flow. Our proposed fully convolutional autoencoder architecture compresses turbulent flow snapshots by a factor of 64 with a single pass, allows for arbitrarily sized input fields, is cheaper to compute than the randomized single-pass SVD for typical simulation sizes, performs well on unseen flow configurations, and has been made publicly available. The results reported here show that the autoencoder dramatically outperforms a randomized single-pass SVD with similar compression ratio and yields comparable performance to a higher-rank decomposition with an order of magnitude less compression in regard to preserving a number of important statistical quantities such as turbulent kinetic energy, enstrophy, and Reynolds stresses.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Unconventional Wells Interference: Supervised Machine Learning for Detecting Fracture Hits

The primary objective of the study was development of a machine learning (ML)-based workflow for fracture hit (“frac hit”) detection and monitoring using shale oil-field data such as drilling surveys, production history (oil and produced water), pressure, and fracking start time and duration records. The ML method takes advantage of long short-term memory (LSTM) and multilayer perceptron (MLP) neural networks to identify the frac hits due to hydraulic communication between the fracking child well(s) and the producing parent well(s) within the same pad (intra-pad interaction) and/or on different pads (inter-pad interaction). It utilizes time series of pressure and production data from within a pad and from adjacent pads. The workflow can capture time variable features of frac hits when the model architecture is deep and wide enough, with enough trainable parameters for deep learning and feature extraction, as demonstrated in this paper by using training and testing subsets of the field data from selected neighboring pads with over a couple of hundred wells. The study was focused on frac-hit interaction among paired wells and demonstrated that the ML model, once trained, can predict the frac-hit probability.

58 GEOSCIENCES↗

DOE OSTI2024

Deep Dive on Energy Finance Options for Local Governments [Slides]

This NREL training provides a basic introduction to the options for financing a clean energy project as well as for recovering the investment and generating revenue from the project. Two common clean energy project types will be used as case studies to walk through the process and details of obtaining project funding and recovering the investment.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

DOE OSTI2021

Helium tribology of Inconel 617 subjected to laser peening for high temperature nuclear reactor applications

Inconel 617 is among the best candidates for utilization in high temperature gas cooled reactor tribo-components. However, the combined effects of sliding contact, along with intermittent idle times and very high temperature material degradation, deteriorates the alloy tribological performance, especially under a helium atmosphere. Laser peening is a surface treatment technique which can enhance the properties at the surface and subsurface by generating deep residual stresses and enhanced microstructure. In this work, we report the tribological behavior of regular laser peened as well as thermally-engineered laser peened Inconel 617 under helium and air atmospheres at 800 °C. In addition to friction and wear studies, the specimens are characterized by different analytical techniques to further understand the mechanisms involved in the peening process and sliding contact. Regardless of the peening process and post-process treatment types, it is observed that laser peening improves the tribological characteristics of Inconel 617. Interestingly, laser peening followed by helium thermal aging shows highly enhanced tribological behavior. This is attributed to the strengthening effect of the laser peening on the surface oxides providing an excellent and lasting protective and lubricating film under helium exposure.

42 ENGINEERING↗

DOE OSTI2024

Simultaneous reweighting of Transverse Momentum Dependent distributions

The Bayesian reweighting procedure is extended to the case of multiple independent extractions of transverse momentum dependent parton distributions (TMDs). By exploiting the data on transverse single spin asymmetries, A N , for inclusive pion production in polarized proton-proton collisions measured at RHIC, we perform a simultaneous reweighting of the quark Sivers, transversity and Collins TMD functions extracted from semi-inclusive deep inelastic scattering (SIDIS) and annihilation into hadron pairs. The impact of the implementation of the Soffer bound, as well as the differences between older and newer e + e - data, are investigated. The agreement with A N data at large-x F values, a kinematical region complementary to those explored in SIDIS measurements, is enhanced, improving the knowledge of the polarized quark TMDs in the large-x region.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2026

Nonenergy Biomass Carbon Removal and Storage (BiCRS): Assessing Durability of Nongaseous Carbon Products Across Terrestrial Storage Fates

Biomass Carbon Removal and Storage, or BiCRS, pathways use plants or algae that remove carbon dioxide from the atmosphere through photosynthesis and store it underground or in long-lived products. While some BiCRS approaches generate an energy product, all BiCRS approaches generate a carbon product. A new subset of BiCRS approaches focus on the storage of these raw or converted carbon products for generation of carbon credits. However, the durability of these approaches is highly variable as carbon products vary widely in their “form” and the conditions of their “fate.” We organize our thinking about carbon products and their durability around these two primary axes. The durability of carbon product “forms” is mediated by chemical recalcitrance and ranges substantially across agricultural residues, municipal solid waste, woody biomass, and nongaseous products of thermochemical conversion (e.g., biochars and bio-oils). Meanwhile, terrestrial storage “fates” vary in the mechanism employed to stall decay, including surface storage, dry storage, shallow anoxic storage, and deep or geologic anoxic storage (or injection). Each mechanism has different implications for suitability with different feedstock forms as well as long-term risks. We present a framework for assessing durability of solid or liquid raw and conversion carbon products under terrestrial storage fates, highlighting knowns, unknowns, and research priorities moving forward.

09 BIOMASS FUELS↗

DOE OSTI2022

Strong Structural and Electronic Coupling in Metavalent PbS Moiré Superlattices

Moiré superlattices are twisted bilayer materials in which the tunable interlayer quantum confinement offers access to new physics and novel device functionalities. Previously, moiré superlattices were built exclusively using materials with weak van der Waals interactions, and synthesizing moiré superlattices with strong interlayer chemical bonding was considered to be impractical. Here, in this study, using lead sulfide (PbS) as an example, we report a strategy for synthesizing moiré superlattices coupled by strong chemical bonding. We use water-soluble ligands as a removable template to obtain free-standing ultrathin PbS nanosheets and assemble them into direct-contact bilayers with various twist angles. Atomic-resolution imaging shows the moiré periodic structural reconstruction at the superlattice interface due to the strong metavalent coupling. Electron energy loss spectroscopy and theoretical calculations collectively reveal the twist-angle-dependent electronic structure, especially the emergent separation of flat bands at small twist angles. The localized states of flat bands are similar to well-arranged quantum dots, promising an application in devices. This study opens a new door to the exploration of deep energy modulations within moiré superlattices alternative to van der Waals twistronics.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2024

Highly confined epsilon-near-zero and surface phonon polaritons in SrTiO 3 membranes

Recent theoretical studies have suggested that transition metal perovskite oxide membranes can enable surface phonon polaritons in the infrared range with low loss and much stronger subwavelength confinement than bulk crystals. Such modes, however, have not been experimentally observed so far. Here, using a combination of far-field Fourier-transform infrared (FTIR) spectroscopy and near-field synchrotron infrared nanospectroscopy (SINS) imaging, we study the phonon polaritons in a 100 nm thick freestanding crystalline membrane of SrTiO 3 transferred on metallic and dielectric substrates. We observe a symmetric-antisymmetric mode splitting giving rise to epsilon-near-zero and Berreman modes as well as highly confined (by a factor of 10) propagating phonon polaritons, both of which result from the deep-subwavelength thickness of the membranes. Theoretical modeling based on the analytical finite-dipole model and numerical finite-difference methods fully corroborate the experimental results. Our work reveals the potential of oxide membranes as a promising platform for infrared photonics and polaritonics.

36 MATERIALS SCIENCE↗

DOE OSTI2022

Impact of dopant-induced band tails on optical spectra, charge carrier transport, and dynamics in single-crystal CdTe

Abstract Cadmium telluride (CdTe) semiconductors are used in thin-film photovoltaics, detectors, and other optoelectronic applications. For all technologies, higher efficiency and sensitivity are achieved with reduced charge carrier recombination. In this study, we use state-of-the-art CdTe single crystals and electro-optical measurements to develop a detailed understanding of recombination rate dependence on excitation and temperature in CdTe. We study recombination and carrier dynamics in high-resistivity (undoped) and arsenic (As)-doped CdTe by employing absorption, the Hall effect, time-resolved photoluminescence, and pump-probe in the 80–600 K temperature range. We report extraordinarily long lifetimes (30 µs) at low temperatures in bulk undoped CdTe. Temperature dependencies of carrier density and mobility reveal ionization of the main acceptors and donors as well as dominant scattering by ionized impurities. We also distinguish different recombination defects. In particular, shallow As Te and deep V Cd −As Cd acceptors were responsible for p-type conductivity. AX donors were responsible for electron capture, while nonradiative recombination centers (V Cd −As Te , As 2 precipitates), and native defects (V Cd −Te Cd ) were found to be dominant in p-type and n-type CdTe, respectively. Bimolecular and surface recombination rate temperature dependencies were also revealed, with bimolecular coefficient T −3/2 temperature dependence and 170 meV effective surface barrier, leading to an increase in surface recombination velocity at high temperatures and excitations. The results of this study allowed us to conclude that enhanced crucible rotation growth of As-doped CdTe is advantageous to As activation, leading to longer lifetimes and larger mobilities and open-circuit voltages due to lower absorption and trapping.

36 MATERIALS SCIENCE↗

DOE OSTI2023

Emergent Glassy Behavior in a Kagome Rydberg Atom Array

Here, we present large-scale quantum Monte Carlo simulation results on a realistic Hamiltonian of kagome-lattice Rydberg atom arrays. Although the system has no intrinsic disorder, intriguingly, our analyses of static and dynamic properties on large system sizes reveal emergent glassy behavior in a region of parameter space located between two valence bond solid phases. The extent of this glassy region is demarcated using the Edwards-Anderson order parameter, and its phase transitions to the two proximate valence bond solids—as well as the crossover towards a trivial paramagnetic phase—are identified. We demonstrate the intrinsically slow (imaginary) time dynamics deep inside the glassy phase and discuss experimental considerations for detecting such a quantum disordered phase with numerous nearly degenerate local minima. Our proposal paves a new route to the study of real-time glassy phenomena and highlights the potential for quantum simulation of a distinct phase of quantum matter beyond solids and liquids in current-generation Rydberg platforms.

74 ATOMIC AND MOLECULAR PHYSICS↗

DOE OSTI2024

An evaluation of GPT models for phenotype concept recognition

Clinical deep phenotyping and phenotype annotation play a critical role in both the diagnosis of patients with rare disorders as well as in building computationally-tractable knowledge in the rare disorders field. These processes rely on using ontology concepts, often from the Human Phenotype Ontology, in conjunction with a phenotype concept recognition task (supported usually by machine learning methods) to curate patient profiles or existing scientific literature. With the significant shift in the use of large language models (LLMs) for most NLP tasks, we examine the performance of the latest Generative Pre-trained Transformer (GPT) models underpinning ChatGPT as a foundation for the tasks of clinical phenotyping and phenotype annotation. The experimental setup of the study included seven prompts of various levels of specificity, two GPT models (gpt-3.5-turbo and gpt-4.0) and two established gold standard corpora for phenotype recognition, one consisting of publication abstracts and the other clinical observations. The best run, using in-context learning, achieved 0.58 document-level F1 score on publication abstracts and 0.75 document-level F1 score on clinical observations, as well as a mention-level F1 score of 0.7, which surpasses the current best in class tool. Without in-context learning, however, performance is significantly below the existing approaches. Our experiments show that gpt-4.0 surpasses the state of the art performance if the task is constrained to a subset of the target ontology where there is prior knowledge of the terms that are expected to be matched. While the results are promising, the non-deterministic nature of the outcomes, the high cost and the lack of concordance between different runs using the same prompt and input make the use of these LLMs challenging for this particular task.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2023

Turbulent entrainment in finite-length wind farms

In this article, we present an entrainment-based model for predicting the flow and power output of finite-length wind farms. The model is an extension of the three-layer approach of Luzzatto-Fegiz & Caulfield ( Phys. Rev. Fluids , vol. 3, 2018, 093802) for wind farms of infinite length, and assumes dependence of key flow quantities, such as the wind farm bulk velocity, on the streamwise distance from the farm entrance. To assist our analysis and validate the proposed model, we undertake a series of large-eddy simulations with different turbine spacing arrangements and layouts. Comparisons are also made with the top-down model with entrance effects of Meneveau ( J. Turbul. , vol. 13, 2012, N7) and data from the literature. The finite-length entrainment model is shown to be capable of capturing the power drop between contiguous rows of turbines as well as describing the advection and turbulent transport of kinetic energy in both the entrance and fully developed regions. The fully developed regime is approximated only deep in the wind farm, after approximately 15 rows of turbines. Our data suggest that for the cases considered in this study, the empirical coefficients that can be used to describe turbulent entrainment and transfers above the wind farm exhibit little dependence on the farm layout and may be considered constant for modelling purposes. However, the flow field within the wind farm layer can be strongly modulated by the turbine density (spacing) as well as the array layout, and to that extent it can be argued that they are both primary factors determining the wind farm power output.

17 WIND ENERGY↗

DOE OSTI2020

Estimating Lossy Compressibility of Scientific Data Using Deep Neural Networks

Simulation based scientific applications generate increasingly large amounts of data on high-performance computing (HPC) systems. To allow data to be stored and analyzed efficiently, data compression is often utilized to reduce the volume and velocity of data. However, a question often raised by domain scientists is the level of compression that can be expected so that they can make more informed decisions, balancing between accuracy and performance. In this letter, we propose a deep neural network based approach for estimating the compressibility of scientific data. To train the neural network, we build both general features as well as compressor-specific features so that the characteristics of both data and lossy compressors are captured in training. Our approach is demonstrated to outperform a prior analytical model as well as a sampling based approach in the case of a biased estimation, i.e., for SZ. However, for the unbiased estimation (i.e., ZFP), the sampling based approach yields the best accuracy, despite the high overhead involved in sampling the target dataset.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Advancing stream temperature prediction with a generalizable large-sample framework across CONUS river reaches

Accurately predicting stream temperature in ungauged basins remains a critical challenge for water resource management, thermoelectric power plant cooling, and ecosystem conservation. Large-sample machine learning models trained on hundreds of well-monitored river basins have shown remarkable performance; however, such models have yet to be developed solely using forcing data that can be readily extracted to simulate stream temperatures anywhere in the contiguous United States (CONUS). In this study, we present a scalable, large-sample deep learning framework using Long Short-Term Memory (LSTM) networks to simulate daily stream temperatures in ungauged basins across the CONUS. The framework leverages both modeled reanalysis of meteorological and streamflow inputs as well as static attributes available for all 2.7 million CONUS river reaches in the National Hydrography Dataset Plus (NHDPlusV2). By generating dynamical inputs from predefined thermally relevant upstream contributing areas, rather than the entire upstream basin, the model also offers improvements in very large basins where full-basin averaging can dilute the most important influences on stream temperature. Evaluated across 300 basins, the model achieves a median Mean Absolute Error (MAE) of 1.1 °C and a Nash-Sutcliffe Efficiency (NSE) of 0.95 on temporally and spatially distinct test folds—comparable to models trained exclusively using meteorological and streamflow observational data. The flexible, high-performing framework generalizes to any unmonitored river reach without significant regulation or unnatural thermal input immediately upstream, substantially expanding predictive capabilities in data-scarce regions.

Hydrology↗

DOE OSTI2026

Constraining the Aerosol Effects on Deep Convective Clouds by Considering the Coupling Between Clouds and the Planetary Boundary Layer

Several mechanisms have been proposed for the aerosol invigoration effect. Although their principles are well established, their actual magnitudes and roles in cloud development remain uncertain and debatable. This uncertainty partly stems from observational-based studies, in which it has been challenging to separate the co-variability between aerosols and meteorology. Addressing this problem requires large data samples. To this end, this study employs the Atmospheric Radiation Measurement data set expanding to 16 years (some up to 17 years, compared to 10 years in previous work) in the U.S. Southern Great Plains. It also conducts a more careful and rigorous analysis to isolate the influences of convective available potential energy (CAPE) and synoptic patterns to address a previously raised concern. We incorporated a new key process affecting aerosol-cloud interaction: cloud-surface coupling. The state/degree of the coupling relationship turns out to play an important role in the invigoration effect. Our analysis reinforces earlier findings of a robust positive relationship between cloud thickness and aerosol loading across CAPE percentiles—but only under cloud-surface coupled conditions. The increase in cloud thickness with aerosol loading is most pronounced in coupled clouds with high CAPE and bases below 1 km. Coupled clouds with bases below 1 km thicken between 1 and 4 km, depending on the CAPE percentile. Decoupled clouds show no such systematic changes. Synoptic patterns also lead to different strengths of the invigoration effect. Clean and polluted air masses are predominantly associated with northerly and southerly winds, respectively, with a stronger invigoration effect in cleaner air masses.

Geosciences↗

DOE OSTI2023

Comparative Study on Deep Learning Methods for Defect Identification and Classification in Composite Aerostructure Material

Aircraft structures are required to have a high level of quality to satisfy their need for light weight, efficient flight, and withstanding high loads over their lifespan. These aerostructures are typically made from composite material due to their good tensile strength and resistance to compression. To ensure their structural integrity, the composite material requires inspection for common flaws such as porosity, delaminations, voids, foreign object debris, and other defects. Ultrasonic testing (UT) is a popular non-destructive inspection (NDI) technique used for effectively evaluating composite material. Current inspection methods rely heavily on human experience and are extremely time consuming. Therefore, there is a need for the development of techniques to reduce the manual inspection time. This work compares the performance of different deep learning-based methods in the identification and classification of defects. Deep learning has shown great promise in numerous fields, and we show its effectiveness in the evaluation of composite aerostructure material. Furthermore, the methods developed here are both highly reliable with a top recall value of 98.63% as well as extremely efficient requiring an average of 4 seconds during the inferencing stage to evaluate new composites.

composites↗