Engineering Papers⌕ Search

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.

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

At least 793 records · Page 44
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Development of lean, efficient, and fast physics-framed deep-learning-based proxy models for subsurface carbon storage

In this work, we present deep-learning-based surrogate models for CCUS developed with four different algorithms and a physics-framed two-phase flow problem involving displacement of water by CO 2 . The deep-learning models were trained using 3D datasets describing the pressure plume, CO 2 saturation plume, and water extraction rate generated by numerical simulation. The hyperparameters defining the architecture of the neural networks were optimized to determine the slimmest network size and training parameters that give the most efficient performance at the least training cost. To develop a robust model that closely mimics the governing physical laws, the discretized form of the two-phase fluid transport equation was used to formulate the supervised deep-learning task. The algorithms investigated in this study predicted the data to above 95% accuracy, with the multi-layer perceptron model demonstrating the best performance by balancing training speed, prediction time, and prediction accuracy with lean network capacity. Furthermore, the surrogate models simultaneously predict reservoir pressure and CO 2 saturation in every grid block, including the surface well extraction rate and bottomhole pressure, at all simulation times for a given static model realization in just a few seconds on a standard desktop computer. A key outcome of this study is that limits can be placed on network design parameters to avoid over designing neural networks, with associated efficiencies in training and prediction times. This is very useful because large volumes of data may be generated in CCUS projects and over-design of neural network architectures imposes penalties that are antithetical to the goal of near-real time forecasting.

58 GEOSCIENCES↗
DOE OSTI2025

Deep Learning-based Surrogate Model for Efficient Reservoir Simulation in Large-scale Geological Carbon Storage: Application in IBDP Dataset

This project introduces an advanced deep learning (DL)-based surrogate modeling approach to enhance the efficiency and accuracy of large-scale geological carbon storage (GCS) simulations. Using the Illinois Basin Decatur Project (IBDP) dataset as training data, the study employs a residual U-Net architecture to predict critical state variables such as pressure and CO₂ saturation, as well as CO₂ plume migration. By incorporating key geological parameters (e.g., porosity, permeability, and rock facies) and physics-informed inputs like the diffusive time of flight and time step, the DL model effectively reduces computational complexity while maintaining robust physical constraints. Compared to traditional simulators like Eclipse, the DL model achieves remarkable accuracy, with a root mean square error (RMSE) of 1.57 psi for pressure and 0.007 for saturation, and dramatically reduces computational time from hours to just 69.9 seconds for 50-step simulations. These results demonstrate the potential of innovative DL methodologies to improve the predictivity and operational efficiency of GCS simulations, providing a reliable foundation for decision-making in CCS operations. Supported by the SMART initiative, this project underscores the success of leveraging computational innovations to advance CCS technologies.

advanced deep learning↗
DOE OSTI2023

Direct nano-imaging of light-matter interactions in nanoscale excitonic emitters

Strong light-matter interactions in localized nano-emitters placed near metallic mirrors have been widely reported via spectroscopic studies in the optical far-field. Here, we report a near-field nano-spectroscopic study of localized nanoscale emitters on a flat Au substrate. Using quasi 2-dimensional CdSe/Cd x Zn 1-x S nanoplatelets, we observe directional propagation on the Au substrate of surface plasmon polaritons launched from the excitons of the nanoplatelets as wave-like fringe patterns in the near-field photoluminescence maps. These fringe patterns were confirmed via extensive electromagnetic wave simulations to be standing-waves formed between the tip and the edge-up assembled nano-emitters on the substrate plane. We further report that both light confinement and in-plane emission can be engineered by tuning the surrounding dielectric environment of the nanoplatelets. Our results lead to renewed understanding of in-plane, near-field electromagnetic signal transduction from the localized nano-emitters with profound implications in nano and quantum photonics as well as resonant optoelectronics.

42 ENGINEERING↗
DOE OSTI2025

Bayesian Optimized Deep Ensemble for Uncertainty Quantification of Deep Neural Networks: a System Safety Case Study on Sodium Fast Reactor Thermal Stratification Modeling

Deep neural networks (DNNs) are increasingly important to scientific computing and engineering system simulations. Accurate uncertainty quantification (UQ) for DNNs is critical in safety-sensitive engineering domains. Traditional Deep Ensemble (DE) methods, while easy to implement, frequently suffer from poorly calibrated uncertainty estimates and limited predictive accuracy due to reliance on fixed architectures with varied weight initializations. To address these issues, we introduce a workflow that combines Bayesian Optimization (BO) and DE. The workflow is modular, scalable, and integrates parallel BO initialized with Sobol sequences to individually optimize the hyperparameters of each ensemble member. This method enhances ensemble diversity, improves predictive accuracy, and provides reliable uncertainty estimates. We evaluate the proposed BODE approach in a sodium fast reactor thermal stratification modeling case study, where we used a densely connected convolutional neural network to predict turbulent viscosity during the reactor transient with consideration of data noise. We benchmark its performance against several optimization approaches, including baseline deep ensemble, evolutionary algorithm-optimized ensemble, ensemble formed via random search combined with greedy selection, and a BO ensemble using random initialization. Here, our results demonstrate superior performance of the developed BODE approach. In noise-free scenarios, BODE notably reduces incorrect aleatoric uncertainty and significantly enhances predictive accuracy. Under conditions of 5% and 10% Gaussian noise, BODE adaptively quantifies uncertainty proportional to data noise, achieving up to an 80% reduction in root mean square error compared to baseline methods and producing well-calibrated prediction intervals.

Bayesian optimization↗
DOE OSTI2020

ContourNet: Salient Local Contour Identification for Blob Detection in Fusion Plasma Simulation Data

We present ContourNet, a deep learning approach to identify salient local isocontours as blobs in large-scale 5D gyrokinetic tokamak simulation data. Blobs-regions of high turbulence that run along the edge wall down toward the diverter and can damage the tokamak-are non-well-defined features but have been empirically localized by isocontours in 2D normalized fluctuating density fields. The key of our study is to train ContourNet to follow the empirical rules to detect blobs over the time-varying simulation data. The architecture of ContourNet is a convolutional neural segmentation network: the inputs are the density field and a rasterized isocontour; the output is a set of isocontour encircling blobs. At the training stage, we feed the network with manually identified isocontours and propagated labels. At the inference stage, we extract isocontours from the segmented blob regions. Results show that our approach can achieve both high accuracy and performance, which enables scientists to understand the blob dynamics influencing the confinement of the plasma.

Blob detection↗
DOE OSTI2022

Defensive symbiosis against giant viruses in amoebae

Protists are important regulators of microbial communities and key components in food webs with impact on nutrient cycling and ecosystem functioning. In turn, their activity is shaped by diverse intracellular parasites, including bacterial symbionts and viruses. Yet, bacteria–virus interactions within protists are poorly understood. Here, we studied the role of bacterial symbionts of free-living amoebae in the establishment of infections with nucleocytoplasmic large DNA viruses (Nucleocytoviricota). To investigate these interactions in a system that would also be relevant in nature, we first isolated and characterized a giant virus (Viennavirus, family Marseilleviridae) and a sympatric potential Acanthamoeba host infected with bacterial symbionts. Subsequently, coinfection experiments were carried out, using the fresh environmental isolates as well as additional amoeba laboratory strains. Employing fluorescence in situ hybridization and qPCR, we show that the bacterial symbiont, identified as Parachlamydia acanthamoebae, represses the replication of the sympatric Viennavirus in both recent environmental isolates as well as Acanthamoeba laboratory strains. In the presence of the symbiont, virions are still taken up, but viral factory maturation is inhibited, leading to survival of the amoeba host. The symbiont also suppressed the replication of the more complex Acanthamoeba polyphaga mimivirus and Tupanvirus deep ocean (Mimiviridae). Our work provides an example of an intracellular bacterial symbiont protecting a protist host against virus infections. The impact of virus–symbiont interactions on microbial population dynamics and eventually ecosystem processes requires further attention.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

First simultaneous global QCD analysis of dihadron fragmentation functions and transversity parton distribution functions

We perform a comprehensive study within quantum chromodynamics (QCD) of dihadron observables in electron-positron annihilation, semi-inclusive deep-inelastic scattering, and proton-proton collisions, including recent cross section data from Belle and azimuthal asymmetries from STAR. We extract simultaneously for the first time π + π − dihadron fragmentation functions (DiFFs) and the nucleon transversity distributions for up and down quarks as well as antiquarks. For the transversity distributions we impose their small- x asymptotic behavior and the Soffer bound. In addition, we utilize a new definition of DiFFs that has a number density interpretation to then calculate expectation values for the dihadron invariant mass and momentum fraction. Furthermore, we investigate the compatibility of our transversity results with those from single-hadron fragmentation (from a transverse momentum dependent/collinear twist-3 framework) and the nucleon tensor charges computed in lattice QCD. We find a universal nature to all of this available information. Future measurements of dihadron production can significantly further this research, especially, as we show, those that are sensitive to the region of large parton momentum fractions. Published by the American Physical Society 2024

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2023

Emerging Best Practices for Electric Utility Planning with Climate Variability: A Resource for Utilities and Regulators

This report is intended to support electric utilities and regulators as they work together to increase the climate resilience of the power system in the United States. It focuses on best practice methods and examples of conducting utility forecasting with climate change (Section 2) as well as three overlapping types of electric utility planning for climate change: resource planning (Section 3), asset planning (Section 4), and contingency planning (Section 5). This report also addresses data development and access (Section 6), emerging pathways for planning including decision-making under deep uncertainty and storylines approaches (Section 7), regulatory considerations (Section 8), and coordination and innovative funding and cost sharing approaches to planning for climate variability (Section 9).

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

Reinforcement Learning Approach to Cybersecurity in Space (RELACSS)

Securing satellite groundstations against cyber-attacks is vital to national security missions. However, these cyber threats are constantly evolving. As vulnerabilities are discovered and patched, new vulnerabilities are discovered and exploited. In order to automate the process of discovering existing vulnerabilities and the means to exploit them, a reinforcement learning framework is presented in this report. We demonstrate that this framework can learn to successfully navigate an unknown network and detect nodes of interest despite the presence of a moving target defense. The agent then exfiltrates a file of interest from the node as quickly as possible. This framework also incorporates a defensive software agent that learns to impede the attacking agents progress. This setup allows for the agents to work against each other and improve their abilities. We anticipate that this capability will help uncover unforeseen vulnerabilities and the means to mitigate them. The modular nature of the framework enables users to swap out learning algorithms and modify the reward functions in order to adapt the learning tasks to various use cases and environments. Several algorithms, viz., tabular Q learning, deep Q networks, proximal policy optimization, advantage actor-critic, generative adversarial imitation learning, are explored for the agents and the results highlighted. The agent learns to solve the tasks in a light-weight abstract environment. Once the agent learns to perform sufficiently well, it can be deployed in a minimega virtual machine environment (or a real network) with wrappers that map abstract actions to software commands. The agent also uses a local representation of the actions called a ‘slot-mechanism’. This allows the agent to learn in a certain network and generalize it to different networks. The defensive agent learns to predict the actions taken by an offensive agent and uses that information to anticipate the threat. This information can then either be used to raise an alarm or to take actions to thwart the attack. We believe that with the appropriate reward design, a representative environment, and action set, this framework can be generalized to tackle other cybersecurity tasks. By sufficiently training these agents, we can anticipate vulnerabilities leading to robust future designs. We can also deploy automated defensive agents that can help secure satellite groundstation and their vital national security missions.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗
DOE OSTI2021

Deep Learning Classification of Cheatgrass Invasion in the Western United States Using Biophysical and Remote Sensing Data

Cheatgrass (Bromus tectorum) invasion is driving an emerging cycle of increased fire frequency and irreversible loss of wildlife habitat in the western US. Yet, detailed spatial information about its occurrence is still lacking for much of its presumably invaded range. Deep learning (DL) has demonstrated success for remote sensing applications but is less tested on more challenging tasks like identifying biological invasions using sub-pixel phenomena. We compare two DL architectures and the more conventional Random Forest and Logistic Regression methods to improve upon a previous effort to map cheatgrass occurrence at >2% canopy cover. High-dimensional sets of biophysical, MODIS, and Landsat-7 ETM+ predictor variables are also compared to evaluate different multi-modal data strategies. All model configurations improved results relative to the case study and accuracy generally improved by combining data from both sensors with biophysical data. Cheatgrass occurrence is mapped at 30 m ground sample distance (GSD) with an estimated 78.1% accuracy, compared to 250-m GSD and 71% map accuracy in the case study. Furthermore, DL is shown to be competitive with well-established machine learning methods in a limited data regime, suggesting it can be an effective tool for mapping biological invasions and more broadly for multi-modal remote sensing applications.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Implications of stop-and-go traffic on training learning-based car-following control

Learning-based car-following control (LCC) of connected and autonomous vehicles (CAVs) is gaining significant attention with the advancement of computing power and data accessibility. While the flexibility and large model capacity of model-free architecture enable LCC to potentially outperform the model-based car-following (CF) model in improving traffic efficiency and mitigating congestion, the generalizability of LCC for traffic conditions different from the training environment/dataset is not well-understood. Herein, this study seeks to explore the impact of stop-and-go traffic in the training dataset on the generalizability of LCC. It uses the characteristics of lead vehicle trajectories to describe stop-and-go traffic, and links the theory of identifiability (i.e., obtaining a unique parameter estimation result using sensor measurements) to the generalizability of behavior cloning (BC) and policy-based deep reinforcement learning (DRL). Correspondingly, the study shows theoretically that: (i) stop-and-go traffic can enable the property of identifiability and enhance the control performance of BC-based LCC in different traffic conditions; (ii) stop-and-go traffic is not necessary for DRL-based LCC to generalize to different traffic conditions; (iii) DRL-based LCC trained with only constant-speed lead vehicle trajectories (not sufficient to ensure identifiability) can be generalized to different traffic conditions; and (iv) stop-and-go traffic increases variance in the training dataset, which improves the convergence of parameter estimation while negatively impacting the convergence of DRL to the optimal control policy. Numerical experiments validate the above findings, illustrating that BC-based LCC entails comprehensive training datasets for generalizing to different traffic conditions, while DRL-based LCC can achieve generalization with simple free-flow traffic training environments. This further suggests DRL as a more promising and cost-effective LCC approach to reduce operational costs, mitigate traffic congestion, and enhance safety and mobility, which can accelerate the deployment and acceptance of CAVs.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2022

Analysis of antibodies from HCV elite neutralizers identifies genetic determinants of broad neutralization

The high genetic diversity of hepatitis C virus (HCV) complicates effective vaccine development. We screened a cohort of 435 HCV-infected individuals and found that 2%–5% demonstrated outstanding HCV-neutralizing activity. From four of these patients, we isolated 310 HCV antibodies, including neutralizing antibodies with exceptional breadth and potency. High neutralizing activity was enabled by the use of the VH1-69 heavy-chain gene segment, somatic mutations within CDRH1, and CDRH2 hydrophobicity. Structural and mutational analyses revealed an important role for mutations replacing the serines at positions 30 and 31, as well as the presence of neutral and hydrophobic residues at the tip of the CDRH3. Based on these characteristics, we computationally created a de novo antibody with a fully synthetic VH1-69 heavy chain that efficiently neutralized multiple HCV genotypes. Finally, our findings provide a deep understanding of the generation of broadly HCV-neutralizing antibodies that can guide the design of effective vaccine candidates.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2022

Learning functional priors and posteriors from data and physics

In this work, we develop a new Bayesian framework based on deep neural networks to be able to extrapolate in space-time using historical data and to quantify uncertainties arising from both noisy and gappy data in physical problems. Specifically, the proposed approach has two stages: (1) prior learning and (2) posterior estimation. At the first stage, we employ the physics-informed Generative Adversarial Networks (PI-GAN) to learn a functional prior either from a prescribed function distribution, e.g., Gaussian process, or from historical data and physics. At the second stage, we employ the Hamiltonian Monte Carlo (HMC) method to estimate the posterior in the latent space of PI-GANs. In addition, we use two different approaches to encode the physics: (1) automatic differentiation, used in the physicsinformed neural networks (PINNs) for scenarios with explicitly known partial differential equations (PDEs), and (2) operator regression using the deep operator network (DeepONet) for PDE-agnostic scenarios. We then test the proposed method for (1) meta-learning for one-dimensional regression, and forward/inverse PDE problems (combined with PINNs); (2) PDE-agnostic physical problems (combined with DeepONet), e.g., fractional diffusion as well as saturated stochastic (100-dimensional) flows in heterogeneous porous media; and (3) spatial-temporal regression problems, i.e., inference of a marine riser displacement field using experimental data from the Norwegian Deepwater Programme (NDP). The results demonstrate that the proposed approach can provide accurate predictions as well as uncertainty quantification given very limited scattered and noisy data, since historical data could be available to provide informative priors. In summary, the proposed method is capable of learning flexible functional priors, e.g., both Gaussian and non-Gaussian process, and can be readily extended to big data problems by enabling mini-batch training using stochastic HMC or normalizing flows since the latent space is generally characterized as low dimensional.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2021

Central American mountains inhibit eastern North Pacific seasonal tropical cyclone activity

Abstract The eastern North Pacific (ENP) has the highest density of tropical cyclones (TCs) on earth, and yet the controls on TCs, from individual events to seasonal totals, remain poorly understood. One effect that has not been fully considered is the unique geography of the Central American mountains. Although observational studies suggest these mountains can readily fuel individual TCs through dynamical processes, here we show that these mountains indeed play the opposite role on the seasonal timescale, hindering seasonal ENP TC activity by up to 35%. We found that these mountains significantly interrupt the abundant moisture transport from the Caribbean Sea to the ENP, limiting deep convection over the open ocean area where TCs preferentially occur. This study advances our fundamental understanding of ENP TC genesis mechanisms across the weather-to-climate timescales, and also highlights the importance of topography representation in improving the ENP regional climate simulations, as well as TC seasonal predictions and future projections.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Hardware-accelerated inference for real-time gravitational-wave astronomy

The field of transient astronomy has seen a revolution with the first gravitational-wave detections and the arrival of multi-messenger observations they enabled. Transformed by the first detection of binary black hole and binary neutron star mergers, computational demands in gravitational-wave astronomy are expected to grow by at least a factor of two over the next five years as the global network of kilometer-scale interferometers are brought to design sensitivity. With the increase in detector sensitivity, real-time delivery of gravitational-wave alerts will become increasingly important as an enabler of multi-messenger followup. In this work, we report a novel implementation and deployment of deep learning inference for real-time gravitational-wave data denoising and astrophysical source identification. This is accomplished using a generic Inference-as-a-Service model that is capable of adapting to the future needs of gravitational-wave data analysis. Overall, our implementation allows seamless incorporation of hardware accelerators and also enables the use of commercial or private (dedicated) as-a-service computing. Based on our results, we propose a paradigm shift in low-latency and offline computing in gravitational-wave astronomy. Such a shift can address key challenges in peak-usage, scalability and reliability, and provide a data analysis platform particularly optimized for deep learning applications. The achieved sub-millisecond scale latency will also be relevant for any machine learning-based real-time control systems that may be invoked in the operation of near-future and next generation ground-based laser interferometers, as well as the front-end collection, distribution and processing of data from such instruments.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2025

Deep Design Data Portal (D3P) v0.01

The Deep Design Data Portal (D3P) tool was developed to demonstrate how readily accessible data sources, such as building energy model reports for design and baseline energy performance data for projects, can provide the data required for reporting to an industry initiative (AIA 2030 commitment), as well as more detailed data that makes the industry dataset more valuable to all stakeholders, enabling project level analysis and analysis of BEM industry trends. D3P provides an easier and less time-consuming way for firms to auto-extract data from this data source, compared to the current reporting workflows of the firms. The BEM reports are the first of several data sources that D3P could integrate. D3P also provides the ability for firms to review, compare, and evaluate the performance of their projects to not only their portfolio, but also to the larger anonymized industry dataset created each time a project is added to D3P. The intent of D3P is to become part of a data-sharing ecosystem to assist creating large anonymized industry datasets that are accessible to industry.

Regnier, Cynthia [Lawrence Berkeley National Labor↗
DOE OSTI2021

2019 Conference on Science at the Sanford Underground Research Facility (Final Technical Report)

The 3rd Conference on Science at the Sanford Underground Research Facility took place on May 14th to 17th, 2019 at the South Dakota School of Mines and Technology. Eighty researcher from all over the U.S., from Europe and from Australia attended the conference and presented on the status of research related to current and future projects at the Sanford Underground Research Facility in Lead, South Dakota. Topics covered by presentations from experts in their field (plenary talks) and contributed oral presentations by junior scientists were neutrino oscillations with focus on science with the Deep Underground Neutrino Experiment (DUNE), dark matter search with priority on the LUX-Zeplin (LZ) experiment, neutrinoless double beta-decay search (Majorana Demonstrator), nuclear astrophysics (CASPAR and DIANA), and geology research (SIGMA-V). Complementary experiments locate at other research facilities were also well represented in the conference program. A public lecture on research in dark matter search for local high school students was organized as part of the conference program and was presented by one of the dark matter plenary speakers.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

European Contributions to Fermilab Accelerator Upgrades and Facilities for the DUNE Experiment

The Proton Improvement Plan (PIP-II) to the FNAL accelerator chain and the Long-Baseline Neutrino Facility (LBNF) will provide the world's most intense neutrino beam to the Deep Underground Neutrino Experiment (DUNE) enabling a wide-ranging physics program. This document outlines the significant contributions made by European national laboratories and institutes towards realizing the first phase of the project with a 1.2 MW neutrino beam. Construction of this first phase is well underway. For DUNE Phase II, this will be closely followed by an upgrade of the beam power to > 2 MW, for which the European groups again have a key role and which will require the continued support of the European community for machine aspects of neutrino physics. Beyond the neutrino beam aspects, LBNF is also responsible for providing unique infrastructure to install and operate the DUNE neutrino detectors at FNAL and at the Sanford Underground Research Facility (SURF). The cryostats for the first two Liquid Argon Time Projection Chamber detector modules at SURF, a contribution of CERN to LBNF, are central to the success of the ongoing execution of DUNE Phase I. Likewise, successful and timely procurement of cryostats for two additional detector modules at SURF will be critical to the success of DUNE Phase II and the overall physics program. The DUNE Collaboration is submitting four main contributions to the 2026 Update of the European Strategy for Particle Physics process. This paper is being submitted to the 'Accelerator technologies' and 'Projects and Large Experiments' streams. Additional inputs related to the DUNE science program, DUNE detector technologies and R&D, and DUNE software and computing, are also being submitted to other streams.

43 PARTICLE ACCELERATORS↗