SEARCH · Engineering Papers

Results for “deep energy method”

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 145 records · Page 8

All sources NASA NTRS DOE OSTI

DOE OSTI2021

Branching Dueling Q-Network Based Online Scheduling of a Microgrid With Distributed Energy Storage Systems

This letter investigates a Branching Dueling Q-Network (BDQ) based online operation strategy for a microgrid with distributed battery energy storage systems (BESSs) operating under uncertainties. Additionally, the developed deep reinforcement learning (DRL) based microgrid online optimization strategy can achieve a linear increase in the number of neural network outputs with the number of distributed BESSs, which overcomes the curse of dimensionality caused by the charge and discharge decisions of multiple BESSs. Numerical simulations validate the effectiveness of the proposed method.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2021

Open Data and Deep Semantic Segmentation for Automated Extraction of Building Footprints

Advances in machine learning and computer vision, combined with increased access to unstructured data (e.g., images and text), have created an opportunity for automated extraction of building characteristics, cost-effectively, and at scale. These characteristics are relevant to a variety of urban and energy applications, yet are time consuming and costly to acquire with today’s manual methods. Several recent research studies have shown that in comparison to more traditional methods that are based on features engineering approach, an end-to-end learning approach based on deep learning algorithms significantly improved the accuracy of automatic building footprint extraction from remote sensing images. However, these studies used limited benchmark datasets that have been carefully curated and labeled. How the accuracy of these deep learning-based approach holds when using less curated training data has not received enough attention. The aim of this work is to leverage the openly available data to automatically generate a larger training dataset with more variability in term of regions and type of cities, which can be used to build more accurate deep learning models. In contrast to most benchmark datasets, the gathered data have not been manually curated. Thus, the training dataset is not perfectly clean in terms of remote sensing images exactly matching the ground truth building’s foot-print. A workflow that includes data pre-processing, deep learning semantic segmentation modeling, and results post-processing is introduced and applied to a dataset that include remote sensing images from 15 cities and five counties from various region of the USA, which include 8,607,677 buildings. The accuracy of the proposed approach was measured on an out of sample testing dataset corresponding to 364,000 buildings from three USA cities. The results favorably compared to those obtained from Microsoft’s recently released US building footprint dataset.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

Deep Reinforcement Learning From Demonstrations to Assist Service Restoration in Islanded Microgrids

Microgrids can be operated in island mode during utility grid outages to support service restoration and improve system resilience. To schedule and dispatch distributed energy resources (DERs) in an islanded microgrid, conventional model-based methods rely on accurate distribution network models and lack generalization and adaptability. Data-driven methods are promising for DER coordination but face practical challenges such as potential hazards to microgrids during online training and insufficient online training opportunities due to low outage rates. This paper presents a novel two-stage learning framework that builds on the deep deterministic policy gradient from demonstrations to identify an optimal restoration strategy. At the pre-training stage, imitation learning is applied to equip the control agent with expert experiences to guarantee acceptable initial performance. At the online training stage, action clipping, reward shaping, and expert demonstrations are leveraged to ensure safe exploration while accelerating the training process. In conclusion, the proposed method is illustrated using the IEEE 123-node system and compared with a representative model-based method and the standard deep deterministic policy gradient method to prove solution accuracy and demonstrate increased computational efficiency.

Du, Yan↗

DOE OSTI2023

Enhancing Oxygen Stability in Low-Cobalt Layered Oxide Cathode Materials by Three-Dimensional Targeted Doping

In this project, we propose to develop a new concept and a generic platform that can lead to the greatly enhanced stabilization of all high-energy cathode materials, and in particular high-nickel (Ni) and low-cobalt (Co) oxides. The new concept is a 3D doping technology that hierarchically combines surface and bulk doping. We will use surface doping to stabilize the surface of primary particles and also introduce dopants in the bulk to further enhance oxygen stability, conductivity, and structural stability in low-Co oxides under high voltage and deep discharging operating conditions. This new concept not only will deliver a low-cost, high-energy cathode but also will provide a generic method that can stabilize all high-energy cathodes. The proposed novel 3D doping approach is poised to resolve some longstanding challenges in fundamental doping effects on battery materials as well as to reduce Li-ion batteries’ cost and improve their safety, energy density, and lifetime. To tackle this problem, we have formed a highly complementary multi-university/national labs/industry team to enable a doping-central and systematic investigation of low-Co materials and create a knowledge base for many electrode materials to be used in advanced electric vehicles. The successful execution of the proposed project relies on five components that can be carried out by the complementary team members: (1) a theoretical investigation of the surface and bulk stabilizing dopants (Persson), (2) a precise synthesis of materials with targeted doping (Lin and Xin), (3) development of electrolytes for high-Ni low-Co oxides (Xu), (4) multi-scale characterization of the structures and their interfaces by scanning transmission electron microscopy (SEM) and synchrotron X-ray imaging and spectroscopy tools (Xin and Lin), and (5) pouch cell-level integration (Fan). The UCI-led project will enable a doping-central and systematic investigation of low-Co materials and create a knowledge base for many electrode materials to be used in advanced electric vehicles.

25 ENERGY STORAGE↗

NASA NTRS2001

Method of Making a Nickel Fiber Electrode for a Nickel Based Battery System

The general purpose of the invention is to develop a high specific energy nickel electrode for a nickel based battery system. The invention discloses a method of producing a lightweight nickel electrode which can be cycled to deep depths of discharge (i.e., 40% or greater of electrode capacity). These deep depths of discharge can be accomplished by depositing the required amount of nickel hydroxide active material into a lightweight nickel fiber substrate.

Doris L Britton↗

DOE OSTI2022

Photometric identification of compact galaxies, stars, and quasars using multiple neural networks

We present MargNet, a deep learning-based classifier for identifying stars, quasars, and compact galaxies using photometric parameters and images from the Sloan Digital Sky Survey Data Release 16 catalogue. MargNet consists of a combination of convolutional neural network and artificial neural network architectures. Using a carefully curated data set consisting of 240 000 compact objects and an additional 150 000 faint objects, the machine learns classification directly from the data, minimizing the need for human intervention. MargNet is the first classifier focusing exclusively on compact galaxies and performs better than other methods to classify compact galaxies from stars and quasars, even at fainter magnitudes. This model and feature engineering in such deep learning architectures will provide greater success in identifying objects in the ongoing and upcoming surveys, such as Dark Energy Survey and images from the Vera C. Rubin Observatory.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2025

An analysis of physics limited dispatch of nuclear renewable integrated energy systems using deep reinforcement learning and dynamic modeling

Previous approaches to dispatching nuclear integrated energy systems (NIES) have focused on the profitability and flexibility of these systems to operate on energy grids with highly variable pricing. However, due to the complexity involved in modeling and designing these systems, there has been less emphasis on ensuring that these dispatch strategies are physically achievable. It is imperative to develop methods that allow the system to remain within the desired NIES operating conditions and perform this based on realistic limited forecasted information. This research employs next generation artificial intelligence, namely deep reinforcement learning (DRL), and a dynamic system model written in Modelica to find a safe and profitable dispatch strategy for a solar nuclear hybrid design. The DRL agent is shown to find a novel dispatch strategy that manages both power ramping and power levels while respecting operational limits. This DRL-based dispatch is compared to other dispatching strategies including an optimal design solution from mixed integer linear programming (MILP). It is found that incorporating the physics of such a tightly coupled NIES limits the profitability of the MILP-based dispatch strategy. As a result, the MILP solution overestimates the design’s generated revenue. In contrast, DRL significantly reduces the number of breaches of safe operational conditions during energy arbitrage while maintaining profitability. Furthermore, this work paves the way for a more detailed assessment of NIES profitability and could be used to aid operator decisions on future NIES projects.

14 - SOLAR ENERGY↗

DOE OSTI2026

The effect of hydroxyl spacing in diols on the solvation structure, dynamics, and transport properties of choline chloride-based deep eutectic solvents

Deep eutectic solvents (DESs) are a class of liquids that offer great potential in alleviating some of the challenges present in today's long-term energy storage methods because they have physical properties that are favorable for storable electrolyte solutions. In this work, a series of glycols (ethylene glycol, 1,3-propanediol, 1,4-butanediol, and 1,5-pentanediol) were studied as potential hydrogen bond donors (HBD) with a common choline chloride (ChCl) as the hydrogen bond acceptor (HBA). The solvation dynamics of the prepared systems were studied by measuring the solvent reorganization response using femtosecond transient absorption spectroscopy (fs-TA). Conductivity, viscosity, density, ET(30) polarity, and dynamics of the prepared DESs were analyzed, with a particular interest in determining the effect of HBD chain length on these parameters. Here, classical molecular dynamics simulations were employed to investigate how the local liquid structure, solvent dynamics, and bulk solvent properties vary with changes in glycol chain length.

Conductivity↗

NASA NTRS1993

Calculations on the competition between association and reaction for C3H(+) + H2

The ab initio results presently obtained for the potential energy surface of competing associative and reactive ion-molecule processes of the reactants H2 and C3H(+) show that the linear ion is able to directly access the deep potential well of the propargyl ion H2CCCH(+). Using the minimum energy potential pathway and properties of the stationary point structures determined via the ab initio methods, calculation results are obtained for both the association-rate coefficient for C3H3(+) production as a function of density, and the branching ratio between the propargyl and cyclic structures of the ion.

Maluendes, Sergio A.↗

DOE OSTI2021

Plant single-cell solutions for energy and the environment

Progress in sequencing, microfluidics, and analysis strategies has revolutionized the granularity at which multicellular organisms can be studied. In particular, single-cell transcriptomics has led to fundamental new insights into animal biology, such as the discovery of new cell types and cell type-specific disease processes. However, the application of single-cell approaches to plants, fungi, algae, or bacteria (environmental organisms) has been far more limited, largely due to the challenges posed by polysaccharide walls surrounding these species’ cells. In this perspective, we discuss opportunities afforded by single-cell technologies for energy and environmental science and grand challenges that must be tackled to apply these approaches to plants, fungi and algae. We highlight the need to develop better and more comprehensive single-cell technologies, analysis and visualization tools, and tissue preparation methods. We advocate for the creation of a centralized, open-access database to house plant single-cell data. Finally, we consider how such efforts should balance the need for deep characterization of select model species while still capturing the diversity in the plant kingdom. Investments into the development of methods, their application to relevant species, and the creation of resources to support data dissemination will enable groundbreaking insights to propel energy and environmental science forward.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2023

A detailed study of interpretability of deep neural network based top taggers

Abstract Recent developments in the methods of explainable artificial intelligence (XAI) allow researchers to explore the inner workings of deep neural networks (DNNs), revealing crucial information about input–output relationships and realizing how data connects with machine learning models. In this paper we explore interpretability of DNN models designed to identify jets coming from top quark decay in high energy proton–proton collisions at the Large Hadron Collider. We review a subset of existing top tagger models and explore different quantitative methods to identify which features play the most important roles in identifying the top jets. We also investigate how and why feature importance varies across different XAI metrics, how correlations among features impact their explainability, and how latent space representations encode information as well as correlate with physically meaningful quantities. Our studies uncover some major pitfalls of existing XAI methods and illustrate how they can be overcome to obtain consistent and meaningful interpretation of these models. We additionally illustrate the activity of hidden layers as neural activation pattern diagrams and demonstrate how they can be used to understand how DNNs relay information across the layers and how this understanding can help to make such models significantly simpler by allowing effective model reoptimization and hyperparameter tuning. These studies not only facilitate a methodological approach to interpreting models but also unveil new insights about what these models learn. Incorporating these observations into augmented model design, we propose the particle flow interaction network model and demonstrate how interpretability-inspired model augmentation can improve top tagging performance.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1993

Electronic characterization of defects in narrow gap semiconductors

The study of point defects in semiconductors has a long and honorable history. In particular, the detailed understanding of shallow defects in common semiconductors traces back to the classic work of Kohn and Luttinger. However, the study of defects in narrow gap semiconductors represents a much less clear story. Here, both shallow defects (caused by long range potentials) and deep defects (from short range potentials) are far from being completely understood. In this study, all results are calculational and our focus is on the chemical trend of deep levels in narrow gap semiconductors. We study substitutional (including antisite), interstitial and ideal vacancy defects. For substitutional and interstitial impurities, the efects of relaxation are included. For materials like Hg(1-x)Cd(x)Te, we study how the deep levels vary with x, of particular interest is what substitutional and interstitial atoms yield energy levels in the gap i.e. actually produce deep ionized levels. Also, since the main technique utilized is Green's functions, we include some summary of that method.

Patterson, James D.↗

DOE OSTI2023

Insights into Methodologies and Stochastic Optimization of Thermal Energy Storage-Coupled Advanced Reactor Systems: A Comparison of Methods for Accessing Long-Term Sub-System Sizing Adequacy

This paper investigates the potential of coupling Thermal Energy Storage (TES) with Advanced Reactors (ARs) to address uncertainties posed by climate change in deep decarbonized power systems. The TES Use-case Team at Idaho National Laboratory (INL) has examined the potential of storing thermal energy from ARs during low demand periods and optimizing discharge during peak-priced hours, in both steady-state and transient conditions. Building on this groundwork, this study bridges the gaps in optimal sizing of the sub-system of TES-coupled AR systems using Risk Analysis Virtual Environment (RAVEN) and Holistic Energy Resource Optimization Network (HERON), INL?s framework for grid optimization. By applying this framework, we present statistically-robust optimal charge, discharge including balance of plant (BOP), and storage sizing for the High-Temperature Gas-Cooled Reactor (HTGR) with 203 MWth output. To this end, we generated synthetic price samples for 30 years using 2018 ? 2021 real-time market data from ERCOT, PJM and MISO. Our results reveals that the TES-coupled HTGR system is highly effective in maximizing revenue from electricity sales. We observed a substantial increase of 40 % in ERCOT and a noteworthy 15 % increase in PJM and MISO when compared to the conventional BOP without TES. This improvement is achieved through regionally-tailored sub-system sizing, which ranges from 398 to 416 MWth for the discharge system and 610 to 1029 MWth for the TES. We find that the average electricity price directly impacts the overall economics, while price volatility influences storage size. Additional sensitivity analyses were performed to access the impact of key assumptions on system economics and sizing, differentiating the optimization window (i.e., 24 ? 219 hours of chronological observations) and by imposing storage continuity condition in tracking TES cycles. We observed that at the 120-hour of the optimization window, a reasonable balance between computation time and accuracy was achieved. Our analysis also highlights the significance of conducting multi-day cycle analysis (> 120-hour) for TES to capture interaction between electricity prices and storage dynamics, providing a comprehensive understanding of TES behavior that AR developers should integrate into their plant designs.

25 ENERGY STORAGE↗

DOE OSTI2022

Monitoring Offshore CO 2 Sequestration Using Marine CSEM Methods; Constraints Inferred from Field- and Laboratory-Based Gas Hydrate Studies

Offshore geological sequestration of CO 2 offers a viable approach for reducing greenhouse gas emissions into the atmosphere. Strategies include injection of CO 2 into the deep-ocean or ocean-floor sediments, whereby depending on pressure–temperature conditions, CO 2 can be trapped physically, gravitationally, or converted to CO 2 hydrate. Energy-driven research continues to also advance CO 2 -for-CH 4 replacement strategies in the gas hydrate stability zone (GHSZ), producing methane for natural gas needs while sequestering CO 2 . In all cases, safe storage of CO 2 requires reliable monitoring of the targeted CO 2 injection sites and the integrity of the repository over time, including possible leakage. Electromagnetic technologies used for oil and gas exploration, sensitive to electrical conductivity, have long been considered an optimal monitoring method, as CO 2 , similar to hydrocarbons, typically exhibits lower conductivity than the surrounding medium. We apply 3D controlled-source electromagnetic (CSEM) forward modeling code to simulate an evolving CO 2 reservoir in deep-ocean sediments, demonstrating sufficient sensitivity and resolution of CSEM data to detect reservoir changes even before sophisticated inversion of data. Laboratory measurements place further constraints on evaluating certain systems within the GHSZ; notably, CO 2 hydrate is measurably weaker than methane hydrate, and >1 order of magnitude more conductive, properties that may affect site selection, stability, and modeling considerations.

58 GEOSCIENCES↗

DOE OSTI2025

Improved heavy-ion PID using scintillation light detector with neural network analysis: a Monte Carlo simulation study

The photon collection efficiency of gaseous scintillator detectors varies according to the position of the impinging charged particles in the medium that generates scintillation light. Thus, when impinging particles are distributed over a large area, the intrinsic photon-number resolution of the system is affected by a large variation. This work presents and discusses a method for adjusting the total number of detected photons to account for variation in the photon collection efficiency as a function of the position of the light source within the scintillating medium. The method was developed and validated by processing data from systematic simulation studies based on GEANT4 that model the response of the Energy Loss Optical Scintillation System (ELOSS) detector. The position of the charged particle is calculated using a deep neural network algorithm. This is accomplished by analyzing the distribution of scintillation light recorded by the array of photosensors. The estimated particle position is then used to calculate the correction factor and adjust the amount of captured light to account for variations in the photon collection efficiency. The neural network algorithm provides excellent tracking capabilities, achieving sub-millimeter position resolution and an angular resolution of 12 mrad, approaching the performance of traditional tracking detectors (e.g., drift chambers). The present method can be generalized to any optical scintillation system where the photon collection efficiency depends on the position of the impinging particle.

Heavy-ion detectors↗

NASA NTRS1980

Wavelength-modulated photocapacitance spectroscopy

Derivative deep-level spectroscopy was achieved with wavelength-modulated photocapacitance employing MOS structures and Schottky barriers. The energy position and photoionization characteristics of deep levels of melt-grown GaAs and the Cr level in high-resistivity GaAs were determined. The advantages of this method over existing methods for deep-level spectroscopy are discussed.

Kamieniecki, E.↗

NASA NTRS2022

New Spectroscopic Confirmations of Lyα Emitters at Z ∼ 7 from the LAGER Survey

We report spectroscopic confirmations of 15 Lyα galaxies at z ∼ 7, implying a spectroscopic confirmation rate of ∼80% on candidates selected from the Lyα Galaxies in the Epoch of Reionization (LAGER), which is the largest (24 deg2) survey aimed at finding Lyα emitters (LAEs) at z ∼ 7 and uses deep narrowband imaging from the Dark Energy Camera at CTIO. LAEs at high redshifts are sensitive probes of cosmic reionization, and narrowband imaging is a robust and effective method for selecting a large number of LAEs. In this work, we present results from the spectroscopic follow-up of LAE candidates in two LAGER fields, COSMOS and WIDE-12, using observations from Keck/LRIS. We report the successful detection of Lyα emission in 15 candidates. Three of these in COSMOS have matching confirmations from a previous spectroscopic follow-up and are part of the overdense region, LAGER-z7OD1. Two other candidates that were not detected with LRIS have prior spectroscopic confirmations from Magellan. Including these, we obtain a spectroscopic confirmation success rate of ∼80% for LAGER LAE candidates. Thorough checks were performed to reject the possibility of these detections being foreground emission resulting with a probability of, at most, one contaminant. We do not detect any other UV nebular lines in our LRIS spectra, apart from Lyα. We estimate a 2σ upper limit for the ratio of N v/Lyα, fNV/fLyα ≲ 0.27. Including confirmations from this work, a total of 33 LAE sources from LAGER are now spectroscopically confirmed. LAGER has more than doubled the sample of spectroscopically confirmed LAE sources at z ∼ 7.

Santosh Harish↗

DOE OSTI2021

Novel usage of deep learning and high-performance computing in long-baseline neutrino oscillation experiments

Mención Internacional en el título de doctorDeep-learning methods are playing a crucial role in numerous scientific and industrialapplications. Over the past two decades, these techniques have helped in the collection,reconstruction, and analysis of large data samples in particle physics experiments. Themain topic of this PhD research is the study of deep-learning techniques in long-baselineneutrino oscillation experiments. Neutrinos are mysterious light elementary particles,and their investigation is essential to shed light on some of the remaining open questionsin physics. The work presented here describes an algorithm based on a convolutionalneural network developed to provide highly accurate and efficient selections of electronneutrino and muon neutrino interactions in the Deep Underground Neutrino Experiment(DUNE). With this algorithm, the electron neutrino (antineutrino) selection efficiencypeaks at 90% (94%) and exceeds 85% (90%) for reconstructed neutrino energies between2-5 GeV. The selection efficiency for muon neutrino (antineutrino) interactions is foundto have a maximum of 96% (97%) and exceeds 90% (95%) efficiency for reconstructedneutrino energies above 2 GeV. When considering all electron neutrino and antineutrinointeractions as signal (both those appearing from oscillations and those intrinsic tothe beam), a selection purity of 90% is achieved. These event selections are criticalto maximise the sensitivity of the experiment to CP-violating effects, key to furtherunderstand the matter-antimatter asymmetry of the Universe.In high-energy physics experiments, deep learning has also been explored for producingfast simulations and physically-motivated manipulations of simulated images. Some ofthose simulations, such as the light production and detection, are very computationallyexpensive and require novel methods to produce the necessary samples while controllingthe varied underlying physics model parameters. To do so, we invented the model-assistedgenerative adversarial network (MAGAN), first validated on simple generic case studiesand then successfully applied to the DUNE photon-detector simulation.Moreover, we also developed graph neural networks for 3D-voxel classification ofambiguities and optical crosstalk for a different particle physics experiment, most preciselyfor the proposed SuperFGD. This novel 3D-granular plastic-scintillator neutrino detectorwill be used to upgrade the near detector of the T2K neutrino oscillation experiment, and our method reports efficiencies and purities of 94-96% per event in the classificationof particle track voxels.Due to the growth and complexity of deep neural networks, researchers have beeninvestigating techniques to train those networks in a more computationally-efficient way.Many efforts have been made by the community to optimise deep-learning models byparallelising or distributing their training computation across multiple devices. In thisthesis, we study an approach based on data locality for those neural networks that cannotbenefit from scaling their computation due to a significant bottleneck in the data I/O.The research also includes a detailed study on the performance of deep neural networkson hardware accelerator boards.Los métodos de aprendizaje profundo son cada vez más utilizados en numerosas aplicacionescientíficas e industriales hoy en día. Durante las dos últimas décadas, estastécnicas se han empleado en la recolección, reconstrucción y análisis de la gran cantidadde datos generados por experimentos de física de partículas. El tema principal de estatesis doctoral es el uso de estos modelos de aprendizaje profundo en experimentos defísica de neutrinos, en concreto en los experimentos de larga distancia DUNE y T2K. Losneutrinos, partículas fundamentales neutras, de las más ligeras del Universo, pueden serclave para explicar algunas de las cuestiones todavía sin resolver en física fundamental.Entre las diferentes contribuciones que esta tesis ha hecho a su estudio, cabe destacar eldesarrollo de un algoritmo basado en una red de neuronas convolucional para seleccionarcon gran eficiencia y precisión las interacciones de neutrinos electrónicos y muónicos enel Deep Underground Neutrino Experiment (DUNE). La eficiencia de selección obtenidapara neutrinos (antineutrinos) electrónicos alcanza un máximo del 90% (94%) y supera el85% (90%) para neutrinos con energías reconstruidas en el rango 2-5 GeV. La selección deneutrinos (antineutrinos) muónicos tiene una eficiencia máxima del 96% (97%) y excedeel 90% (95%) para neutrinos con energías reconstruidas de más de 2 GeV. Considerandocomo señal todas las interacciones de neutrinos y antineutrinos electrónicos (procedentestanto de oscilaciones como intrínsecos en el haz inicial), se logra una pureza en la seleccióndel 90%. Dichas selecciones de eventos son fundamentales para maximizar la sensibilidaddel experimento a los efectos de violació...

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗