Engineering Papers⌕ Search

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.

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

At least 307 records · Page 17
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

NETL’s Perspective on Storage Efficiency and CO2-SCREEN

Carbon capture and storage (CCS) is a process that captures carbon dioxide (CO2) by separating it from anthropogenic emissions sources before atmospheric release and storing that CO2 in deep geologic reservoirs. CCS is a powerful method for reducing anthropogenic CO2 which can ultimately diminish the effects of climate change. Prospective CO2 storage resource is the amount of carbon dioxide that can be stored in a given geologic formation typically given as a mass (e.g., metric tons). Obtaining accurate estimates of CO2 storage resources is necessary for governments and industries to make energy-related policy decisions. Researchers at the National Energy Technology Laboratory (NETL) under the Department of Energy (DOE) developed a methods and a tool [CO2-SCREEN (Storage prospeCtive Resource Estimation Excel aNalysis) to estimate prospective carbon storage resources for saline formations, unconventional shale formations, and residual oil zones. The methods and tool provide CO2 storage and efficiency outputs in the form of probability estimates (i.e. P10 and P90) as well as partitioning storage and efficiency estimates based on storage mechanism (total, free phase, sorbed phase, and dissolution phase). This presentation will focus on how storage efficiency is calculated based on numerical modeling efforts, how it’s applied in the storage methods and tool, and then highlighting needs for future development.

Hanson, Angela Goodman↗
DOE OSTI2024

Deep Generative Models in Energy System Applications: Review, Challenges, and Future Directions

In recent years, with the advent of mature machine learning products like ChatGPT, Stable Diffusion, and Sora, the world has witnessed tremendous changes driven by the rapid development of generative artificial intelligence (GAI). Beyond applications in text, speech, image, and video creation, deep generative models (DGMs) underpinning these cutting-edge technologies have also been employed by domain researchers to address scientific and engineering challenges. This paper aims to fill a gap in the research community by providing a systematic review of how DGMs have been utilized in energy system applications. After introducing four most popular DGMs, we review and categorize 196 research articles into five focus areas: data generation, forecasting, situational awareness, modeling, and optimal decision-making. Through this classification, we uncover trends in how DGMs are employed for each type of problem, highlighting GAI techniques that contribute to breakthroughs over traditional methods. We discuss limitations in existing literature, engineering challenges, and propose future directions, all tailored to the unique nature of problems in energy system engineering. Our goal is to offer insights for energy system domain researchers, providing a comprehensive view of existing studies and potential future opportunities.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2020

DelPlasmid: Finding Plasmids with Deep Learning and Machine Learning v1

Extrachromosomal genetic elements or plasmids are an important driver of DNA exchange and genetic innovation in prokaryotes. The success of plasmids has been attributed to their independent replication from host cell chromosomes and their frequent self-transfer. In recent years, the Department of Energy has recognized the importance of plasmid DNA to the viability and success of microbial communities and JGI has responded with funding to support the research and development of new methods and tools for the efficient sequencing of plasmid DNA. LBNL #2019-037 is responsive to this call.

Andreopoulos, William↗
DOE OSTI2022

AI-enabled traveling wave protection for microgrids

Grid forming inverters provide voltage and frequency regulations for microgrids; in the meantime, new challenges are introduced for microgrid protections. For instance, inverters’ control strategies can affect protection behaviors, and low short-circuit ratios and bi-directional power flows also make protection operations complex. Protection schemes based on conventional principles such as overcurrent and distance relays do not always provide reliable, sensitive, or selective operations. Here, we devise a traveling wave protection approach for microgrids using a wavelet-driven deep neural network named WaveletKernelNet (WKN). Compared with conventional methods, the presented approach provides enhanced sensitivity, higher selectivity, and better identification of various faults in microgrids. Extensive case studies validate the efficacy and excellent performance of the devised approach.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2021

Molecular dynamics simulation of metallic Al–Ce liquids using a neural network machine learning interatomic potential

Al-rich Al-Ce alloys have the possibility of replacing heavier steel and cast-irons for use in high-temperature applications. Knowledge about the structures and properties of Al-Ce alloys at liquid state is vital for optimizing the manufacture process to produce desired allows. However, reliable molecular dynamics simulation of Al-Ce alloy systems remains a great challenge due to the lack of accurate Al-Ce interatomic potential. In this work, an artificial neural network (ANN) deep machine learning (ML) method is used to develop a reliable interatomic potential for Al-Ce alloy. Ab initio molecular dynamics (AIMD) simulation data on Al-Ce liquid with small unit cell (~200 atoms) and on the known Al-Ce crystalline compounds are collected to train the interatomic potential using ANN-ML. The obtained ANN-ML model reproduces well the energies, forces, and atomic structure of Al 90 Ce 10 liquid and crystalline phases of Al-Ce compounds in comparison with ab initio results. The developed ANN-ML potential is applied in molecular dynamics simulations to study the structures and properties of metallic Al 90 Ce 10 liquid, which would provide useful insight for guiding experimental process to produce desired Al-Ce allows.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2020

Methods for R&D Portfolio Analysis and Evaluation (Workshop Report)

The Workshop on Methods for R&D Portfolio Analysis and Evaluation convened on 17–18 July 2019 at the National Renewable Energy Laboratory in Golden, Colorado, and examined strengths and weaknesses of the various methodologies applicable to R&D portfolio modeling, analysis, and decision support, given pragmatic constraints such as data availability, uncertainties in estimating the impact of R&D spending, and practical operational overheads. Participants employed their deep expertise in approaches such as stochastic optimization, real options, Monte-Carlo analysis, Bayesian networks, decision theory, complex systems analysis, deep uncertainty, and technology-evolution modeling to critique the initial example models developed by the project’s core team and to conduct thought experiments grounded in real-life technology models, progress data, expert elicitation, and portfolio information. This engagement of participants’ methodological expertise with the practical requirements of real-life portfolio decision support yielded ideas for improved approaches, alternative methodological hypotheses, and hybridization of methodologies that are well-grounded theoretically, computationally sound, and realistically executable given data availability and other practical constraints.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2020

Methods for R&D Portfolio Analysis and Evaluation (Workshop Report)

The Workshop on Methods for R&D Portfolio Analysis and Evaluation convened on 17-18 July 2019 at the National Renewable Energy Laboratory in Golden, Colorado, and examined strengths and weaknesses of the various methodologies applicable to R&D portfolio modeling, analysis, and decision support, given pragmatic constraints such as data availability, uncertainties in estimating the impact of R&D spending, and practical operational overheads. Participants employed their deep expertise in approaches such as stochastic optimization, real options, Monte-Carlo analysis, Bayesian networks, decision theory, complex systems analysis, deep uncertainty, and technology-evolution modeling to critique the initial example models developed by the project’s core team and to conduct thought experiments grounded in real-life technology models, progress data, expert elicitation, and portfolio information. This engagement of participants’ methodological expertise with the practical requirements of real-life portfolio decision support yielded ideas for improved approaches, alternative methodological hypotheses, and hybridization of methodologies that are well-grounded theoretically, computationally sound, and realistically executable given data availability and other practical constraints.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2022

SMALE: Enhancing Scalability of Machine Learning Algorithms on Extreme-Scale Computing Platforms

Deployment and execution of machine learning tasks on extreme-scale computing platforms face several significant technical challenges: 1) High computing cost incurred by dense networks – The computing workload of deep networks with densely-connected topology increases rapidly with the network size, imposing a non-scalable computing model of extreme-scale computing platforms; 2) Non-optimized workload distribution – Many advanced deep learning algorithms, e.g., sparsification and irregular net-work topology, produce very unbalanced workload distribution on extreme-scale computing platforms. The computation efficiency is greatly hindered by the incurred data and computation redundancies as well as long tails of the node with extensive workload; 3) Constraints in data movement and I/O bottle-neck – Inter-node data movement in extreme-scale computing platforms are associated with high energy and latency costs, and subject to the constraints of I/O bandwidth; and 4) Generalization of algorithm realization and acceleration on computing platforms – The large varieties of machine learning algorithms and structures of extreme-scale computing platforms make the derivation of a generalized algorithm realization and acceleration method very challenging, which, however, is the requirement by domain scientists and interested users. We call the above challenges Smale’s Problems in Machine Learning and Understanding for High-Performance Computing Scientific Discovery. The objective of our three-year research project is to develop a holistic innovation set at structure, assembly, and acceleration layers of machine learning algorithms to address the above challenges in algorithm deployment and execution. Three tasks are particularly performed, including: At the algorithm structure level, we investigate the techniques that can structurally sparsify on the topology of deep networks for computing workload reduction. We also study clustering and pruning techniques that can optimize the workload distributions over the extreme-scale computing platforms; At the algorithm assembly level, we derive a unified learning framework for unsupervised transfer learning and dynamic growing capabilities. Novel training methods are also exploited to enhance the training efficiency of the proposed framework; At the algorithm acceleration level, we will develop a series of techniques that can accelerate the computation of sparse matrix operations, which are one of the core executions in deep learning and optimize memory access of the concerned platforms. Our proposed techniques attack the fundamental problems in machine learning algorithms running on extreme-scale computing platforms by vertically integrating the solutions at three closely entangled layers, paving the long-term scaling path of machine learning applications under DOE context. Three tasks corresponding to the above respective research orientations are performed during the three-year project period with our collaborators at ORNL. The outcome of the proposed project is anticipated to form a holistic solution set of novel algorithms and network topologies, efficient training techniques, and fast acceleration methods to promote the computing scalability of the machine learning applications of particular interest to DOE.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

INTEGRATE - Inverse Network Transformations for Efficient Generation of Robust Airfoil and Turbine Enhancements

The INTEGRATE (Inverse Network Transformations for Efficient Generation of Robust Airfoil and Turbine Enhancements) project is developing a new inverse-design capability for the aerodynamic design of wind turbine rotors using invertible neural networks. This AI-based design technology can capture complex non-linear aerodynamic effects while being 100 times faster than design approaches based on computational fluid dynamics. This project enables innovation in wind turbine design by accelerating time to market through higher-accuracy early design iterations to reduce the levelized cost of energy. INVERTIBLE NEURAL NETWORKS Researchers are leveraging a specialized invertible neural network (INN) architecture along with the novel dimension-reduction methods and airfoil/blade shape representations developed by collaborators at the National Institute of Standards and Technology (NIST) learns complex relationships between airfoil or blade shapes and their associated aerodynamic and structural properties. This INN architecture will accelerate designs by providing a cost-effective alternative to current industrial aerodynamic design processes, including: - Blade element momentum (BEM) theory models: limited effectiveness for design of offshore rotors with large, flexible blades where nonlinear aerodynamic effects dominate - Direct design using computational fluid dynamics (CFD): cost-prohibitive - Inverse-design models based on deep neural networks (DNNs): attractive alternative to CFD for 2D design problems, but quickly overwhelmed by the increased number of design variables in 3D problems AUTOMATED COMPUTATIONAL FLUID DYNAMICS FOR TRAINING DATA GENERATION - MERCURY FRAMEWORK The INN is trained on data obtained using the University of Marylands (UMD) Mercury Framework, which has with robust automated mesh generation capabilities and advanced turbulence and transition models validated for wind energy applications. Mercury is a multi-mesh paradigm, heterogeneous CPU-GPU framework. The framework incorporates three flow solvers at UMD, 1) OverTURNS, a structured solver on CPUs, 2) HAMSTR, a line based unstructured solver on CPUs, and 3) GARFIELD, a structured solver on GPUs. The framework is based on Python, that is often used to wrap C or Fortran codes for interoperability with other solvers. Communication between multiple solvers is accomplished with a Topology Independent Overset Grid Assembler (TIOGA). NOVEL AIRFOIL SHAPE REPRESENTATIONS USING GRASSMAN SPACES We developed a novel representation of shapes which decouples affine-style deformations from a rich set of data-driven deformations over a submanifold of the Grassmannian. The Grassmannian representation as an analytic generative model, informed by a database of physically relevant airfoils, offers (i) a rich set of novel 2D airfoil deformations not previously captured in the data , (ii) improved low-dimensional parameter domain for inferential statistics informing design/manufacturing, and (iii) consistent 3D blade representation and perturbation over a sequence of nominal shapes. TECHNOLOGY TRANSFER DEMONSTRATION - COUPLING WITH NREL WISDEM Researchers have integrated the inverse-design tool for 2D airfoils (INN-Airfoil) into WISDEM (Wind Plant Integrated Systems Design and Engineering Model), a multidisciplinary design and optimization framework for assessing the cost of energy, as part of tech-transfer demonstration. The integration of INN-Airfoil into WISDEM allows for the design of airfoils along with the blades that meet the dynamic design constraints on cost of energy, annual energy production, and the capital costs. Through preliminary studies, researchers have shown that the coupled INN-Airfoil + WISDEM approach reduces the cost of energy by around 1% compared to the conventional design approach. This page will serve as a place to easily access all the publications from this work and the repositories for the software developed and released through this pr...

aerodynamics↗
DOE OSTI2024

Time Series Foundation Models and Deep Learning Architectures for Earthquake Temporal and Spatial Nowcasting

Advancing the capabilities of earthquake nowcasting, the real-time forecasting of seismic activities, remains crucial for reducing casualties. This multifaceted challenge has recently gained attention within the deep learning domain, facilitated by the availability of extensive earthquake datasets. Despite significant advancements, the existing literature on earthquake nowcasting lacks comprehensive evaluations of pre-trained foundation models and modern deep learning architectures; each focuses on a different aspect of data, such as spatial relationships, temporal patterns, and multi-scale dependencies. This paper addresses the mentioned gap by analyzing different architectures and introducing two innovative approaches called Multi Foundation Quake and GNNCoder. We formulate earthquake nowcasting as a time series forecasting problem for the next 14 days within 0.1-degree spatial bins in Southern California. Earthquake time series are generated using the logarithm energy released by quakes, spanning 1986 to 2024. Our comprehensive evaluations demonstrate that our introduced models outperform other custom architectures by effectively capturing temporal-spatial relationships inherent in seismic data. The performance of existing foundation models varies significantly based on the pre-training datasets, emphasizing the need for careful dataset selection. However, we introduce a novel method, Multi Foundation Quake, that achieves the best overall performance by combining a bespoke pattern with Foundation model results handled as auxiliary streams.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

A Membrane Contactor Enabling Energy-Efficient CO 2 Capture from Point Sources with Deep Eutectic Solvents

We demonstrate a scalable and energy-efficient hollow fiber membrane contactor (HFMC)-based process using a green solvent for CO 2 capture. This process uses a deep eutectic solvent (DES) in an HFMC to provide close interfacial interactions and contact between the DES and CO 2 . This approach overcomes disadvantages associated with direct absorption in DES and could potentially be applied to a variety of solvent-based CO 2 capture methods. Commercial low-cost polymer hollow fiber membranes (e.g., microporous polypropylene) were evaluated for CO 2 capture with reline, a prototypical DES. Single-gas measurements showed that the DES-based polypropylene HFMC can capture and separate CO 2 while rejecting N2. From a mixed gas containing 50 mol % N 2 and 50 mol % CO ν , the DES-based HFMC separated CO 2 with a purity of 96.9 mol %. The effect of several process parameters including solvent flow rate, pressure, and temperature on the CO 2 separation performance was studied. The flux of the recovered CO 2 was 67.43 mmole/m 2 /h at a feed pressure of 4 bar. In situ Fourier transform infrared (FTIR) measurements combined with density functional theory (DFT)-based molecular dynamics simulations revealed that reline absorbs CO 2 by physical absorption without forming a new chemical compound, and CO 2 separation by reline occurs via the pressure swing mechanism. This research provides fundamental insights about physical solvent-based separation processes and a pathway toward practical deployment.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Machine Learning-Guided Discovery of Ternary Compounds Containing La, P, and Group 14 Elements

In this work, we integrate a deep machine learning (ML) method with first-principles calculations to efficiently search for the energetically favorable ternary compounds. Using La–Si–P as a prototype system, we demonstrate that ML-guided first-principles calculations can efficiently explore crystal structures and their relative energetic stabilities, thus greatly accelerate the pace of material discovery. A number of new La–Si–P ternary compounds with formation energies less than 30 meV/atom above the known ternary convex hull are discovered. Among them, the formation energies of La 5 SiP 3 and La 2 SiP phases are only 2 and 10 meV/atom, respectively, above the convex hull. These two compounds are dynamically stable with no imaginary phonon modes. Moreover, by replacing Si with heavier-group 14 elements in the eight lowest-energy La–Si–P structures from our ML-guided predictions, a number of low-energy La–X–P phases (X = Ge, Sn, Pb) are predicted.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

DeepZipper. II. Searching for Lensed Supernovae in Dark Energy Survey Data with Deep Learning

Gravitationally lensed supernovae (LSNe) are important probes of cosmic expansion, but they remain rare and difficult to find. Current cosmic surveys likely contain 5–10 LSNe in total while next-generation experiments are expected to contain several hundred to a few thousand of these systems. We search for these systems in observed Dark Energy Survey (DES) five year SN fields—10 3 sq. deg. regions of sky imaged in the griz bands approximately every six nights over five years. To perform the search, we utilize the DeepZipper approach: a multi-branch deep learning architecture trained on image-level simulations of LSNe that simultaneously learns spatial and temporal relationships from time series of images. We find that our method obtains an LSN recall of 61.13% and a false-positive rate of 0.02% on the DES SN field data. DeepZipper selected 2245 candidates from a magnitude-limited (m i < 22.5) catalog of 3,459,186 systems. We employ human visual inspection to review systems selected by the network and find three candidate LSNe in the DES SN fields.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2024

Recovered supernova Ia rate from simulated LSST images

Aims.TheVera C. RubinObservatory’s Legacy Survey of Space and Time (LSST) will revolutionize time-domain astronomy by detecting millions of different transients. In particular, it is expected to increase the number of known type Ia supernovae (SN Ia) by a factor of 100 compared to existing samples up to redshift ∼1.2. Such a high number of events will dramatically reduce statistical uncertainties in the analysis of the properties and rates of these objects. However, the impact of all other sources of uncertainty on the measurement of the SN Ia rate must still be evaluated. The comprehension and reduction of such uncertainties will be fundamental both for cosmology and stellar evolution studies, as measuring the SN Ia rate can put constraints on the evolutionary scenarios of different SN Ia progenitors. Methods.We used simulated data from the Dark Energy Science Collaboration (DESC) Data Challenge 2 (DC2) and LSST Data Preview 0 to measure the SN Ia rate on a 15 deg 2 region of the “wide-fast-deep” area. We selected a sample of SN candidates detected in difference images, associated them to the host galaxy with a specially developed algorithm, and retrieved their photometric redshifts. We then tested different light-curve classification methods, with and without redshift priors (albeit ignoring contamination from other transients, as DC2 contains only SN Ia). We discuss how the distribution in redshift measured for the SN candidates changes according to the selected host galaxy and redshift estimate. Results.We measured the SN Ia rate, analyzing the impact of uncertainties due to photometric redshift, host-galaxy association and classification on the distribution in redshift of the starting sample. We find that we are missing 17% of the SN Ia, on average, with respect to the simulated sample. As 10% of the mismatch is due to the uncertainty on the photometric redshift alone (which also affects classification when used as a prior), we conclude that this parameter is the major source of uncertainty. We discuss possible reduction of the errors in the measurement of the SN Ia rate, including synergies with other surveys, which may help us to use the rate to discriminate different progenitor models.

Astronomy & Astrophysics↗
DOE OSTI2020

Skyrmion fluctuations at a first-order phase transition boundary

Magnetic skyrmions are topologically protected spin textures with promising prospects for applications in data storage. They can form a lattice state due to competing magnetic interactions and are commonly found in a small region of the temperature—magnetic field phase diagram. Recent work has demonstrated that these magnetic quasi-particles fluctuate at the μeV energy scale. Here, we use a coherent x-ray correlation method at an x-ray free-electron laser to investigate these fluctuations in a magnetic phase coexistence region near a first-order transition boundary where fluctuations are not expected to play a major role. Surprisingly, we find that the relaxation of the intermediate scattering function at this transition differs significantly compared to that deep in the skyrmion lattice phase. The observation of a compressed exponential behavior suggests solid-like dynamics, often associated with jamming. We assign this behavior to disorder and the phase coexistence observed in a narrow field-window near the transition, which can cause fluctuations that lead to glassy behavior.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2023

Physics guided machine learning for multi-material decomposition of tissues from dual-energy CT scans of simulated breast models with calcifications

We introduce a physics guided data-driven method for image-based multi-material decomposition for dual-energy computed tomography (CT) scans. The method is demonstrated for CT scans of virtual human phantoms containing more than two types of tissues. The method is a physics-driven supervised learning technique. We take advantage of the mass attenuation coefficient of dense materials compared to that of muscle tissues to perform a preliminary extraction of the dense material from the images using unsupervised methods. We then perform supervised deep learning on the images processed by the extracted dense material to obtain the final multi-material tissue map. The method is demonstrated on simulated breast models with calcifications as the dense material placed amongst the muscle tissues. The physics-guided machine learning method accurately decomposes the various tissues from input images, achieving a normalized root-mean-squared error of 2.75%.

Gopalakrishnan Meena, Murali↗
DOE OSTI2022

High-dimensional anomaly detection with radiative return in $\mathcal{e}$⁺$\mathcal{e}$⁻ collisions

Experiments at a future $\mathcal{e}$⁺$\mathcal{e}$⁻ collider will be able to search for new particles with masses below the nominal centre-of-mass energy by analyzing collisions with initial-state radiation (radiative return). We show that machine learning methods that use imperfect or missing training labels can achieve sensitivity to generic new particle production in radiative return events. In addition to presenting an application of the classification without labels (CWoLa) search method in $\mathcal{e}$⁺$\mathcal{e}$⁻ collisions, our study combines weak supervision with variable-dimensional information by deploying a deep sets neural network architecture. We have also investigated some of the experimental aspects of anomaly detection in radiative return events and discuss these in the context of future detector design.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2022

On the Verification of Deep Reinforcement Learning Solution for Intelligent Operation of Distribution Grids

Capabilities of deep reinforcement learning (DRL) in obtaining fast decision policies in high dimensional and stochastic environments have led to its extensive use in operational research, including the operation of distribution grids with high penetration of distributed energy resources (DER). However, the feasibility and robustness of DRL solutions are not guaranteed for the system operator, and hence, those solutions may be of limited practical value. This paper proposes an analytical method to find feasibility ellipsoids that represent the range of multi-dimensional system states in which the DRL solution is guaranteed to be feasible. Empirical studies and stochastic sampling determine the ratio of the discovered to the actual feasible space as a function of the sample size. In addition, the performance of logarithmic, linear, and exponential penalization of infeasibility during the DRL training are studied and compared in order to reduce the number of infeasible solutions

Hosseini, Mohammad Mehdi↗