SEARCH · Engineering Papers

Results for “Deep Operator Networks”

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 109 records · Page 6

All sources NASA NTRS DOE OSTI

DOE OSTI2022

Arizona State University Requirements Analysis Report

EPOC uses the Deep Dive process to discuss and analyze current and planned science, research, or education activities and the anticipated data output of a particular use case, site, or project to help inform the strategic planning of a campus or regional networking environment. This includes understanding future needs related to network operations, network capacity upgrades, and other technological service investments. A Deep Dive comprehensively surveys major research stakeholders’ plans and processes in order to investigate data management requirements over the next 5–10 years. Between October 2021 and February 2022 staff members from the Engagement and Performance Operations Center (EPOC) met with researchers and staff from Arizona State University (ASU) for the purpose of a Deep Dive into scientific and research drivers. The goal of this activity was to help characterize the requirements for a number of campus use cases, and to enable cyberinfrastructure support staff to better understand the needs of the researchers within the community.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

DOE OSTI2021

University of Central Florida Campus-Wide Deep Dive

EPOC uses the Deep Dive process to discuss and analyze current and planned science use cases and anticipated data output of a particular use case, site, or project to help inform the strategic planning of a campus or regional networking environment. This includes understanding future needs related to network operations, network capacity upgrades, and other technological service investments. A Deep Dive comprehensively surveys major research stakeholders’ plans and processes in order to investigate data management requirements over the next 5–10 years. Deep Dives help ensure that key stakeholders have a common understanding of the issues and the actions that a campus or regional network may need to undertake to offer solutions. The EPOC team leads the effort and relies on collaboration with the hosting site or network, and other affiliated entities that participate in the process. EPOC organizes, convenes, executes, and shares the outcomes of the review with all stakeholders. Between December 2020 and August 2021, staff members from the Engagement and Performance Operations Center (EPOC) met with researchers and staff at University of Central Florida (UCF) for the purpose of a Campus-Wide Deep Dive into research drivers. The goal of this meeting was to help characterize the requirements for five campus research use cases and to enable cyberinfrastructure support staff to better understand the needs of the researchers they support.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

DOE OSTI2021

A seamless multiscale operator neural network for inferring bubble dynamics

Modelling multiscale systems from nanoscale to macroscale requires the use of atomistic and continuum methods and, correspondingly, different computer codes. Here, we develop a seamless method based on DeepONet, which is a composite deep neural network (a branch and a trunk network) for regressing operators. In particular, we consider bubble growth dynamics, and we model tiny bubbles of initial size from 100 nm to 10 $\mathrm {\mu }\textrm {m}$ , modelled by the Rayleigh–Plesset equation in the continuum regime above 1 $\mathrm {\mu }\textrm {m}$ and the dissipative particle dynamics method for bubbles below 1 $\mathrm {\mu }\textrm {m}$ in the atomistic regime. After an offline training based on data from both regimes, DeepONet can make accurate predictions of bubble growth on-the-fly (within a fraction of a second) across four orders of magnitude difference in spatial scales and two orders of magnitude in temporal scales. The framework of DeepONet is general and can be used for unifying physical models of different scales in diverse multiscale applications.

Mechanics↗

DOE OSTI2026

Polarized target nuclear magnetic resonance measurements with deep neural networks

Continuous-wave Nuclear Magnetic Resonance (CW-NMR) operated in constant-current mode has served as a foundational technique for polarization measurement in solid-state dynamically polarized targets within nuclear and high-energy physics experiments for several decades, and it remains an essential tool. Conventional Q-meter-based phase-sensitive detection is critical for precise real-time determination of target polarization during scattering runs. However, the accuracy and reliability of these measurements are frequently compromised by elevated noise levels, baseline drift, and systematic uncertainties arising from signal isolation and fitting, ultimately degrading the overall experimental figure of merit. In this work, we report the first successful application of neural network architectures to continuous-wave NMR polarization metrology. By leveraging advanced machine learning techniques for signal extraction and denoising, we achieve a substantial reduction of fitting uncertainties under a variety of realistic simulated and experimental conditions. These improvements translate directly into more robust real-time (online) polarization monitoring and higher precision in subsequent offline analysis. By reducing analysis-induced uncertainty, the resulting methodology can improve the effective figure of merit for scattering experiments employing dynamically polarized targets and provides a new toolset for NMR-based polarimetry in high-energy and nuclear physics.

Metrology↗

DOE OSTI2022

Probing Electron Beam Induced Transformations on a Single-Defect Level via Automated Scanning Transmission Electron Microscopy

A robust approach for real-time analysis of the scanning transmission electron microscopy (STEM) data streams, based on ensemble learning and iterative training (ELIT) of deep convolutional neural networks, is implemented on an operational microscope, enabling the exploration of the dynamics of specific atomic configurations under electron beam irradiation via an automated experiment in STEM. Combined with beam control, this approach allows studying beam effects on selected atomic groups and chemical bonds in a fully automated mode. Here, in this study, we demonstrate atomically precise engineering of single vacancy lines in transition metal dichalcogenides and the creation and identification of topological defects in graphene. The ELIT-based approach facilitates direct on-the-fly analysis of the STEM data and engenders real-time feedback schemes for probing electron beam chemistry, atomic manipulation, and atom by atom assembly.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2021

NOAA National Centers for Environmental Information Fisheries Acoustics Archive Network Deep Dive

EPOC uses the Deep Dive process to discuss and analyze current and planned science use cases and anticipated data output of a particular use case, site, or project to help inform the strategic planning of a campus or regional networking environment. This includes understanding future needs related to network operations, network capacity upgrades, and other technological service investments. A Deep Dive comprehensively surveys major research stakeholders’ plans and processes in order to investigate data management requirements over the next 5–10 years. Deep Dives help ensure that key stakeholders have a common understanding of the issues and the actions that a campus or regional network may need to undertake to offer solutions. The EPOC team leads the effort and relies on collaboration with the hosting site or network, and other affiliated entities that participate in the process. EPOC organizes, convenes, executes, and shares the outcomes of the review with all stakeholders. Between May 2021 and August 2021, staff members from the Engagement and Performance Operations Center (EPOC) met with researchers and staff from the National Oceanic and Atmospheric Administration (NOAA)'s N-Wave (the Enterprise network that supports the NOAA mission) and National Centers for Environmental Information (NCEI)'s Fisheries Acoustics Archive for the purpose of a recording a Deep Dive into research drivers. The goal of these meetings was to help characterize the requirements for the research use case, and to enable cyberinfrastructure support staff to better understand the needs of the researchers they support.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2025

Deep Reinforcement Learning for Distribution System Operations: A Tutorial and Survey

Here, the rapid evolution of modern electric power distribution systems into complex networks of interconnected active devices, distributed generation (DG), and storage poses increasing difficulties for system operators. The large-scale integration of distributed energy resources (DERs) and the rapid exchange of measurement data via communication networks present major opportunities for advancing grid operations but also introduce greater uncertainty, higher data dimensionality, more complex network and device models, and challenging control and optimization problems. Deep reinforcement learning (DRL) algorithms are promising in addressing these challenges. However, they have not been effectively adapted for power systems applications, requiring extensive customization for implementation and evaluation. This has resulted in reproducibility challenges and a steep learning curve for researchers new to applying DRL algorithms to the power systems domain. To bridge these gaps, this tutorial aims to serve as a valuable resource for researchers interested in exploring learning-based algorithms to operate active power distribution networks. Specifically, this work presents a generalized process for translating sequential decision-making problems in power distribution systems into Markov decision process (MDP) formulations, illustrated through concrete grid service examples. Additionally, we introduce a simple environment design strategy to develop and evaluate example DRL algorithms for distribution system applications, complete with an included code repository to guide users through environment construction.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2021

South Dakota Region Scientific Deep Dive

EPOC uses the Deep Dive process to discuss and analyze current and planned science use cases and anticipated data output of a particular use case, site, or project to help inform the strategic planning of a campus or regional networking environment. This includes understanding future needs related to network operations, network capacity upgrades, and other technological service investments. A Deep Dive comprehensively surveys major research stakeholders’ plans and processes in order to investigate data management requirements over the next 5–10 years. Questions crafted to explore this space include the following: 1) How, and where, will new data be analyzed and used? 2) How will the process of doing science change over the next 5–10 years? and 3) How will changes to the underlying hardware and software technologies influence scientific discovery? Deep Dives help ensure that key stakeholders have a common understanding of the issues and the actions that a campus or regional network may need to undertake to offer solutions. The EPOC team leads the effort and relies on collaboration with the hosting site or network, and other affiliated entities that participate in the process. EPOC organizes, convenes, executes, and shares the outcomes of the review with all stakeholders

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

DOE OSTI2024

Distributed-Memory Sparse Deep Neural Network Inference Using Global Arrays

Partitioned Global Address Space (PGAS) models exhibit tremendous promise in developing efficient and productive distributed-memory parallel applications. They have been used extensively in scientific computations due to conveniently offering a ``shared-memory''-like model and convenient interfaces that separate communication with synchronization. Traditionally, PGAS communication models have been applied to dense/contiguously distributed data, but most modern applications depict varied levels of sparsity. Existing PGAS models require certain adaptations to support distributed sparse computations, since associated computations often require matrix arithmetic, in addition to data movement. The Global Arrays toolkit from Pacific Northwest National Laboratory (PNNL) is one of the earliest PGAS models to combine one-sided data communication and distributed matrix operations and is still used in the popular NWChem quantum chemistry suite. Recently, we have expanded the Global Arrays toolkit to support common sparse operations, like sparse matrix-dense matrix multiplies (SpMM), sparse matrix-sparse matrix multiplication (SpGEMM) and Sampled Dense-Dense Matrix Multiplication (SDDMM). As it turns out, these operations are the bedrock of sparse Deep Learning (DL); sparse deep neural networks and Graph Neural Networks (GNNs) have gained increasing attention recently in achieving speedups on training and inference with reduced memory footprints. Unlike scientific applications in High Performance Computing (HPC), modern (distributed-memory capable) DL toolkits often rely on non-standardized and closed-source vendor software optimizations, creating challenges in software-hardware co-design at scale. Our goal is to support a variety of distributed-memory sparse matrix operations and helper functions in the newly created Sparse Global Arrays (SGA), such that it is possible to build portable and productive Machine Learning scenarios for algorithm/software and hardware codesign purposes. Contemporary data-parallel schemes for training/inference are undergoing a major overhaul since model replication limits scalability and causes resource inefficiencies. As such, we have adopted tensor parallelism in decomposing the model and inputs, to mitigate memory issues. Current implementation is built on top of MPI and uses CPUs to maximize the portability across the platforms.

Distributed computing, machine learning↗

DOE OSTI2022

Physics-constrained deep neural network method for estimating parameters in a redox flow battery

Here, in this paper, we present a physics-constrained deep neural network (PCDNN) method for parameter estimation in the zero-dimensional (0D) model of the vanadium redox flow battery (VRFB). In this approach, we use deep neural networks to approximate the model parameters as functions of the operating conditions. This method allows the integration of VRFB computational models as the physical constraints in the parameter learning process, leading to enhanced accuracy of parameter estimation and cell voltage prediction. Using an experimental dataset, we demonstrate that the PCDNN method can estimate model parameters for a range of operating conditions and improve the 0D model prediction of voltage compared to the 0D model prediction with constant operation-condition-independent parameters estimated with traditional inverse methods. We also demonstrate that the PCDNN approach has an improved generalization ability for estimating parameter values for operating conditions not used in the training process.

25 ENERGY STORAGE↗

DOE OSTI2025

Accurate and rapid acoustic damage characterization in complex structures using sparse sensor networks and deep learning models

Damage diagnosis in critical components is essential for ensuring the safety and reliability of operations across industries, spanning manufacturing, aerospace, and energy. Traditional acoustic nondestructive testing methods primarily focus on detecting defects through the direct scattering of single-mode incident waves from the damage, which limit their applicability to simple structures and small inspection areas. Our earlier research demonstrated that machine learning algorithms combined with sparse sensor networks can identify critical defect signatures even from multiply scattered, multi-mode acoustic signals, indicating the potential for improved defect inspection in complex, real-world structures. In this work, we demonstrate the successful implementation of this approach in a fixed sensor configuration to rapidly and accurately detect simulated defects in a geometrically complex, real-world structure, a brake rotor hub. Three different types of defects were physically simulated on the surface of the hub, and the collected data were used to train an autoencoder-based deep learning model. Two models were tested, one using single measurements and the other using multiple measurements taking advantage of the spatial distribution of the sensor network. After training, the multi-measurement model achieved 100 % accuracy in identifying, classifying, and locating unseen, unique damages. This work illustrates the potential of the proposed method for a wide range of industrial applications.

36 MATERIALS SCIENCE↗

DOE OSTI2024

Physics-Guided, Physics-Informed, and Physics-Encoded Neural Networks and Operators in Scientific Computing: Fluid and Solid Mechanics

Abstract Advancements in computing power have recently made it possible to utilize machine learning and deep learning to push scientific computing forward in a range of disciplines, such as fluid mechanics, solid mechanics, materials science, etc. The incorporation of neural networks is particularly crucial in this hybridization process. Due to their intrinsic architecture, conventional neural networks cannot be successfully trained and scoped when data are sparse, which is the case in many scientific and engineering domains. Nonetheless, neural networks provide a solid foundation to respect physics-driven or knowledge-based constraints during training. Generally speaking, there are three distinct neural network frameworks to enforce the underlying physics: (i) physics-guided neural networks (PgNNs), (ii) physics-informed neural networks (PiNNs), and (iii) physics-encoded neural networks (PeNNs). These methods provide distinct advantages for accelerating the numerical modeling of complex multiscale multiphysics phenomena. In addition, the recent developments in neural operators (NOs) add another dimension to these new simulation paradigms, especially when the real-time prediction of complex multiphysics systems is required. All these models also come with their own unique drawbacks and limitations that call for further fundamental research. This study aims to present a review of the four neural network frameworks (i.e., PgNNs, PiNNs, PeNNs, and NOs) used in scientific computing research. The state-of-the-art architectures and their applications are reviewed, limitations are discussed, and future research opportunities are presented in terms of improving algorithms, considering causalities, expanding applications, and coupling scientific and deep learning solvers.

Computer Science↗

DOE OSTI2026

Detection and imaging of chemicals and hidden explosives using terahertz time-domain spectroscopy and deep learning

Detecting concealed chemicals and explosives remains a critical challenge in global security. Terahertz time-domain spectroscopy (THz-TDS) offers a promising non-invasive and stand-off detection technique owing to its ability to penetrate optically opaque materials without causing ionization damage. While many chemicals exhibit distinct spectral features in the terahertz range, conventional terahertz-based detection methods often struggle in real-world environments, where variations in sample geometry, thickness, and packaging can lead to inconsistent spectral responses. In this study, we present a chemical imaging system that integrates THz-TDS with deep learning to enable accurate pixel-level identification and classification of different explosives. Operating in reflection mode and enhanced with plasmonic nanoantenna arrays, our THz-TDS system achieves a peak dynamic range of 96 dB and a detection bandwidth of 4.5 THz, supporting practical, stand-off operation. By analyzing individual time-domain pulses with deep neural networks, the system exhibits strong resilience to environmental variations and sample inconsistencies. Blind testing across eight chemicals—including pharmaceutical excipients and explosive compounds—resulted in an average classification accuracy of 99.42% at the pixel level. Notably, the system maintained an average accuracy of 88.83% when detecting explosives concealed under opaque paper coverings, demonstrating its robust generalization capability. These results highlight the potential of combining advanced terahertz spectroscopy with neural networks for highly sensitive and specific chemical and explosive detection in diverse and operationally relevant scenarios.

Imaging and sensing↗

DOE OSTI2020

Data optimization for large batch distributed training of deep neural networks

Distributed training in deep learning (DL) is common practice as data and models grow. The current practice for distributed training of deep neural networks faces the challenges of communication bottlenecks when operating at scale, and model accuracy deterioration with an increase in global batch size. Present solutions focus on improving message exchange efficiency as well as implementing techniques to tweak batch sizes and models in the training process. The loss of training accuracy typically happens because the loss function gets trapped in a local minima. We observe that the loss landscape minimization is shaped by both the model and training data and propose a data optimization approach that utilizes machine learning to implicitly smooth out the loss landscape resulting in fewer local minima. Our approach filters out data points which are less important to feature learning, enabling us to speed up the training of models on larger batch sizes to improved accuracy.

Gahlot, Shubhankar↗

DOE OSTI2023

On the influence of over-parameterization in manifold based surrogates and deep neural operators

Constructing accurate and generalizable approximators (surrogate models) for complex physico-chemical processes exhibiting highly non-smooth dynamics is challenging. The main question is what type of surrogate models we should construct and should these models be under-parameterized or over-parameterized. In this work, we propose new developments and perform comparisons for two promising approaches: manifold-based polynomial chaos expansion (m-PCE) and the deep neural operator (DeepONet), and we examine the effect of over-parameterization on generalization. While m-PCE enables the construction of a mapping by first identifying low-dimensional embeddings of the input functions, parameters, and quantities of interest (QoIs), a neural operator learns the nonlinear mapping via the use of deep neural networks. Here, we demonstrate the performance of these methods in terms of generalization accuracy by solving the 2D time-dependent Brusselator reaction-diffusion system with uncertainty sources, modeling an autocatalytic chemical reaction between two species. We first propose an extension of the m-PCE by constructing a mapping between latent spaces formed by two separate embeddings of the input functions and the output QoIs. To further enhance the accuracy of the DeepONet, we introduce weight self-adaptivity in the loss function. We demonstrate that the performance of m-PCE and DeepONet is comparable for cases of relatively smooth input-output mappings. However, when highly non-smooth dynamics is considered, DeepONet shows higher approximation accuracy. We also find that for m-PCE, modest over-parameterization leads to better generalization, both within and outside of distribution, whereas aggressive over-parameterization leads to over-fitting. In contrast, an even highly over-parameterized DeepONet leads to better generalization for both smooth and non-smooth dynamics. Furthermore, we compare the performance of the above models with another recently proposed operator learning model, the Fourier Neural Operator, and show that its over-parameterization also leads to better generalization. Taken together, our studies show that m-PCE can provide very good accuracy at very low training cost, whereas a highly over-parameterized DeepONet can provide better accuracy and robustness to noise but at higher training cost. In both methods, the inference cost is negligible.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2021

Baylor University Campus-Wide Deep Dive

In January 2020, staff members from the Engagement and Performance Operations Center (EPOC) and the Lonestar Education And Research Network (LEARN) met with researchers and staff at Baylor University for the purpose of a Campus-Wide Deep Dive into research drivers. The goal of this meeting was to help characterize the requirements for five campus research use cases and to enable cyberinfrastructure support staff to better understand the needs of the researchers they support. Profiled scientific use cases included: - Experimental High Energy Physics (HEP) - Proton Computed Tomography (pCT) - Nutrition and Relation to Digestive Microbiome - Baylor University Core Research Facilities - Molecular Quantum-dot Cellular Automata (QCA), and Material Science of Quantum Computing - Modeling and Simulation of Low-Dimensional and Nano-Structured Materials - Computational Fluid Dynamics Material for this event included the written documentation from each of the research areas at Baylor University, documentation about the current state of technology support, and a write-up of the discussion that took place in person. The Case Studies highlighted the ongoing challenges that Baylor University has in supporting a cross-section of established and emerging research use cases. Each Case Study mentioned unique challenges which were summarized into common needs. These included: - Tradeoffs for network/software security, and usability of the resulting infrastructure. Better communication to set expectations and understand realities is required. - Computation use on campus is widespread and healthy. While no major problems were uncovered, upgrades to maintain current usage patterns and encourage growth will be required. - Storage is a critical need for enterprise use cases and research. In particular, a campus wide ‘storage architecture’ to support research use cases (e.g. instruments, data sharing) is required in the 2-5 year time window. - Instrumentation on campus is healthy and expanding. Technology must scale with this in the form of computation and storage. - Working with LEARN to upgrade network capacity (in multiples of 10G, or upgrades to 100G) will be required in the 1-3 year time frame. - Network monitoring and visibility will help to establish external science use cases. - Data sharing via portal systems is not currently a critical need, but growing in scope. EPOC can assist Baylor with options.

99 GENERAL AND MISCELLANEOUS↗

DOE OSTI2021

Alfvén eigenmode classification based on ECE diagnostics at DIII-D using deep recurrent neural networks

Modern tokamaks have achieved significant fusion production, but further progress towards steady-state operation has been stymied by a host of kinetic and MHD instabilities. Control and identification of these instabilities is often complicated, warranting the application of data-driven methods to complement and improve physical understanding. In particular, Alfvén eigenmodes are a class of ubiquitous mixed kinetic and MHD instabilities that are important to identify and control because they can lead to loss of confinement and potential damage to the walls of a plasma device. In the present work, we use reservoir computing networks to classify Alfvén eigenmodes in a large labeled database of DIII-D discharges, covering a broad range of operational parameter space. However, despite the large parameter space, we show excellent classification and prediction performance, with an average hit rate of 91% and false alarm ratio of 7%, indicating promise for future implementation with additional diagnostic data and consolidation into a real-time control strategy.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2024

Fourier-MIONet: Fourier-enhanced multiple-input neural operators for multiphase modeling of geological carbon sequestration

Geologic carbon sequestration (GCS) is a safety-critical technology that aims to reduce the amount of carbon dioxide in the atmosphere, which also places high demands on reliability. Multiphase flow in porous media is essential to understand CO 2 migration and pressure fields in the subsurface associated with GCS. However, numerical simulation for such problems in 4D is computationally challenging and expensive, due to the multiphysics and multiscale nature of the highly nonlinear governing partial differential equations (PDEs). It prevents us from considering multiple subsurface scenarios and conducting real-time optimization. Here, we develop a Fourier-enhanced multiple-input neural operator (Fourier-MIONet) to learn the solution operator of the problem of multiphase flow in porous media. Fourier-MIONet utilizes the recently developed framework of the multiple-input deep neural operators (MIONet) and incorporates the Fourier neural operator (FNO) in the network architecture. Once Fourier-MIONet is trained, it can predict the evolution of saturation and pressure of the multiphase flow under various reservoir conditions, such as permeability and porosity heterogeneity, anisotropy, injection configurations, and multiphase flow properties. Compared to the enhanced FNO (U-FNO), the proposed Fourier-MIONet has 90% fewer unknown parameters, and it can be trained in significantly less time (about 3.5 times faster) with much lower CPU memory (<15%) and GPU memory (<35%) requirements, to achieve similar prediction accuracy. In addition to the lower computational cost, Fourier-MIONet can be trained with only 6 snapshots of time to predict the PDE solutions for 30 years. Furthermore, we observed that Fourier-MIONet can maintain good accuracy when predicting out-of-distribution (OOD) data. The excellent generalizability of Fourier-MIONet is enabled by its adherence to the physical principle that the solution to a PDE is continuous over time. Furthermore, the developed Fourier-MIONet makes it possible to solve the long-time evolution of geological carbon sequestration in a large-scale three-dimensional space accurately and efficiently.

97 MATHEMATICS AND COMPUTING↗