Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “network acceleration”

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 469 records · Page 26
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Imaging supermoiré relaxation in helical trilayer graphene

In twisted van der Waals materials, local atomic relaxation can alter the underlying electronic structure. Characterizing lattice reconstruction and its susceptibility to strain is essential for understanding emergent electronic states, especially in multilayers in which interference between moiré lattices yields larger supermoiré patterns whose energy is highly sensitive to local stacking. Here, in this study, we image spatial modulations in the electronic character of helical trilayer graphene, which indicate relaxation into a superstructure of large domains with uniform moiré periodicity. We show that the supermoiré domain size is increased by strain and can be altered in the same device while preserving the local properties within each domain. Finally, we observe a higher conductance at the domain boundaries, consistent with predictions that they host counterpropagating edge modes. Our work provides a real-space visualization of moiré-periodic domains, reveals two independently tunable length scales and demonstrates strain engineering as a route towards designing correlated topological networks at the supermoiré scale.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Variational neural network approach to QFT in the field basis

We present a variational neural network approach for solving quantum field theories in the field basis, focusing on the free Klein-Gordon model formulated in momentum space. While recent studies have explored neural-network-based variational methods for scalar field theory in position space, a systematic benchmark of the analytically solvable Klein-Gordon ground state—particularly in the momentum-space field basis—has been lacking. In this work, we represent the ground-state wavefunctional as a neural network defined on a discretized set of field configurations and train it by minimizing the Hamiltonian expectation value. This framework enables direct comparison to exact analytic results for a range of key observables, including the ground-state energy, two-point correlators, expectation value of the field, and the structure of the learned wavefunctional itself. Our results provide quantitative diagnostics of accuracy and establish a validated foundation for extending neural-network wavefunctional methods to interacting field theories and position-space formulations.

Klein-Gordon model↗
DOE OSTI2022

Deep Convolutional Neural Networks Exploit High-Spatial- and -Temporal-Resolution Aerial Imagery to Phenotype Key Traits in Miscanthus

Miscanthus is one of the most promising perennial crops for bioenergy production, with high yield potential and a low environmental footprint. The increasing interest in this crop requires accelerated selection and the development of new screening techniques. New analytical methods that are more accurate and less labor-intensive are needed to better characterize the effects of genetics and the environment on key traits under field conditions. We used persistent multispectral and photogrammetric UAV time-series imagery collected 10 times over the season, together with ground-truth data for thousands of Miscanthus genotypes, to determine the flowering time, culm length, and biomass yield traits. We compared the performance of convolutional neural network (CNN) architectures that used image data from single dates (2D-spatial) versus the integration of multiple dates by 3D-spatiotemporal architectures. The ability of UAV-based remote sensing to rapidly and non-destructively assess large-scale genetic variation in flowering time, height, and biomass production was improved through the use of 3D-spatiotemporal CNN architectures versus 2D-spatial CNN architectures. The performance gains of the best 3D-spatiotemporal analyses compared to the best 2D-spatial architectures manifested in up to 23% improvements in R2, 17% reductions in RMSE, and 20% reductions in MAE. The integration of photogrammetric and spectral features with 3D architectures was crucial to the improved assessment of all traits. In conclusion, our findings demonstrate that the integration of high-spatiotemporal-resolution UAV imagery with 3D-CNNs enables more accurate monitoring of the dynamics of key phenological and yield-related crop traits. This is especially valuable in highly productive, perennial grass crops such as Miscanthus, where in-field phenotyping is especially challenging and traditionally limits the rate of crop improvement through breeding.

47 OTHER INSTRUMENTATION↗
DOE OSTI2025

Mastering the Copolymerization Behavior of Ethyl Cyanoacrylate as Gel Polymer Electrolyte for Lithium‐metal Battery Application

Polymers with strong electron-withdrawing groups (e.g., cyano-containing polymers) are attractive for a wide range of applications due to their high dielectric constant and outstanding electrochemical stability. However, the polymerization of such monomers is difficult to control with trace of water affording instant reactions, and copolymerization with other monomers without using strong acid is even more challenging. The present study demonstrates a facile approach enabling efficient and controllable copolymerization of ethyl cyanoacrylate (ECA) without adding undesired additives, achieving mechanically robust and high ion-conduction gel polymer electrolyte (GPE) for safe and long cycle-life lithium-metal batteries (LMBs). The incorporated dual-lithium salts, i.e., lithium difluoro(oxalato)borate (LiDFOB) and lithium bis(trifluoromethanesulphonyl)imide (LiTFSI) not only facilitate radical polymerization of ECA monomers by suppressing their anionic polymerization, but also promote the formation of high-ionic conducting GPE. The incorporated methyl methacrylate (MMA) monomer accelerates the radical polymerization of ECA (confirmed by DFT calculations), achieving controlled copolymerization of ECA-based copolymers. Here, the mechanically robust polymer network made by the ECA copolymer enables LMBs with both LFP cathodes and high-voltage LCO cathodes (4.5 V) operatable at different temperatures with ultra-long cycle life at 1 C (capacity retention of 81.1 % and 83.8 %, respectively, over 1000 cycles).

Min, Weixing [Nankai University, Tianjin (China)]↗
DOE OSTI2020

Leveraging inter-firm influence in the diffusion of energy efficiency technologies: An agent-based model

Energy efficiency technologies (EETs) are crucial for saving energy and reducing carbon dioxide emissions. However, the diffusion of EETs in small and medium-sized enterprises is rather slow. Literature shows the interactions between innovation adopters and potential adopters have significant impacts on innovation diffusion. Enterprises lack the motivation to share information, and EETs usually lack observability, which suppress the inter-firm influence. Thus, an information platform, together with proper policies encouraging or forcing enterprises to disclose EET-related information, should help harness inter-firm influence to accelerate EETs' diffusion. To explore whether and how such an information platform affects EETs' diffusion in small and medium-sized enterprises, this report builds an agent-based model to mimic EET diffusion processes. Based on a series of controlled numerical experiments, some counter-intuitive phenomena are discovered and explained. The results show that the information platform is a double-edged sword that notably accelerates EETs' diffusion by approximately 47% but may also boost negative information to diffuse even faster and delay massive adoption of EETs. Increasing network density and the intensity of inter-firm influence are effective to speed EET diffusion, but their impacts diminish drastically after reaching some critical values (0.05 and 0.15 respectively) and eventually harm the stability of the system. Ultimately, the findings implicate that EET suppliers should carefully launch their promising but immature products; policies that can reduce the perceived risk by enterprises and the effort to maintain an informative rather than judgmental information platform can prominently mitigate the negative side effects brought by high fluidity of information.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2024

Active learning of ternary alloy structures and energies

Abstract Machine learning models with uncertainty quantification have recently emerged as attractive tools to accelerate the navigation of catalyst design spaces in a data-efficient manner. Here, we combine active learning with a dropout graph convolutional network (dGCN) as a surrogate model to explore the complex materials space of high-entropy alloys (HEAs). We train the dGCN on the formation energies of disordered binary alloy structures in the Pd-Pt-Sn ternary alloy system and improve predictions on ternary structures by performing reduced optimization of the formation free energy, the target property that determines HEA stability, over ensembles of ternary structures constructed based on two coordinate systems: (a) a physics-informed ternary composition space, and (b) data-driven coordinates discovered by the Diffusion Maps manifold learning scheme. Both reduced optimization techniques improve predictions of the formation free energy in the ternary alloy space with a significantly reduced number of DFT calculations compared to a high-fidelity model. The physics-based scheme converges to the target property in a manner akin to a depth-first strategy, whereas the data-driven scheme appears more akin to a breadth-first approach. Both sampling schemes, coupled with our acquisition function, successfully exploit a database of DFT-calculated binary alloy structures and energies, augmented with a relatively small number of ternary alloy calculations, to identify stable ternary HEA compositions and structures. This generalized framework can be extended to incorporate more complex bulk and surface structural motifs, and the results demonstrate that significant dimensionality reduction is possible in thermodynamic sampling problems when suitable active learning schemes are employed.

Chemistry↗
DOE OSTI2021

Advances in CdZnTeSe for Radiation Detector Applications

Detection of X- and gamma-rays is essential to a wide range of applications from medical imaging to high energy physics, astronomy, and homeland security. Cadmium zinc telluride (CZT) is the most widely used material for room-temperature detector applications and has been fulfilling the requirements for growing detection demands over the last three decades. However, CZT still suffers from the presence of a high density of performance-limiting defects, such as sub-grain boundary networks and Te inclusions. Cadmium zinc telluride selenide (CZTS) is an emerging material with compelling properties that mitigate some of the long-standing issues seen in CZT. This new quaternary is free from sub-grain boundary networks and possesses very few Te inclusions. In addition, the material offers a high degree of compositional homogeneity. The advancement of CZTS has accelerated through investigations of the material properties and virtual Frisch-grid (VFG) detector performance. The excellent material quality with highly reduced performance-limiting defects elevates the importance of CZTS as a potential replacement to CZT at a substantially lower cost.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2022

An MILP-Based Distributed Energy Management for Coordination of Networked Microgrids

An MILP-based distributed energy management for the coordination of networked microgrids is proposed in this paper. Multiple microgrids and the utility grid are coordinated through iteratively adjusted price signals. Based on the price signals received, the microgrid controllers (MCs) and distribution management system (DMS) update their schedules separately. Then, the price signals are updated according to the generation–load mismatch and distributed to MCs and DMS for the next iteration. The iteration continues until the generation–load mismatch is small enough, i.e., the generation and load are balanced under agreed price signals. Through the proposed distributed energy management, various microgrids and the utility grid with different economic, resilient, emission and socio-economic objectives are coordinated with generation–load balance guaranteed and the microgrid customers’ privacy preserved. In particular, a piecewise linearization technique is employed to approximate the augmented Lagrange term in the alternating direction method of multipliers (ADMM) algorithm. Thus, the subproblems are transformed into mixed integer linear programming (MILP) problems and efficiently solved by open-source MILP solvers, which would accelerate the adoption and deployment of microgrids and promote clean energy. The proposed MILP-based distributed energy management is demonstrated through various case studies on a networked microgrids test system with three microgrids.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Machine Learning-Driven Conservative-to-Primitive Conversion in Hybrid Piecewise Polytropic and Tabulated Equations of State

We present a novel machine learning (ML)-based method to accelerate conservative-to-primitive inversion, focusing on hybrid piecewise polytropic and tabulated equations of state. Traditional root-finding techniques are computationally expensive, particularly for large-scale relativistic hydrodynamics simulations. To address this, we employ feedforward neural networks (NNC2PS and NNC2PL), trained in PyTorch (2.0+) and optimized for GPU inference using NVIDIA TensorRT (8.4.1), achieving significant speedups with minimal accuracy loss. The NNC2PS model achieves 𝐿 1 and 𝐿 ∞ errors of 4.54 × 10 −7 and 3.44 × 10−6, respectively, while the NNC2PL model exhibits even lower error values. TensorRT optimization with mixed-precision deployment substantially accelerates performance compared to traditional root-finding methods. Specifically, the mixed-precision TensorRT engine for NNC2PS achieves inference speeds approximately 400 times faster than a traditional single-threaded CPU implementation for a dataset size of 1,000,000 points. Ideal parallelization across an entire compute node in the Delta supercomputer (dual AMD 64-core 2.45 GHz Milan processors and 8 NVIDIA A100 GPUs with 40 GB HBM2 RAM and NVLink) predicts a 25-fold speedup for TensorRT over an optimally parallelized numerical method when processing 8 million data points. Moreover, the ML method exhibits sub-linear scaling with increasing dataset sizes. We release the scientific software developed, enabling further validation and extension of our findings. By exploiting the underlying symmetries within the equation of state, these findings highlight the potential of ML, combined with GPU optimization and model quantization, to accelerate conservative-to-primitive inversion in relativistic hydrodynamics simulations.

conservative-to-primitive conversion↗
DOE OSTI2026

Using Explainable Artificial Intelligence to Predict Perovskite Solar Cell Electrical Metastability from Operando Photoluminescence Images in Accelerated Stress Testing

Metal halide perovskite (MHP) solar cells exhibit a metastable response to bias governed by coupled ionic–electronic processes, complicating the conventional reciprocity relation between luminescence intensity and device open-circuit voltage (V oc ). This limits the use of luminescence as a diagnostic for device screening or accelerated stress testing, motivating new approaches that can interpret photoluminescence (PL) signals under nonequilibrium conditions. From the artificial intelligence perspective, we develop an explainable deep learning framework that integrates convolutional neural networks (CNN), long short-term memory (LSTM) layers, and an attention mechanism to learn spatiotemporal features from operando photoluminescence PL image sequences. The model achieves a mean absolute error of ±0.027 V in predicting open-circuit voltage transients and reduces extreme-tail errors by up to 78% compared to physics-based reciprocity calculations. Gradient-weighted Class Activation Mapping (Grad-CAM) provides interpretability by highlighting physically meaningful regions such as electrode edges and emergent defect features. From the engineering application perspective, this framework enables accurate, contactless prediction of device V oc and identification of degradation-relevant features during accelerated aging of perovskite solar cells. This approach demonstrates how explainable AI can enhance operando diagnostics and reliability analysis in photovoltaic devices under nonequilibrium conditions.

14 SOLAR ENERGY↗
DOE OSTI2023

Prompt Photofission Neutron Detection in Depleted Uranium

The detection of prompt photofission neutrons during active interrogation is a strong indication of the presence of special nuclear materials. However, the high-energy photons used for interrogation create a very challenging radiation environment for the detection of prompt fission signatures. These challenges include detector saturation and pulse pile-up. Additionally, there is an elevated neutron background that further challenges the detection of prompt fission neutrons. This background is produced because of (γ, Xn) photonuclear reactions in the surrounding high-Z materials. Here, we demonstrate the detection of prompt photofission neutrons in these challenging environments. Depleted uranium (DU) and lead targets are interrogated with bremsstrahlung photons produced by a 9-MV electron linear accelerator. Fast neutrons are detected with trans-stilbene organic detectors, and scintillation pulses are analyzed using a previously developed and demonstrated artificial neural network system. We observe a 5 times higher photoneutron count rate when the lead target is replaced with the DU target. Additionally, we observe a difference in the photoneutron light-output distributions of lead and DU. Here, this difference in the measured distributions is due to the difference in the photoneutron-energy spectra; DU photoneutrons are emitted with (γ, n) and watt-energy spectra, whereas lead photoneutrons are emitted with only the (γ, n) spectrum.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2024

Defect diffusion graph neural networks (d2gnn)

SAND2025-01004O Defect Diffusion Graph Neural Networks (d2gnn) is a software tool that assists in the discovery of new materials for high-temperature, clean-energy applications. It uses advanced graph neural networks to model the relationship between material structures and their defect properties. The application helps predict how materials will behave under different conditions and accelerates the development of innovative materials. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.

Witman, Matthew [Sandia National Lab. (SNL-CA), Li↗
DOE OSTI2021

Multi-Sectoral Urban Interactions: Fundamental Science Needs to Inform Pathways to More Resilient Communities in a Changing Climate Multi-Sectoral Urban Interactions: Fundamental Science Needs to Inform Pathways to More Resilient Communities in a Changing Climate

Urban areas and the supply networks that support their resource use are inherently multisectoral systems composed of infrastructural, environmental, and socio-institutional components. These systems are vulnerable to accelerating and interacting stresses from climate change, population growth, resource scarcity, and land-use pressure at the same time as they have a major influence on regional and global systems. For instance, a majority of the world’s greenhouse gas emissions, food consumption, and economic activity can be attributed to urban areas. Urban areas are highly heterogenous, both across and within cities in terms of their socio-demographic, environmental, and infrastructural characteristics. This heterogeneity shapes how urban systems interact and co-evolve and contributes to different economic, environmental, and health outcomes for communities within urban areas. Urban heterogeneity also generates differential vulnerabilities to stressors and differential capacity for adapting to change. The evolution of urban space is thus critical in shaping how human societies respond to global change as they seek to improve resilience to stressors, support prosperous and equitable communities, and use natural resources in a sustainable manner. Developing fundamental scientific understanding of urban heterogeneity and system interactions across sectors and scales is critical for mapping the resilience, sustainability, and equity implications of alternative future pathways. On July 2021 the MSD Urban Systems Working Group organized this workshop to provide a venue for coordination and identification of shared objectives, research themes, and major knowledge gaps, as well as developing a shared strategy for addressing these gaps. This report summarizes the outcomes of this workshop.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2022

Deep Generative Models for Materials Discovery and Machine Learning-Accelerated Innovation

Machine learning and artificial intelligence (AI/ML) methods are beginning to have significant impact in chemistry and condensed matter physics. For example, deep learning methods have demonstrated new capabilities for high-throughput virtual screening, and global optimization approaches for inverse design of materials. Recently, a relatively new branch of AI/ML, deep generative models (GMs), provide additional promise as they encode material structure and/or properties into a latent space, and through exploration and manipulation of the latent space can generate new materials. These approaches learn representations of a material structure and its corresponding chemistry or physics to accelerate materials discovery, which differs from traditional AI/ML methods that use statistical and combinatorial screening of existing materials via distinct structure-property relationships. However, application of GMs to inorganic materials has been notably harder than organic molecules because inorganic structure is often more complex to encode. In this work we review recent innovations that have enabled GMs to accelerate inorganic materials discovery. We focus on different representations of material structure, their impact on inverse design strategies using variational autoencoders or generative adversarial networks, and highlight the potential of these approaches for discovering materials with targeted properties needed for technological innovation.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Distance preserving machine learning for uncertainty aware accelerator capacitance predictions

Abstract Accurate uncertainty estimations are essential for producing reliable machine learning models, especially in safety-critical applications such as accelerator systems. Gaussian process models are generally regarded as the gold standard for this task; however, they can struggle with large, high-dimensional datasets. Combining deep neural networks with Gaussian process approximation techniques has shown promising results, but dimensionality reduction through standard deep neural network layers is not guaranteed to maintain the distance information necessary for Gaussian process models. We build on previous work by comparing the use of the singular value decomposition against a spectral-normalized dense layer as a feature extractor for a deep neural Gaussian process approximation model and apply it to a capacitance prediction problem for the High Voltage Converter Modulators in the Oak Ridge Spallation Neutron Source. Our model shows improved distance preservation and predicts in-distribution capacitance values with less than 1% error.

43 PARTICLE ACCELERATORS↗
DOE OSTI2022

A systematic method for selecting molecular descriptors as features when training models for predicting physiochemical properties

Machine learning has proven to be a powerful tool for accelerating biofuel development. Although numerous models are available to predict a range of properties using chemical descriptors, there is a trade-off between interpretability and performance. Neural networks provide predictive models with high accuracy at the expense of some interpretability, while simpler models such as linear regression often lack in accuracy. In addition to model architecture, feature selection is also critical for developing interpretable and accurate predictive models. We present a method for systematically selecting molecular descriptor features and developing interpretable machine learning models without sacrificing accuracy. Our method simplifies the process of selecting features by reducing feature multicollinearity and enables discoveries of new relationships between global properties and molecular descriptors. To demonstrate our approach, we developed models for predicting melting point, boiling point, flash point, yield sooting index, and net heat of combustion with the help of the Tree-based Pipeline Optimization Tool (TPOT). For training, we used publicly available experimental data for up to 8351 molecules. Our models accurately predict various molecular properties for organic molecules (mean absolute percent error (MAPE) ranges from 3.3% to 10.5%) and provide a set of features that are well-correlated to the property. This method enables researchers to explore sets of features that significantly contribute to the prediction of the property, offering new scientific insights. To help accelerate early stage biofuel research and development, we also integrated the data and models into a open-source, interactive web tool.

09 BIOMASS FUELS↗
DOE OSTI2020

Amino acid interacting network in the receptor-binding domain of SARS-CoV-2 spike protein

The relation between amino acid (AA) sequence and biologically active conformation controls the process of polypeptide chains folding into three-dimensional (3d) protein structures. The recent achievements in the resolution achieved in cryo-electron microscopy coupled with improvements in computational methodologies have accelerated the analysis of structures and properties of proteins. However, the detailed interaction between AAs has not been fully elucidated. Herein, we present a de novo method to evaluate inter-amino acid interactions based on the concept of accurately evaluating the amino acid bond pairs (AABP). The results obtained enabled the identification of complex 3d long-range interconnected AA interacting network in proteins. The method is applied to the receptor binding domain (RBD) of the SARS-CoV-2 spike protein. We show that although nearest-neighbor AAs in the primary sequence have large AABP, other nonlocal AAs make substantial contribution to AABP with significant participation of both covalent and hydrogen bonding. Detailed analysis of AABP in RBD reveals the pivotal role they play in sequence conservation with profound implications on residue mutations and for therapeutic drug design. This approach could be easily applied to many other proteins of biomedical interest in life sciences.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Efficient Mixed-Precision Matrix Factorization of the Inverse Overlap Matrix in Electronic Structure Calculations with AI-Hardware and GPUs

In recent years, a new kind of accelerated hardware has gained popularity in the artificial intelligence (AI) community which enables extremely high-performance tensor contractions in reduced precision for deep neural network calculations. In this article, we exploit Nvidia Tensor cores, a prototypical example of such AI-hardware, to develop a mixed precision approach for computing a dense matrix factorization of the inverse overlap matrix in electronic structure theory, S –1 . This factorization of S –1 , written as ZZT = S –1 , is used to transform the general matrix eigenvalue problem into a standard matrix eigenvalue problem. Here we present a mixed precision iterative refinement algorithm where Z is given recursively using matrix–matrix multiplications and can be computed with high performance on Tensor cores. To understand the performance and accuracy of Tensor cores, comparisons are made to GPU-only implementations in single and double precision. Additionally, we propose a nonparametric stopping criteria which is robust in the face of lower precision floating point operations. The algorithm is particularly useful when we have a good initial guess to Z, for example, from previous time steps in quantum-mechanical molecular dynamics simulations or from a previous iteration in a geometry optimization.

36 MATERIALS SCIENCE↗