Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “learning efficiency”

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 1,207 records · Page 67

Performance Analysis of an Optimization Algorithm for Metamaterial Design on the Integrated High-Performance Computing and Quantum Systems

Optimizing metamaterials with complex geometries is a big challenge. Although an active learning algorithm, combining machine learning (ML), quantum computing, and optical simulation, has emerged as an efficient optimization tool, it still faces difficulties in optimizing complex structures that have potentially high performance. In this work, we comprehensively analyze the performance of an optimization algorithm for metamaterial design on the integrated HPC and quantum systems. We demonstrate significant time advantages through message-passing interface (MPI) parallelization on the high-performance computing (HPC) system showing approximately 54% faster ML tasks and 67 times faster optical simulation against serial workloads. Furthermore, we analyze the performance of a quantum algorithm designed for optimization, which runs with various quantum simulators on a local computer or HPC-quantum system. Results showcase ~24 times speedup when executing the optimization algorithm on the HPC-quantum hybrid system. This study paves a way to optimize complex metamaterials using the integrated HPC-quantum system.

Kim, Seongmin↗

Track Seeding and Labelling with Embedded-space Graph Neural Networks

To address the unprecedented scale of HL-LHC data, the Exa.TrkX project is investigating a variety of machine learning approaches to particle track reconstruction. The most promising of these solutions, graph neural networks (GNN), process the event as a graph that connects track measurements (detector hits corresponding to nodes) with candidate line segments between the hits (corresponding to edges). Detector information can be associated with nodes and edges, enabling a GNN to propagate the embedded parameters around the graph and predict node-, edge- and graph-level observables. Previously, message-passing GNNs have shown success in predicting doublet likelihood, and we here report updates on the state-of-the-art architectures for this task. In addition, the Exa.TrkX project has investigated innovations in both graph construction, and embedded representations, in an effort to achieve fully learned end-to-end track finding. Hence, we present a suite of extensions to the original model, with encouraging results for hitgraph classification. In addition, we explore increased performance by constructing graphs from learned representations which contain non-linear metric structure, allowing for efficient clustering and neighborhood queries of data points. We demonstrate how this framework fits in with both traditional clustering pipelines, and GNN approaches. The embedded graphs feed into high-accuracy doublet and triplet classifiers, or can be used as an end-to-end track classifier by clustering in an embedded space. A set of post-processing methods improve performance with knowledge of the detector physics. Finally, we present numerical results on the TrackML particle tracking challenge dataset, where our framework shows favorable results in both seeding and track finding.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

A Machine Learning-Assisted Framework to Control Thermally Anisotropic Building Envelopes in Residential Buildings

To curb the energy consumption of buildings and their related CO2 emissions, Oak Ridge National Laboratory (ORNL) has developed the thermally anisotropic building envelope (TABE) —a multi-layer design comprising insulation materials and metal foils connected to thermal loops. In this study, a machine learning-assisted framework was developed to control the TABE in residential buildings to reduce the computation load for future optimal rule-based control and application. First, a 2D finite element model was established in COMSOL to calculate the hourly heat flux through exterior walls installed with the TABE. Then, TABE wall heat fluxes were simulated for various given indoor and outdoor boundary conditions, as well as thermal loops fluid temperatures and flow rates. Since the finite element simulations are computationally expensive, an artificial neural network (ANN) was then trained to use as a proxy of the finite element (COMSOL) modeling. Finally, the trained ANN model was coupled with the EnergyPlus model to predict the energy consumption of a US Department of Energy prototype single-family house installed with the TABE. An optimal simple rule-based control was determined from predefined rules for a case study. The results demonstrate that the developed machine learning–assisted framework can reduce 99.9% of the computation time while efficiently managing residential building energy for installed TABE walls.

Shen, Zhenglai↗

A Dynamic Hierarchical Attention Framework for Multimodal Malware Detection

The increasing use of Android in the worldwide mobile ecosystem has come along with a significant increase in advanced malware, highlighting the critical necessity for efficient, scalable, and adaptable detection systems. Despite recent advancements in machine learning improving malware detection, the majority of current solutions are limited to one, two, or three data modalities, hence neglecting the comprehensive behavioral spectrum of contemporary multi-vector threats. This thesis presents the first comprehensive multimodal framework for Android malware detection, which combines textual, time-series (temporal), graph-based (structural), and visual information using an innovative hierarchical attention mechanism and Dynamic Fusion Controller (DFC). Our methodology consistently classifies and processes modalities as either sequential or structural, facilitating content-adaptive weighting and resilient cross-modal representation learning. We advance the implementation of cutting-edge time series techniques, such as MiniRocket, for malware detection, hence creating new opportunities for temporal analysis in cybersecurity. Comprehensive experimental assessment shows that our framework performs exceptionally well, with 99.46% classification accuracy and 97.15% detection accuracy, significantly outperforming existing approaches through effective multimodal integration and hierarchical attention mechanisms.

Nazmin, Tamanna↗

Trustworthiness and Trust: Identifying Factors that Drive Successful Human-AI Interaction in Nuclear Power Plant Applications

Emerging technologies such as artificial intelligence (AI) and machine learning (ML) are rapidly evolving and considered a promising tool for efficient and continued safe operations of the U.S. nuclear power plants (NPPs). Emerging AI techniques like large language models (LLMs) are one such technology that may support personnel at existing NPPs perform work more efficiently. For example, operators may query the current operational status of a power plant via a chat interface leveraging LLMs to access plant-related information in an interactive manner rather than manually collecting various sensor data for tasks such as surveillances or completing work orders. This is a fundamental shift in the way operators currently perform their tasks today. The literature of human-automation interaction indicates that trust is a crucial factor that drives successful interaction between a human operator and an automated system, like an AI-infused NPP application. This work presents the results of a literature review on key factors that relate to trust in AI/LLM technologies for NPP applications. The relevant literature of human factors and cognitive engineering has identified various factors related to trust including trustworthiness, performance characteristics, operator skill and perceived risk. This preliminary literature review will guide development and evaluation of models involving the identified factors influencing trust in AI and develop a framework for human-centered design for interface between humans and AI. By addressing trust, this work supports developing a technical basis for designing key characteristics of AI/LLM to support calibrated trust, which will ultimately support wide-scale adoption of AI/LLM technologies, as well as ensure safe, effective, and reliable use.

99 - GENERAL AND MISCELLANEOUS↗

NEPTUNIUM OXIDE PROCESSING

The Savannah River Site's HB-Line Facility completed a campaign in which fifty nine cans of neptunium oxide were produced and shipped to the Idaho National Laboratory in the 9975 shipping container. The neptunium campaign was divided into two parts: Part 1 which consisted of oxide made from H-Canyon neptunium solution which did not require any processing prior to conversion into an oxide, and Part 2 which consisted of oxide made from additional H-Canyon neptunium solutions which required processing to purify the solution prior to conversion into an oxide. The neptunium was received as a nitrate solution and converted to oxide through ion-exchange column extraction, precipitation, and calcination. Numerous processing challenges were encountered in order make a final neptunium oxide product that could be shipped in a 9975 shipping container. Among the challenges overcome was the issue of scale: translating lab scale production into full facility production. The balance between processing efficiency and product quality assurance was addressed during this campaign. Lessons learned from these challenges are applicable to other processing projects.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

A Modular and Transferable Reinforcement Learning Framework for the Fleet Rebalancing Problem

Mobility on demand (MoD) systems show great promise in realizing flexible and efficient urban transportation. However, significant technical challenges arise from operational decision making associated with MoD vehicle dispatch and fleet rebalancing. For this reason, operators tend to employ simplified algorithms that have been demonstrated to work well in a particular setting. To help bridge the gap between novel and existing methods, we propose a modular framework for fleet rebalancing based on model-free reinforcement learning (RL) that can leverage an existing dispatch method to minimize system cost. In particular, by treating dispatch as part of the environment dynamics, a centralized agent can learn to intermittently direct the dispatcher to reposition free vehicles and mitigate against fleet imbalance. We formulate RL state and action spaces as distributions over a grid partitioning of the operating area, making the framework scalable and avoiding the complexities associated with multiagent RL. Numerical experiments, using real-world trip and network data, demonstrate that RL reduces waiting time by 28% to 38% for the same-day evaluation, 17% to 44% for cross-day evaluation, and 22% to 25% for cross-season evaluation compared with no rebalancing scenarios. This approach has several distinct advantages over baseline methods including: improved system cost; high degree of adaptability to the selected dispatch method; and the ability to perform scale-invariant transfer learning between problem instances with similar vehicle and request distributions.

33 ADVANCED PROPULSION SYSTEMS↗

Introductory lecture: Systems materials engineering approach for solar-to-chemical conversion

Solar-to-chemical (STC) production using a fully integrated system is an attractive goal, but to-date there has yet to be a system that can demonstrate the required efficiency or durability, or could be manufactured at a reasonable cost. One can learn a great deal from the natural photosynthesis where the conversion of carbon dioxide and water to carbohydrates is routinely carried out at a highly coordinated system level. Here, we discuss the several key features worth mentioning in these systems: spatial and directional arrangement of the light-harvesting components; charge separation and transport; as well as the desired chemical conversion at catalytic sites in compartmentalized spaces. In order to design an efficient artificial photosynthetic materials system, at the level of the individual components better catalysts need to be developed, new light-absorbing semiconductor materials will need to be discovered, architectures will need to be designed for effective capture and conversion of sunlight, and more importantly, processes need to be developed for the efficient coupling and integration of the components into a complete artificial photosynthetic system.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Exciting DeePMD: Learning excited-state energies, forces, and non-adiabatic couplings

We extend the DeePMD neural network architecture to predict electronic structure properties necessary to perform non-adiabatic dynamics simulations. While learning the excited state energies and forces follows a straightforward extension of the DeePMD approach for ground-state energies and forces, how to learn the map between the non-adiabatic coupling vectors (NACV) and the local chemical environment descriptors of DeePMD is less trivial. Most implementations of machine-learning-based non-adiabatic dynamics inherently approximate the NACVs, with an underlying assumption that the energy-difference-scaled NACVs are conservative fields. We overcome this approximation, implementing the method recently introduced by Richardson [J. Chem. Phys. 158, 011102 (2023)], which learns the symmetric dyad of the energy-difference-scaled NACV. Furthermore, the efficiency and accuracy of our neural network architecture are demonstrated through the example of the methaniminium cation CH 2 NH 2 + .

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Machine Learning Applied to Star–Galaxy–QSO Classification and Stellar Effective Temperature Regression

In modern astrophysics, machine learning has increasingly gained popularity with its incredibly powerful ability to make predictions or calculated suggestions for large amounts of data. We describe an application of the supervised machine-learning algorithm, random forests (RF), to the star/galaxy/QSO classification and the stellar effective temperature regression based on the combination of Large Sky Area Multi-Object Fiber Spectroscopic Telescope and Sloan Digital Sky Survey spectroscopic data. This combination enables us to obtain reliable predictions with one of the largest training samples ever used. The training samples are built with a nine-color data set of about three million objects for the classification and a seven-color data set of over one million stars for the regression. The performance of the classification and regression is examined with validation and blind tests on the objects in the RAdial Velocity Extension, 6dFGS, UV-bright Quasar Survey and Apache Point Observatory Galactic Evolution Experiment surveys. We demonstrate that RF is an effective algorithm, with classification accuracies higher than 99% for stars and galaxies, and higher than 94% for QSOs. These accuracies are higher than machine-learning results in former studies. The total standard deviations of the regression are smaller than 200 K, which is similar to those of some spectrum-based methods. The machine-learning algorithm with the broad-band photometry provides us with a more efficient approach for dealing with massive amounts of astrophysical data than do traditional color cuts and spectral energy distribution fits.

79 ASTRONOMY AND ASTROPHYSICS↗

Machine Learning-Based Identification of the Interface Regions for Coupling Local and Nonlocal Models

Local-nonlocal coupling approaches provide a means to combine the computational efficiency of local models and the accuracy of nonlocal models. However, the coupling process can be challenging, requiring expertise to identify the interface between local and nonlocal regions. Here, this study introduces a machine learning-based approach to automatically detect the regions in which the local and nonlocal models should be used. The method uses loading functions evaluated at grid points to decide the model selection at those points. Training of the networks is based on datasets provided by classes of loading functions for which reference coupling configurations are computed using accurate coupled solutions, where accuracy is measured in terms of the relative error between the solution to the coupling approach and the solution to the nonlocal model. We study two approaches that vary in data structure. The first, the full-domain input data approach, uses the entire load vector and outputs a complete label vector, performing a global classification. The second, a window-based approach, processes loads into windows and addresses the problem as a node-wise classification where each window's central point is classified individually. The classification problems are solved via deep learning algorithms based on convolutional neural networks. The performance of these approaches is studied on one-dimensional numerical examples using F1-scores and accuracy metrics. Notably, the windowing approach achieves an accuracy of 0.96 and an F1-score of 0.97, highlighting its potential to automate coupling processes effectively and enhance computational efficiency in material science applications.

97 MATHEMATICS AND COMPUTING↗

In situ compression artifact removal in scientific data using deep transfer learning and experience replay

The massive amount of data produced during simulation on high-performance computers has grown exponentially over the past decade, exacerbating the need for streaming compression and decompression methods for efficient storage and transfer of this data---key to realizing the full potential of large-scale computational science. Lossy compression approaches such as JPEG when applied to scientific simulation data realized as a stream of images can achieve good compression rates but at the cost of introducing compression artifacts and loss of information. This paper develops a unified framework for in situ compression artifact removal in which the fully convolutional neural network architectures are combined with scalable training, transfer learning, and experience replay to achieve superior accuracy and efficiency while significantly decreasing the storage footprint as compared with the traditional optimization-based approaches. We demonstrate the proposed approach and compare it with compressed sensing postprocessing and other baseline deep learning models using climate simulations and nuclear reactor simulations, both of which are driven by hyperbolic partial differential equations. Our approach when applied to remove the compression artifacts on the JPEG-compressed nuclear reactor simulation data (using a transfer-trained model that was pretrained on the climate simulation data and updated incrementally as the nuclear reactor simulation progressed), achieved a significant improvement---mean peak signal-to-noise ratio of 42.438 as compared with 27.725 obtained with the compressed sensing approach.

97 MATHEMATICS AND COMPUTING↗

Polyalkenamers as Drop-In Additives for Ring-Opening Metathesis Polymerization: A Promising Upcycling Paradigm

Here we report a distinct strategy to upcycle waste polyalkenamers such as polybutadiene into new, performance-advantaged materials by using them as drop-in additives for ring-opening metathesis polymerization (ROMP). The polyalkenamers serve as competent chain-transfer agents in ROMPs of common classes of cyclic olefin monomers, facilitating good molecular weight control, allowing low Ru catalyst loadings, and enabling efficient incorporation of the polyalkenamer into the synthesized polymeric material. We successfully demonstrate ROMP using model polyalkenamers and translate these learnings to leverage commercial polybutadiene and acrylonitrile butadiene styrene (ABS) as chain transfer agents for ROMP copolymerizations. Critically, our strategy is shown to be highly efficient and operationally simple, quantitatively incorporating the polyalkenamer and inheriting aspects of its thermomechanical performance. Our results highlight a promising pathway for the upcycling of polyalkenamers and provide an alternative to existing deconstruction and functional upcycling strategies.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

ESM data downscaling: a comparison of super-resolution deep learning models

Abstract Climate projections at fine spatial resolutions are required to conduct accurate risk assessment for critical infrastructure and design adaptation planning. Generating these projections using advanced Earth system models (ESM) requires significant computational resources. To address this issue, various statistical downscaling techniques have been introduced to generate fine-resolution data from coarse-resolution simulations. In this study, we evaluate and compare five deep learning-based downscaling techniques, namely, super-resolution convolutional neural networks, fast super-resolution convolutional neural network ESM, efficient sub-pixel convolutional neural network, enhanced deep residual network (EDRN), and super-resolution generative adversarial network (SRGAN). These techniques are applied to a dataset generated by the Energy Exascale Earth System Model (E3SM), focusing on key surface variables such as surface temperature, shortwave heat flux, and longwave heat flux. Models are trained and validated using paired fine-resolution (0.25 $$^{\circ }$$ ∘ ) and coarse-resolution (1 $$^{\circ }$$ ∘ ) monthly data obtained from a 9-year simulation. Next, blind testing is performed using monthly data obtained from two different years outside of the training and validation set. To evaluate the efficiency of each technique, different statistical metrics are used, including mean squared error (MSE), peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and learned perceptual image patch similarity (LPIPS). The results show that EDRN outperforms other algorithms in terms of PSNR, SSIM, and MSE, but struggles to capture fine-scale features in the data. In contrast, SRGAN, a generative model that uses perceptual loss, excels in capturing fine details at boundaries and internal structures, resulting in lower LPIPS than other methods.

Pawar, Nikhil M. (ORCID:0000000211613289)↗

Prediction of Silicon Content in a Blast Furnace via Machine Learning: A Comprehensive Processing and Modeling Pipeline

Silicon content plays an important role in determining the operational efficiency of blast furnaces (BFs) and their downstream processes in integrated steelmaking; however, existing sampling methods and first-principles models are somewhat limited in their capability and flexibility. Current data-based prediction models primarily rely on a limited set of manually selected furnace parameters. Additionally, different BFs present a diverse set of operating parameters and state variables that are known to directly influence the hot metal’s silicon content, such as fuel injection, blast temperature, and raw material charge composition, among other process variables that have their own impacts. The expansiveness of the parameter set adds complexity to parameter selection and processing. This highlights the need for a comprehensive methodology to integrate and select from all relevant parameters for accurate silicon content prediction. Providing accurate silicon content predictions would enable operators to adjust furnace conditions dynamically, improving safety and reducing economic risk. To address these issues, a two-stage approach is proposed. First, a generalized data processing scheme is proposed to accommodate diverse furnace parameters. Second, a robust modeling pipeline is used to establish a machine learning (ML) model capable of predicting hot metal silicon content with reasonable accuracy. The method employed herein predicted the average Si content of the upcoming furnace cast with an accuracy of 91% among 200 target predictions for a specific furnace provisioned by the XGBoost model. This prediction is achieved using only the past shift’s operating conditions, which should be available in real time. This performance provides a strong baseline for the modeling approach with potential for further improvement through provision of real-time features.

Chemistry↗

Ground State Energy Functional with Hartree–Fock Efficiency and Chemical Accuracy

We introduce the deep post Hartree–Fock (DeePHF) method, a machine learning-based scheme for constructing accurate and transferable models for the ground-state energy of electronic structure problems. DeePHF predicts the energy difference between results of highly accurate models such as the coupled cluster method and low accuracy models such as the Hartree–Fock (HF) method, using the ground-state electronic orbitals as the input. It preserves all the symmetries of the original high accuracy model. The added computational cost is less than that of the reference HF or DFT and scales linearly with respect to system size. We examine the performance of DeePHF on organic molecular systems using publicly available data sets and obtain the state-of-art performance, particularly on large data sets.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

An efficient surrogate model of secondary electron formation and evolution

This work extends the adjoint-deep learning framework for runaway electron (RE) evolution, developed by McDevitt et al. [Phys. Plasmas 32, 042503 (2025)], to account for large-angle collisions. By incorporating large-angle collisions, the framework allows the avalanche of REs to be captured, an essential component of RE dynamics. This extension is accomplished by using a Rosenbluth–Putvinski approximation to estimate the distribution of secondary electrons generated by large-angle collisions. By evolving both the primary and multiple generations of secondary electrons, the present formulation can capture both the detailed temporal evolution of a RE population beginning from an arbitrary initial momentum space distribution, along with providing approximations to the saturated growth and decay rates of the RE population. Predictions of the adjoint-deep learning framework are verified against a traditional RE solver, with good agreement present across a broad range of parameters.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

MassiveGNN: Efficient Training via Prefetching for Massively Connected Distributed Graphs

Graph Neural Networks (GNN) are indispensable in learning from graph-structured data, yet their rising computational costs, especially on massively connected graphs, pose significant challenges in terms of execution performance. To tackle this, distributed-memory solutions such as partitioning the graph to concurrently train multiple replicas of GNNs are in practice. However, approaches requiring a partitioned graph usually suffer from communication overhead and load imbalance, even under optimal partitioning and communication strategies due to irregularities in the neighborhood minibatch sampling. This paper proposes practical trade-offs for improving the sampling and communication overheads for representation learn- ing on distributed graphs (using popular GraphSAGE architecture) by developing a parameterized prefetch and eviction scheme on top of the state-of-the-art Amazon DistDGL distributed GNN framework, demonstrating about 15–40% improvement in end-to-end training performance on the NERSC Perlmutter supercomputer for various OGB datasets.

Machine Leanring, high performance comptuing, grap↗