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 1,621 records · Page 90

Rejection Sampling with Autodifferentiation -- Case study: Fitting a Hadronization Model

We present an autodifferentiable rejection sampling algorithm termed Rejection Sampling with Autodifferentiation (RSA). In conjunction with reweighting, we show that RSA can be used for efficient parameter estimation and model exploration. Additionally, this approach facilitates the use of unbinned machine-learning-based observables, allowing for more precise, data-driven fits. To showcase these capabilities, we apply an RSA-based parameter fit to a simplified hadronization model.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Panel Session 13: TRU Waste Generator Sites - Implementation of the New US DOE WIPP WAC

This panel focused on the next phase of the US National Transuranic (TRU) Program (NTP) to support shipments to the Waste Isolation Pilot Plant (WIPP: located in Carlsbad, New Mexico, USA). Topics include program changes to increase waste stream approval efficiency, Documented Safety Analysis (DSA)/Waste Acceptance Criteria (WAC), TRUPACT-III and Remote Handled (RH) shipments, lessons learned from NTP waste certification and transportation, and NTP transportation stakeholder engagement and support programs. Presentations proposed include: 1 - National TRU Program Update (Kenneth Princen, US DOE (USA)); 2 - WIPP WAC (Rev 9) Implementation (Mark Pearcy, Nuclear Waste Partnership, LLC (USA)); 3 - Remote-Handled (RH) TRU Waste Update (J.R. Stroble, US DOE (USA)); 4 - National TRU Program Transportation Stakeholder Engagement and Support (James Mason, US DOE (USA))

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

DeepFreeze: Towards Scalable Asynchronous Checkpointing of Deep Learning Models

In the age of big data, deep learning has emerged as a powerful tool to extract insight and exploit its value, both in industry and scientific applications. One common pattern emerging in such applications is frequent checkpointing of the state of the learning model during training, needed in a variety of scenarios: analysis of intermediate states to explain features and correlations with training data, exploration strategies involving alternative models that share a common ancestor, knowledge transfer, resilience, etc. However, with increasing size of the learning models and popularity of distributed data-parallel training approaches, simple checkpointing techniques used so far face several limitations: low serialization performance, blocking I/O, stragglers due to the fact that only a single process is involved in checkpointing. This paper proposes a checkpointing technique specifically designed to address the aforementioned limitations, introducing efficient asynchronous techniques to hide the overhead of serialization and I/O, and distribute the load over all participating processes. Experiments with two deep learning applications (CANDLE and ResNet) on a pre-Exascale HPC platform (Theta) shows significant improvement over state-of-art, both in terms of checkpointing duration and runtime overhead.

checkpointing↗

OASIS: Offsetting Active Reconstruction Attacks in Federated Learning

Federated Learning (FL) has garnered significant attention for its potential to protect user privacy while enhancing model training efficiency. For that reason, FL has found its use in various domains, from health care to industrial engineering, especially where data cannot be easily exchanged due to sensitive information or privacy laws. However, recent research has demonstrated that FL protocols can be easily compromised by active reconstruction attacks executed by dishonest servers. These attacks involve the malicious modification of global model parameters, allowing the server to obtain a verbatim copy of users' private data by inverting their gradient updates. Tackling this class of attack remains a crucial challenge due to the strong threat model. In this paper, we propose a defense mechanism, namely OASIS, based on image augmentation that effectively counteracts active reconstruction attacks while preserving model performance. We first uncover the core principle of gradient inversion that enables these attacks and theoretically identify the main conditions by which the defense can be robust regardless of the attack strategies. We then construct our defense with image augmentation showing that it can undermine the attack principle. Comprehensive evaluations demonstrate the efficacy of the defense mechanism highlighting its feasibility as a solution.

deep neural networks↗

Error-Bounded Learned Scientific Data Compression with Preservation of Derived Quantities

Scientific applications continue to grow and produce extremely large amounts of data, which require efficient compression algorithms for long-term storage. Compression errors in scientific applications can have a deleterious impact on downstream processing. Thus, it is crucial to preserve all the “known” Quantities of Interest (QoI) during compression. To address this issue, most existing approaches guarantee the reconstruction error of the original data or primary data (PD), but cannot directly control the problem of preserving the QoI. In this work, we propose a physics-informed compression technique that is composed of two parts: (i) reduction of the PD with bounded errors and (ii) preservation of the QoI. In the first step, we combine tensor decompositions, autoencoders, product quantizers, and error-bounded lossy compressors to bound the reconstruction error at high levels of compression. In the second step, we use constraint satisfaction post-processing followed by quantization to preserve the QoI. To illustrate the challenges of reducing the reconstruction errors of the PD and QoI, we focus on simulation data generated by a large-scale fusion code, XGC, which can produce tens of petabytes in a single day. The results show that our approach can achieve a high compression amount while accurately preserving the QoI within scientifically acceptable bounds.

97 MATHEMATICS AND COMPUTING↗

First Ever Polymer Flood Field Pilot to Enhance the Recovery of Heavy Oils on Alaska North Slope – Producer Responses and Operational Lessons Learned

The US Department of Energy and Hilcorp Alaska, LLC are jointly cosponsoring a field pilot project entitled “First Ever Field Pilot on Alaska’s North Slope to Validate the Use of Polymer Floods for Heavy Oil Enhanced Oil Recovery (EOR).” The objective of this pilot is to perform a field experiment to validate the use of an advanced polymer flooding technology to unlock the vast heavy oil resources on Alaska North Slope (ANS). Two pairs of horizontal injection and production wells have been deployed in an isolated fault block of the Schrader Bluff heavy oil reservoir at the Milne Point Field to conduct a polymer flood pilot which was designed to acquire field performance data to optimize polymer flood design in the Schrader Bluff heavy oil reservoirs on ANS. Hydrolyzed polyacrylamide (HPAM) polymer injection started on August 28, 2018 using a custom made polymer mixing and pumping unit. Polymer solution properties such as concentration, viscosity, and filter ratio, have been closely monitored and adjusted as necessary. Operational procedures have been improved to ensure adequate injectivity and polymer propagation through the formation. Oil and water production is tested frequently to monitor water cut performance, and produced water is sampled and analyzed for polymer content. Tracers were pumped pre and post polymer injection startup to compare polymer flood breakthrough timing and sweep efficiency. Polymer injectivity of the horizontal wells drilled in the Schrader Bluff NB sand is found to be sufficient to replace the reservoir production voidage although there were some declines as high viscosity polymer swept the near wellbore region. Production data show significant reduction in water cut and the oil production rate has stabilized. No polymer production has been confirmed from the two horizontal producers after 22 months of polymer injection into the two supporting horizontal injectors. Tracer data show very low sweep efficiencies with waterflood alone, whereas significant improvement has been achieved with polymer flood. Many operational lessons have been learned and improvements have been made regarding polymer mixing, pumping, and onsite quality control, particularly in a challenging Arctic environment. Adequate polymer injection rate can be achieved with diligent monitoring and quality assurance of the properties of the injected polymer solution.

Ning, Samson↗

Supervised Learning-Based Spatial Position Estimation with Vertical Displacement for Hovering UAV Wireless Power Transfer

This study presents a supervised learning-based spatial position estimation approach for wireless power transfer (WPT) systems supporting hovering unmanned aerial vehicle (UAV) charging. Unlike stationary charging scenarios, hovering UAVs introduce continuous lateral misalignment and vertical displacement, leading to variations in magnetic coupling and reduced power transfer efficiency. To address this challenge, the proposed method estimates the relative spatial position of the receiver coil using only electrical measurements obtained at the secondary side. A supervised learning model is trained to map output voltage and current features to spatial coordinates, enabling position awareness without requiring external sensors, vision systems, or communication links. The sensing functionality is inherently integrated into the WPT system, allowing simultaneous power transfer and localization through the same magnetic interface. Experimental validation is conducted on a laboratory-scale prototype under varying lateral offsets and air-gap conditions. In addition, spline-based interpolation is employed to increase spatial data density for training. The results demonstrate that the proposed framework can capture spatial variations associated with both lateral and vertical displacement, providing reliable position estimation under hovering conditions. This work establishes a hardware-efficient, sensorless solution for UAV wireless charging and serves as a baseline for advanced data-driven position estimation methods in dynamic WPT systems.

Asa, Erdem [ORNL] (ORCID:0000000190884812)↗

Application of machine learning to sporadic experimental data for understanding epitaxial strain relaxation

Understanding epitaxial strain relaxation is one of the key challenges in functional thin films with strong structure–property relations. Herein, we employ an emerging data analytics approach to quantitatively evaluate the underlying relationships between critical thickness ($h_c$) of strain relaxation and various physical and chemical features, despite the sporadic experimental data points available. First, we have collected and refined the reported $h_c$ of the perovskite oxide thin film/substrate system to construct a consistent sub-dataset which captures a common trend among the varying experimental details. Then, we employ correlation analyses and feature engineering to find the most relevant feature set which includes Poisson's ratio and lattice mismatch. With the insight offered by correlation analyses and feature engineering, machine learning (ML) models have been trained to deduce a decent accuracy, which has been further validated experimentally. In this work, the demonstrated framework is expected to be efficiently extended to the other classes of thin films in understanding $h_c$.

36 MATERIALS SCIENCE↗

NEML2: An efficient and modular multiphysics constitutive modeling library for hybrid computing environments

This paper presents NEML2, an open-source, high-performance library developed for constitutive material modeling, designed to support the flexible and modular development of models for complex material behavior. Building on the foundational structure of its predecessor, NEML, the NEML2 library introduces significant improvements, including enhanced vectorization, automatic differentiation, and seamless integration with PyTorch, facilitating the application of machine learning techniques in material simulations. NEML2 provides a C++ backend with Python bindings, enabling users to create custom material models that can be executed efficiently on both CPU and GPU platforms. The library also supports coupling with Multiphysics simulation frameworks like MOOSE, making it suitable for realistic simulations involving coupled physical processes. Rigorous quality assurance through unit and regression testing ensures the reliability of results, while the extensible, user-friendly design encourages collaboration and reproducibility across the scientific community. This paper provides an overview of NEML2’s architecture, core features, and applications, highlighting its impact on accelerating material qualification and advancing computational methods in materials science.

GPU↗

Evaluating the causes of cost reduction in photovoltaic modules

Photovoltaic (PV) module costs have declined rapidly over forty years but the reasons remain elusive. Here we advance a conceptual framework and quantitative method for quantifying the causes of cost changes in a technology, and apply it to PV modules. Our method begins with a cost model that breaks down cost into variables that changed over time. Cost change equations are then derived to quantify each variable's contribution. We distinguish between changes observed in variables of the cost model – which we term low-level mechanisms of cost reduction – and research and development, learning-by-doing, and scale economies, which we refer to as high-level mechanisms. We find that increased module efficiency was the leading low-level cause of cost reduction in 1980–2012, contributing almost 25% of the decline. Government-funded and private R&D was the most important high-level mechanism over this period. After 2001, however, scale economies became a more significant cause of cost reduction, approaching R&D in importance. Policies that stimulate market growth have played a key role in enabling PV's cost reduction, through privately-funded R&D and scale economies, and to a lesser extent learning-by-doing. The method presented here can be adapted to retrospectively or prospectively study many technologies, and performance metrics besides cost.

14 SOLAR ENERGY↗

How to Host An Effective Data Competition: Statistical Advice for Competition Design and Analysis

Data competitions rely on real-time leaderboards to rank competitor entries and stimulate algorithm improvement. While such competitions have become quite popular and prevalent, particularly in supervised learning formats, their implementations by the host are highly variable. Without careful planning, a supervised learning competition is vulnerable to overfitting, where the winning solutions are so closely tuned to the particular set of provided data that they cannot generalize to the underlying problem of interest to the host. This paper outlines some important considerations for strategically designing relevant and informative data sets to maximize the learning outcome from hosting a competition based on our experience. It also describes a postcompetition analysis that enables robust and efficient assessment of the strengths and weaknesses of solutions from different competitors, as well as greater understanding of the regions of the input space that are well-solved. The postcompetition analysis, which complements the leaderboard, uses exploratory data analysis and generalized linear models (GLMs). The GLMs not only expand the range of results we can explore, they also provide more detailed analysis of individual subquestions including similarities and differences between algorithms across different types of scenarios, universally easy or hard regions of the input space, and different learning objectives. When coupled with a strategically planned data generation approach, the methods provide richer and more informative summaries to enhance the interpretation of results beyond just the rankings on the leaderboard. The methods are illustrated with a recently completed competition to evaluate algorithms capable of detecting, identifying, and locating radioactive materials in an urban environment.

97 MATHEMATICS AND COMPUTING↗

Attention to quantum complexity

The imminent era of error-corrected quantum computing demands robust methods to characterize quantum state complexity from limited, noisy measurements. We introduce the Quantum Attention Network (QuAN), a classical artificial intelligence (AI) framework leveraging attention mechanisms tailored for learning quantum complexity. Inspired by large language models, QuAN treats measurement snapshots as tokens while respecting permutation invariance. Combined with our parameter-efficient miniset self-attention block, this enables QuAN to access high-order moments of bit-string distributions and preferentially attend to less noisy snapshots. We test QuAN across three quantum simulation settings: driven hard-core Bose-Hubbard model, random quantum circuits, and toric code under coherent and incoherent noise. QuAN directly learns entanglement and state complexity growth from experimental computational basis measurements, including complexity growth in random circuits from noisy data. In regimes inaccessible to existing theory, QuAN unveils the complete phase diagram for noisy toric code data as a function of both noise types, highlighting AI’s transformative potential for assisting quantum hardware.

Kim, Hyejin [Cornell Univ., Ithaca, NY (United Sta↗

Machine learning assisted unfolding for neutrino cross-section measurements with the OmniFold technique

The choice of unfolding method for a cross-section measurement is tightly coupled to the model dependence of the efficiency correction and the overall impact of cross-section modeling uncertainties in the analysis. A key issue is the dimensionality used in unfolding, as the kinematics of all outgoing particles in an event typically affect the reconstruction performance in a neutrino detector. OmniFold is an unfolding method that iteratively reweights a simulated dataset, using machine learning to utilize arbitrarily high-dimensional information, that has previously been applied to proton-proton and proton-electron datasets. This paper demonstrates OmniFold’s application to a neutrino cross-section measurement for the first time using a public T2K near detector simulated dataset, comparing its performance with traditional approaches using a mock data study.

Machine learning↗

Using Artificial Intelligence to Improve Reliability and Operational Efficiency of Small-Scale Hydroelectric Distributed Generation

Reliability and resilience are critical concerns for distributed generation (DG) at the rural electric level. The integration of renewable energy sources, such as small-scale hydroelectric distributed generators (hydro DGs), introduces operational challenges, particularly regarding aging infrastructure and grid stability. Artificial Intelligence (AI)-driven Machine Learning (ML) models and applications of Large Language Models (LLMs) offer promising solutions for optimizing DG operations and enhancing resilience. This paper explores AI-based models for improving efficiency, fault resolution, and outage mitigation in small-scale hydro DGs. Furthermore, it highlights the development of a centralized, AI-powered information portal for rural electric cooperatives and municipalities. The research evaluates hydro DG plant models and discusses the applicability of AI-powered question-answering tools for real-time operations, focusing on statistical data, load flow, voltage regulation, and generation power. The findings demonstrate AI’s potential to transform DG management to ensure greater stability and resilience in rural electric grids.

Bhattacharyya, Arjun [ORNL] (ORCID:000900060976046↗

A Plug-in Hybrid Consumer Choice Model with Detailed Market Segmentation

This paper describes a consumer choice model for projecting U.S. demand for plug-in hybrid electric vehicles (PHEV) in competition among 13 light-duty vehicle technologies over the period 2005-2050. New car buyers are disaggregated by region, residential area, attitude toward technology risk, vehicle usage intensity, home parking and work recharging. The nested multinomial logit (NMNL) model of vehicle choice incorporates daily vehicle usage distributions, refueling and recharging availability, technology learning by doing, and diversity of choice among makes and models. Illustrative results are presented for a Base Case, calibrated to the Annual Energy Outlook (AEO) 2009 Reference Updated Case, and an optimistic technology scenario reflecting achievement of U.S. Department of Energy s (DOE s) FreedomCAR goals. PHEV market success is highly dependent on the degree of technological progress assumed. PHEV sales reach one million in 2037 in the Base Case but in 2020 in the FreedomCARGoals Case. In the FreedomCARGoals Case, PHEV cumulative sales reach 1.5 million by 2015. Together with efficiency improvements in other technologies, petroleum use in 2050 is reduced by about 45% from the 2005 level. After technological progress, PHEV s market success appears to be most sensitive to recharging availability, consumers attitudes toward novel echnologies, and vehicle usage intensity. Successful market penetration of PHEVs helps bring down battery costs for electric vehicles (EVs), resulting in a significant EV market share after 2040.

02 PETROLEUM↗

Defect And Damage Characterization Of Additively Manufactured Titanium Alloy Ti-5553 Using Traditional Computed Tomography Volume Segmentation And Machine Learning Algorithms

The mechanical response of a component is affected by defects, such as porosity, arising from the laser powder bed fusion (LPBF) fabrication process. Thus, it is important to develop accurate and efficient inspection methods for identifying porosity. In this work, porosity identified in an X-ray computed tomography (XCT) volume of a Ti-5553 coupon was compared to pores identified in a serial sectioned volume that represented the ground truth. The porosity of the XCT scan was identified using contrast-based, ISO-based, and machine learning (ML) methods for segmentation. Large inherent porosity was easy to identify, but the ISO thresholding still struggled due to the intensity gradient resulting from both the beam hardening in XCT and the uneven lighting of the serial sectioning panels. Further, the results show that ML-based methods were better suited for identifying small pores and reducing the amount of false positives. Additionally, high strain-rate impact testing was done on some of the XCT samples as well as post-mortem XCT inspection, and the same suite of segmentation and quantification tools were used to identify the large spallation cavities. The comparison of porosity pre- and post-mortem provides insight on the influence of the LPBF porosity on the formation of spall cavities.

36 MATERIALS SCIENCE↗

On-the-fly active learning of interpretable Bayesian force fields for atomistic rare events

Abstract Machine learned force fields typically require manual construction of training sets consisting of thousands of first principles calculations, which can result in low training efficiency and unpredictable errors when applied to structures not represented in the training set of the model. This severely limits the practical application of these models in systems with dynamics governed by important rare events, such as chemical reactions and diffusion. We present an adaptive Bayesian inference method for automating the training of interpretable, low-dimensional, and multi-element interatomic force fields using structures drawn on the fly from molecular dynamics simulations. Within an active learning framework, the internal uncertainty of a Gaussian process regression model is used to decide whether to accept the model prediction or to perform a first principles calculation to augment the training set of the model. The method is applied to a range of single- and multi-element systems and shown to achieve a favorable balance of accuracy and computational efficiency, while requiring a minimal amount of ab initio training data. We provide a fully open-source implementation of our method, as well as a procedure to map trained models to computationally efficient tabulated force fields.

36 MATERIALS SCIENCE↗

Studying the hadron structure with PANDA and CLAS using machine learning techniques

The hadron spectroscopy and structure are currently very active fields of research to study the non-perturbative regime of quantum chronodynamics. The first one studies the complex structure of excited hadrons by looking at their decay products, while the latter uses lepton scattering on nucleons. Both methods require reconstruction algorithms with great efficiency and good particle identification and background rejection rates. This work aims to provide these by either improving the existing methods or developing new ones. The first part of this document presents a feasibility study of a predicted hybrid charmonium state for the PANDA experiment. Lattice QCD calculations predict the ground state hybrid charmonium to be a spin exotic with quantum numbers of JP C = 1?+ at a mass of around 4.3 GeV with a width to be around 20 MeV. A machine learning based data analysis scheme is proposed to further improve the signal efficiency and the background reduction, alongside with improvements of the analysis software (PandaRoot), that are vital for this study. These improvements include a reworked clustering algorithm for the electromagnetic calorimeter (EMC) and an optimized monte carlo matching for neutral particles. The second part of this document is about studying the proton structure. A multidimensional study of the structure function ratio Fsin(?)LU /FUU has been performed for K±, based on the measurement of beam-spin asymmetries. It uses the high statistics data recorded with the CLAS12 spectrometer at Jefferson Laboratory. Fsin(?)LU is a twist-3 quantity that provides information about the quark gluon correlations in the proton. This document will present for the first time a simultaneous analysis of two kaon channels over a large kinematic range of z, xB , PT and Q2 with virtualities Q2 ranging from 1 GeV2 up to 8 GeV2 using machine learning techniques for improved particle identification.

Kripko, Aron↗