Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Training Time”

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 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

A machine learning estimator trained on synthetic data for real-time earthquake ground-shaking predictions in Southern California

Abstract After large-magnitude earthquakes, a crucial task for impact assessment is to rapidly and accurately estimate the ground shaking in the affected region. To satisfy real-time constraints, intensity measures are traditionally evaluated with empirical Ground Motion Models that can drastically limit the accuracy of the estimated values. As an alternative, here we present Machine Learning strategies trained on physics-based simulations that require similar evaluation times. We trained and validated the proposed Machine Learning-based Estimator for ground shaking maps with one of the largest existing datasets (<100M simulated seismograms) from CyberShake developed by the Southern California Earthquake Center covering the Los Angeles basin. For a well-tailored synthetic database, our predictions outperform empirical Ground Motion Models provided that the events considered are compatible with the training data. Using the proposed strategy we show significant error reductions not only for synthetic, but also for five real historical earthquakes, relative to empirical Ground Motion Models.

Environmental Sciences & Ecology↗
DOE OSTI2022

Subsurface stress criticality associated with fluid injection and determined using machine learning

Machine-learning methods and apparatus are disclosed to determine critical state or other parameters related to fluid-driven failure of a terrestrial locale impacted by anthropogenic activities such as hydraulic fracturing, hydrocarbon extraction, wastewater disposal, or geothermal harvesting. Acoustic emission, seismic waves, or other detectable indicators of microscopic processes are sensed. A classifier is trained using time series of microscopic data along with corresponding data of critical state or failure events. In disclosed examples, random forests and artificial neural networks are used, and grid-search or EGO procedures are used for hyperparameter tuning. Once trained, the classifier can be applied to live data from a fluid injection locale in order to assess a frictional state, assess seismic hazard, assess permeability, make predictions regarding a future fluid-driven failure event, or drive engineering solutions for mitigation or remediation. Variations are disclosed.

Johnson, Paul Allan↗
DOE OSTI2021

Failure prediction and estimation of failure parameters

Machine-learning methods and apparatus are disclosed to determine frictional state or other parameters in an earthquake zone or other failing medium, using acoustic emission, seismic waves, or other detectable indicators of microscopic processes. Predictions of future failures are demonstrated in different regimes. A classifier is trained using time series of acoustic emission data along with historic data of frictional state or failure events. In disclosed examples, random forests and gradient boost trees are used, and grid-search or EGO procedures are used for hyperparameter tuning. Once trained, the classifier can be applied to testing or live data in order to assess a frictional state, assess seismic hazard, or make predictions regarding a future failure event. The technology has been developed in a double direct shear apparatus, but can be widely applied to seismic faults, other terrestrial failures, or failures in man-made structures. Variations are disclosed.

Johnson, Paul Allan↗
DOE OSTI2021

Electronic demodulation of optically phase demodulated signals

Device, methods and systems for the electronic demodulation of optically phase demodulated signals are described. An example optical local oscillator generator configured to generate a radio frequency (RF) tone at a desired RF frequency includes a first input configured to receive a broadband optical pulse train, a second input coupled to a delay line interferometer to receive a first control voltage for controlling a delay value of the interferometer and to produce an output optical pulse train, a dispersive element, coupled to the delay line interferometer, to map the output optical pulse train to a time-domain modulated optical pulse train, an optical-to-electrical converter, coupled to the dispersive element, to convert the time-domain modulated optical pulse train to an analog electrical signal, and an RF filter, coupled to the optical-to-electrical converter, to filter the analog electrical signal to generate the RF tone at the desired RF frequency.

Perlmutter, David Simon↗
DOE OSTI2025

Model-based Hierarchical Reinforcement Learning for Improved Physical Security Design: A Prototype

Prior work in FY24 developed an adversarial AI agent aid in path analysis of physical protection systems. This agent, trained using a model-based reinforcement learning algorithm, was able to successfully learn the most vulnerable path in facilities. It was able to extend the current state of practice for physical protection design by exhibiting dynamic behavior based on current environmental conditions. Whereas PathTrace largely performs a static, graph-based analysis, the AI agent was able to make decisions based on relative position in the facility, current conditions (was the adversarial agnet discovered?), and proximity to secondary targets. The agent demonstrated some novel capabilities, but had limitations that need to be resolved before it can be used for production purposes. For example, the adversarial agent generalizes poorly and takes a relatively long time to train. Nonetheless, there is still considerable promise for developing the adversarial agent further in order to explore even richer, more dynamic behaviors (e.g., adversary motivations, environmental debris, and more). This work considers a complementary idea; development of a planning agent. The planning agent is envisioned as an auto-complete-like tool that can help accelerate security system design by human experts. The agent would respect existing barriers and sensors placed by a human expert while offering cost-effective suggestions (i.e., implicitly balancing effectiveness with cost) to improve the design. The goal is for this agent to be part of an expert’s toolbox, not to totally upend the current state-of-practice, or to displace human experts. The ultimate goal would be concurrent training of both the adversarial and planning agent together, to learn entirely through self-play. This would represent an entirely new way of performing system deign. We selected a hierarchical, model-based reinforcement learning algorithm to serve as the planning agent. This is an extension of concepts used in the prior FY24 adversarial agent work. There, we had a single agent acting an environment. Here, we have two different sub-agents (policies), working together, to form a complete agent. There is a manager policy, which can select abstract goals on slower time scales, and a worker, which performs primitive actions to reach goals selected by the manager. It is worth noting that this class of algorithm is challenging to work with. From our understanding, our work is one of the first successful uses of model-based reinforcement learning (MBRL) in nuclear energy1 , and likely the first hierarchical model-based reinforcement learning application in nuclear energy. Further, this work is one of the first known attempts to apply AI to perform a design tasks in nuclear energy. Consequently, there were significant implementation challenges and the bulk of the work was focused on successful implementation and algorithm design. The results presented here are very low technology readiness level as a consequence of the lack of related literature, but still represent a significant step forward in the pursuit of applied AI for design.

42 ENGINEERING↗
DOE OSTI2024

Emulator-Based Bayesian Calibration of the CISNET Colorectal Cancer Models

Purpose To calibrate Cancer Intervention and Surveillance Modeling Network (CISNET)'s SimCRC, MISCAN-Colon, and CRC-SPIN simulation models of the natural history colorectal cancer (CRC) with an emulator-based Bayesian algorithm and internally validate the model-predicted outcomes to calibration targets.Methods We used Latin hypercube sampling to sample up to 50,000 parameter sets for each CISNET-CRC model and generated the corresponding outputs. We trained multilayer perceptron artificial neural networks (ANNs) as emulators using the input and output samples for each CISNET-CRC model. We selected ANN structures with corresponding hyperparameters (i.e., number of hidden layers, nodes, activation functions, epochs, and optimizer) that minimize the predicted mean square error on the validation sample. We implemented the ANN emulators in a probabilistic programming language and calibrated the input parameters with Hamiltonian Monte Carlo-based algorithms to obtain the joint posterior distributions of the CISNET-CRC models' parameters. We internally validated each calibrated emulator by comparing the model-predicted posterior outputs against the calibration targets.Results The optimal ANN for SimCRC had 4 hidden layers and 360 hidden nodes, MISCAN-Colon had 4 hidden layers and 114 hidden nodes, and CRC-SPIN had 1 hidden layer and 140 hidden nodes. The total time for training and calibrating the emulators was 7.3, 4.0, and 0.66 h for SimCRC, MISCAN-Colon, and CRC-SPIN, respectively. The mean of the model-predicted outputs fell within the 95% confidence intervals of the calibration targets in 98 of 110 for SimCRC, 65 of 93 for MISCAN, and 31 of 41 targets for CRC-SPIN.Conclusions Using ANN emulators is a practical solution to reduce the computational burden and complexity for Bayesian calibration of individual-level simulation models used for policy analysis, such as the CISNET CRC models. In this work, we present a step-by-step guide to constructing emulators for calibrating 3 realistic CRC individual-level models using a Bayesian approach.

artificial neural networks↗
DOE OSTI2024

Investigation of candidates for reactor produced radioactive materials in support of radiological training exercises

Bromine-82, Potassium-42 and Copper-64 have been successfully adopted as radioactive surrogates for outdoor large area contamination training. The goal of this project was to discover new materials that could supplement potassium bromide (KBr) and copper pellets in radiological dispersal device (RDD) training events to reduce the down time of the training fields and to broaden the toolbox of the RDD surrogate training event program at Idaho National Laboratory. Of the ten different materials investigated, sodium nitrite, gallium metal, and gallium oxide presented the greatest promise as potential materials to replace potassium bromide in RDD training events.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗
DOE OSTI2022

Forecasting distributed energy resources adoption for power systems

Failing to incorporate accurate distributed energy resource penetration forecasts into long-term resource and transmission planning can lead to cost inefficiencies at best and system failures at worst. We have developed an open-source tool that employs an advanced Bass specification to calibrate and forecast technology adoption. The advanced specification includes geographic clustering, exogenously estimated market size, and dynamic time steps. Training on historical adoption of rooftop photovoltaics at the U.S. county-level and using detailed techno-economic estimates, our model achieves a two-year average mean-absolute-percentage-error of 19% in predicting system counts at the county-level, weighted by population. Model error was negatively correlated with market maturity - the error was 12% for counties in states with at least 28 W-per-capita of installed capacity. The advanced specification significantly reduces unweighted forecasting percent error compared to a conventional Bass specification: from 196% to 25% for capacity and from 226% to 22% for system count.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2022

Tsunami Early Warning From Global Navigation Satellite System Data Using Convolutional Neural Networks

Abstract We investigate the potential of using Global Navigation Satellite System (GNSS) observations to directly forecast full tsunami waveforms in real time. We train convolutional neural networks to use less than 9 min of GNSS data to forecast the full tsunami waveforms over 6 hr at select locations, and obtain accurate forecasts on a test data set. Our training and test data consists of synthetic earthquakes and associated GNSS data generated for the Cascadia Subduction Zone using the MudPy software, and corresponding tsunami waveforms in Puget Sound computed using GeoClaw. We use the same suite of synthetic earthquakes and waveforms as in earlier work where tsunami waveforms were used for forecasting, and provide a comparison. We also explore varying the number of GNSS stations, their locations, and their observation durations.

Rim, Donsub↗
DOE OSTI2024

Plant Disease Detection Technology Assessment

Visual inspections by US Customs and Border Protection agriculture specialists have identified approximately 20,000 regulated, quarantined pests each year in agricultural products entering the United States. Most of these pests identified in the Agriculture Quarantine and Inspection (AQI) program are insects. Many pathogens are difficult to detect in agricultural products, particularly in early stages of infection. New technologies can help to detect plant pathogens and the diseases that they cause. This technology assessment was performed for the US Department of Homeland Security Science and Technology Directorate (DHS S&T) through the Food, Agriculture, and Veterinary Defense (FAV-D) program to identify emerging technologies that could address this hard problem. These emerging technologies differ in their diagnostic sensitivities and specificities, as well as in their measurement time and training requirements. New instruments that detect volatile organic compounds characteristic of plant disease or pathogens could provide a less invasive inspection method. Dogs, which can successfully detect many concealed agricultural products, have also been trained to detect some plant pests and pathogens. Simple immunological tests offer sensitive and specific detection of many pathogens at the point of use. Advanced imaging methods that use AI to sort fruits and vegetables and recognize anomalies at high speeds could be used in cooperation with exporters to improve food quality and reduce pests. Advances in nucleic acid–based detection methods that have become gold standards for confirmatory diagnostics are now making those methods available for faster, point-of-use detection. These new methods should be developed in the context of AQI operational requirements, which apply risk-based sampling protocols to protect agriculture and facilitate commerce and passenger transit.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2026

Feasibility and strategic implications of deploying nuclear power reactors in Africa

This report assesses the feasibility and strategic implications of deploying nuclear power reactors, including large-scale plants, advanced small modular reactors (SMRs), and microreactors, in African countries. Case studies focus on South Africa, Egypt, Kenya, Ghana, and Nigeria, examining nuclear energy’s role in Africa’s rapidly evolving energy landscape, marked by fast-growing demand, significant electricity access gaps, increasing renewable penetration, and strong policy commitments to industrialization and energy security. Several U.S. reactor technologies and designs are considered based on their development status and readiness for deployment. The analysis finds that nuclear power can provide reliable, clean baseload and flexible generation, as well as high-temperature process heat for desalination, hydrogen production, and industrial applications. However, suitability is highly country-specific, depending on grid size and stability, transmission capacity, cooling water availability, regulatory readiness, and fuel supply chains. Near-term deployment opportunities are strongest for light-water reactors (such as NuScale, BWRX-300, AP300, and SMR-300) that use low-enriched uranium and build on proven technology. More advanced concepts, including gas-cooled, sodium-cooled, molten-salt cooled reactors, and microreactors, will likely be relevant for African deployment in the 2030s or later, contingent on demonstration projects, high-assay low-enriched uranium (HALEU) fuel availability, and mature international licensing frameworks. Economic analysis shows that SMRs are capital-intensive, with projected overnight costs for 300 MWe units in 2025 ranging from approximately 1.4 to 2.6 billion USD per module. The levelized cost of electricity (LCOE) is highly sensitive to the weighted average cost of capital (WACC). Given typically higher financing costs and utility balance-sheet weaknesses in many African countries, bankable project structures will require sovereign guarantees, robust offtake arrangements, and layered financing from export credit agencies, development finance institutions, and vendor nations. Comparisons with recent large nuclear projects in the United Arab Emirates (UAE) and Egypt underscore the central role of state-backed loans, long tenors, and concessional terms. Country case studies illustrate a spectrum of readiness and opportunity. South Africa operates two 920 MWe pressurized light water reactors (totaling 1,840 MWe) at Koeberg and has the most mature regulatory and industrial base, positioning it as a prime candidate for both large reactors and SMRs to replace coal, support desalination, and anchor industrial hubs. Egypt is constructing four VVER-1200 units at El Dabaa with strong state leadership and could later complement this fleet with SMRs for coastal and industrial applications. Kenya and Ghana are advancing through IAEA Milestones with growing institutional capacity and clear interest in SMRs that match their smaller grids and industrialization plans. Nigeria has the largest demand potential but faces acute constraints in grid reliability, project bankability, and regulatory capacity; targeted deployments of large reactors and SMRs near coastal or industrial sites could have high impact if accompanied by major grid upgrades and institutional reforms. The report identifies cross-cutting challenges such as financing, political continuity, public acceptance, nonproliferation and security, waste and back-end management, regulatory capacity, grid adequacy, and long deployment timelines for first-of-a-kind designs, and ANL/NSE-26/3 ii proposes broad directions for resolution. These include stronger multifaceted financing for nuclear, long-term national energy strategies that transcend electoral cycles, proactive stakeholder engagement, strengthened regional and national regulators, and systematic workforce development through centers of excellence and expanded training. The United States should develop partnerships with African countries and offer end-to-end nuclear package similar to those used effectively by competitors: coordinated project development, state-backed financing, long-term fuel services, and durable in-country support through regional offices and sustained workforce/regulatory training. With timely planning, sustained political commitment, and appropriate financing and institutional support, nuclear energy, both large reactors and advanced SMRs, can become a meaningful, though not dominant, pillar of Africa’s future power mix, enhancing energy security, enabling industrial growth, and supporting climate goals.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2026

Arbitrary Polynomial Separations in Trainable Quantum Machine Learning

Recent theoretical results in quantum machine learning have demonstrated a general trade-off between the expressive power of quantum neural networks (QNNs) and their trainability; as a corollary of these results, practical exponential separations in expressive power over classical machine learning models are believed to be infeasible as such QNNs take a time to train that is exponential in the model size. We here circumvent these negative results by constructing a hierarchy of efficiently trainable QNNs that exhibit unconditionally provable, polynomial memory separations of arbitrary constant degree over classical neural networks—including state-of-the-art models, such as Transformers—in performing a classical sequence modeling task. This construction is also computationally efficient, as each unit cell of the introduced class of QNNs only has constant gate complexity. We show that contextuality—informally, a quantitative notion of semantic ambiguity—is the source of the expressivity separation, suggesting that other learning tasks with this property may be a natural setting for the use of quantum learning algorithms.

Anschuetz, Eric R. [California Institute of Techno↗
DOE OSTI2025

End-to-end deep learning pipeline for real-time Bragg peak segmentation: from training to large-scale deployment

X-ray crystallography reconstruction, which transforms discrete X-ray diffraction patterns into three-dimensional molecular structures, relies critically on accurate Bragg peak finding for structure determination. As X-ray free electron laser (XFEL) facilities advance toward MHz data rates (1 million images per second), traditional peak finding algorithms that require manual parameter tuning or exhaustive grid searches across multiple experiments become increasingly impractical. While deep learning approaches offer promising solutions, their deployment in high-throughput environments presents significant challenges in automated dataset labeling, model scalability, edge deployment efficiency, and distributed inference capabilities. We present an end-to-end deep learning pipeline with three key components: (1) a data engine that combines traditional algorithms with our peak matching algorithm to generate high-quality training data at scale, (2) a modular architecture that scales from a few million to hundreds of million parameters, enabling us to train large expert-level models offline while deploying smaller, distilled models at the edge, and (3) a decoupled producer-consumer architecture that separates specialized data source layer from model inference, enabling flexible deployment across diverse computing environments. Using this integrated approach, our pipeline achieves accuracy comparable to traditional methods tuned by human experts while eliminating the need for experiment-specific parameter tuning. Although current throughput requires optimization for MHz facilities, our system's scalable architecture and demonstrated model compression capabilities provide a foundation for future high-throughput XFEL deployments.

Wang, Cong↗
DOE OSTI2025

Simple Wins: Driving Effective Implementation of Energy Efficiency Projects

Small- and medium-sized manufacturers (SMMs) in the United States, making up over 98% of manufacturing firms, account for 48.3% of the sector’s energy consumption. Despite access to energy assessments and technical resources, such as those from the US Department of Energy’s Better Plants program and Industrial Training and Assessment Centers, implementation rates for identified energy-saving measures remain lower than expectations, averaging 47%. Some barriers were identified by other researchers as limited workforce capacity, inadequate training, and time constraints hinder progress. This article studied the development of customized checklists together with the energy assessment report as a practical solution to improve implementation rates for energy efficiency projects among SMMs. The framework for the checklists was grounded in five principles: short, precise, actionable, relevant, and codeveloped (SPARC). A case study of a 500,000-squarefoot SMM demonstrates how tailored checklists targeting significant energy users—such as heating, ventilating and air conditioning (HVAC), lighting, and compressed air systems for this facility—can simplify the process for staff to do facility walkthroughs to monitor best practices and track the progress of energy efficiency project implementation.

Guo, Wei [Oak Ridge National Laboratory (ORNL), Oa↗
DOE OSTI2022

Development of lean, efficient, and fast physics-framed deep-learning-based proxy models for subsurface carbon storage

In this work, we present deep-learning-based surrogate models for CCUS developed with four different algorithms and a physics-framed two-phase flow problem involving displacement of water by CO 2 . The deep-learning models were trained using 3D datasets describing the pressure plume, CO 2 saturation plume, and water extraction rate generated by numerical simulation. The hyperparameters defining the architecture of the neural networks were optimized to determine the slimmest network size and training parameters that give the most efficient performance at the least training cost. To develop a robust model that closely mimics the governing physical laws, the discretized form of the two-phase fluid transport equation was used to formulate the supervised deep-learning task. The algorithms investigated in this study predicted the data to above 95% accuracy, with the multi-layer perceptron model demonstrating the best performance by balancing training speed, prediction time, and prediction accuracy with lean network capacity. Furthermore, the surrogate models simultaneously predict reservoir pressure and CO 2 saturation in every grid block, including the surface well extraction rate and bottomhole pressure, at all simulation times for a given static model realization in just a few seconds on a standard desktop computer. A key outcome of this study is that limits can be placed on network design parameters to avoid over designing neural networks, with associated efficiencies in training and prediction times. This is very useful because large volumes of data may be generated in CCUS projects and over-design of neural network architectures imposes penalties that are antithetical to the goal of near-real time forecasting.

58 GEOSCIENCES↗
DOE OSTI2021

Anomaly Detection, Localization and Classification using Drifting Synchrophasor Data Streams

With ongoing automation and digitization of the electric power system, several Phasor Measurement Units(PMUs) have been deployed for monitoring and control. PMU data can have multiple anomalies, and many of the researchers in the past have concentrated on training machine/deep learning algorithms offline for anomaly detection over PMU data (i.e., not in real time). These machine/deep learning algorithms, when trained offline on a sample rather than a population of the dataset, fail to consider the dynamic behavior of the power grid in real-time, resulting in low accuracy. Considering the dynamic behavior of the power grid (e.g., change in load, generation, distributed energy resources (DERs) switching, network, controls), the definition of data anomalies varies in time and requires online training. A fundamental challenge is to enable online (i.e., real-time) training of machine/deep learning algorithms for anomaly detection over streaming PMU data. While machine/deep learning is often desirable to manage data streams, training a deep learning algorithm over streaming PMU data is nontrivial due to changes in data statistics caused by dynamic streaming data. This paper proposes PMUNET: a novel device-level deep learning-based data-driven approach for anomaly detection, localization, and classification over streaming PMU data, using online learning and multivariate data-drift detection algorithm .Two variants of PMUNET, Dynamic data Change Driven Learning (DCDL) and Continuity Driven Learning (CDL), are proposed and compared. DCDL aims to train the deep learning algorithm whenever the definition of anomaly changes due to the power grid dynamics. On the other hand, CDL continuously trains the deep learning algorithm over the PMU data-stream. The experimental results verify that DCDL outperforms CDL and other efficient anomaly detection methods over multiple events such as faults and load/ generator/capacitor/DERs variations/switching for IEEE 14 and 39 Bus test system as well as real PMU industrial data. The result verifies that DCDL variant of PMUNET improves over existing approach with a gain of 2% - 10% in terms of accuracy, false-positive rate, and false-negative rate.

adversarial deep learning↗
DOE OSTI2024

ION Work Reduction Opportunity Realization Demonstration

The purpose of this research was to realize one of the advanced training work reduction opportunities first presented in the Idaho National Laboratory (INL) report, “Process for Significant Nuclear Work Function Innovation Based on Integrated Operations Concepts” (INL/EXT-21-64134) [1], with a nuclear power plant (NPP) research partner. Researchers modernized two trainings: (1) an accredited instructor-led training (ILT) overview course on Westinghouse DS 480-volt (V) circuit breakers to a multimedia-focused computer-based-training (CBT) learning module, and (2) an on-demand chaptered video on how to properly rack and un-rack a Westinghouse DS 480-V circuit breaker. These modernized work products were developed and implemented in a manner consistent with the industry guidelines found in Institution of Nuclear Power Operations (INPO) Teaching and Learning 23-001 [2]. Researchers calculated that the modernized accredited training course reduced the time necessary to prepare and deliver the training material by a factor of 8:1. The amount of time learners spend in class could be reduced by this same factor. In other words, if a course took 8 hours to deliver a class, the new CBT instruction would take just over 1 hour. The researchers noted that the requirement for any practicum training by the learners with the instructor(s) would remain in place. But through interviews with new and experienced learners, the researchers discovered that the confidence of these learners in performing the racking and un-racking of the circuit breaker improved as a result of using the new modernized CBT process. Additionally, the learners who tested the modernized work products enjoyed the modernized CBT and the learning video significantly more than current in-class learning methods. These are encouraging results for the nuclear industry, as this modernization of training can be applied to other classes and is scalable across the industry. In line with the Integrated Operations for Nuclear (ION) model, positive workload analysis supports the investment of resources in modernizing NPP training processes and infrastructure. Implementation of the advanced training technologies in this report is likely to result in substantive long-term workload benefits to instructors and learners and result in hard-dollar savings on contractor spends. Additionally, investment in these modernized training processes will result in improved learner proficiency. The results of this research can be applied to additional operator, technical, and general training topics to provide additional workload and learning benefits in addition to what was explored.

42 ENGINEERING↗