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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,783 records · Page 99

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Characterization of Arsenic and Selenium in Coal Fly Ash to Improve Evaluations for Disposal and Reuse Potential (Final Technical Report)

Coal fly ash is a high volume waste material that is discarded in landfills and surface water impoundments across the U.S. and is also widely recycled for a variety of applications. The leaching of potential of contaminants of concern, such as arsenic (As) and selenium (Se), is often the driver of risk assessments for coal ash disposal and reuse. The extent of leachable As and Se depends on several factors related to environmental conditions and fly ash characteristics. Previous studies employed various methods to delineate the concentration, chemical form, and distribution of As and Se in fly ash materials. However, few studies have attempted to directly correlate these properties to mobilization parameters relevant to disposal and reuse. Instead, the coal residuals industries often rely upon standardized leaching protocols that can be laborious or involve hazardous chemicals. The goals of the project were to: 1) Develop and evaluate a characterization protocol that can be used to screen fly ash samples for leachability of As and Se; 2) Characterize As, Se, and associated constituents of fly ash particles at multiple length scales (nanometer to micrometer) to determine if elemental associations differ as a function of the resolution of characterization; and 3) Establish a predictive model for the chemical composition of coal ash produced annually at major U.S. coal fired power facilities on 50-year national coal supply records. For the first objective, we performed leaching experiments with 52 fly ash samples collected from 15 different U.S. power plants and representing coal feedstocks from the three major domestic coal regions. For this work, we assessed the mobilization potential of As and Se in fly ash based on standardized leaching protocols and performed multivariate and lasso regression analyses to explore correlations of leachable As and Se contents with characteristics such as major element contents, loss on ignition (LOI) and pH. The results of regression models indicated that major elements (Fe, Ca, Al) for a wide range of fly ashes can serve as predictor variables for the leaching potential of As, but not for Se. LOI and pH were not important predictive variables in the models. Both regression approaches resulted in relatively strong fits for leachable As (correlation coefficient R 2 = 0.78 for both models) compared to models for leachable Se (R 2 = 0.49). Overall, these results suggest that correlation models combined with on-site elemental analysis with portable analyzers may enable a screening method for leachable As in coal ash. For the second objective, we utilized nanoscale 2-D imaging (30-50 nm spot size) with the Hard X-ray Nanoprobe (HXN) in combination with microprobe X-ray capabilities (~5 µm resolution) to determine As and Se elemental associations in fly ash particles. Speciation of As and Se was also measured at the nano- to microscale with X-ray absorption spectroscopy. The enhanced resolution of HXN showed As and Se that were diffusely located around or comingled with Ca- and Fe-rich particles. The results also showed nanoparticles of Se attached to the surface of fly ash grains. Overall, a comparison of As and Se species across scales highlights the heterogeneity and complexity of chemical associations for these trace elements of concern in coal fly ash. For the final objective, we developed a predictive model for major element composition of coal ash in reserve at disposal sites of major U.S. coal fired power plants. This model was constructed from coal purchase records of 705 power stations from 1973-2022 and was trained on coal ash composition data showing that coal ash elemental composition is strongly associated with the source of feedstock coal. The model showed regional shifts in the major element contents of ash produced by power plants in the last 50 years, particularly for calcium and iron (expressed as %CaO and %Fe 2 O 3 ), as coal-fired power stations changed their source of coal over this time frame. Our approach enables an estimation of coal ash chemical composition that is stored in waste impoundments at individual power stations. Such information can help delineate the regional market potential for material applications that would utilize coal ash harvested from disposal sites across the U.S.

01 COAL, LIGNITE, AND PEAT↗

DOE OSTI2025

Model Card for WaveDenoiser

This study used STEAD to train and evaluate this model because STEAD is among the best benchmark datasets available for local to regional data. STEAD is a global dataset with over 1 million 60 s long seismic waveforms that originated from approximately 450,000 earthquakes and background noise captured by more than 2,500 seismic stations. Each waveform in STEAD was attached with metadata such as earthquake locations, station locations, and signal arrival times when available

58 GEOSCIENCES↗

DOE OSTI2026

Describing Point Defect Topology in 2D Energy Materials Through Computer Vision

Point defects such as vacancies and impurity atoms strongly impact the performance of 2D materials. Traditional efforts often rely on manual detection, a process that is time-intensive, prone to human error, and challenging to scale. Here we leverage machine learning (ML) methods to identify and quantify vacancies within 2D transition metal carbides (Ti3C2, MXenes), aiming to expedite detection while improving accuracy. MXenes exhibit valuable defect-defined electrochemical properties, but we currently lack statistical understanding of defect topology needed to fully harness these materials. Here we employ a convolutional neural network for semantic segmentation of experimental MXene images, opening an opportunity to conduct a rigorous statistical study on defect hierarchy while investigating local relaxation in the lattice. We show how the integration of ML can yield fundamental insight into point defects, providing a powerful tool that will play an increasingly crucial role in the future of materials science. ML is often not just a matter of straightforward application, and pretrained models proved ineffective in this case. Instead, we trained our own neural network (NN) and applied data augmentation techniques and fine-tuning to the training dataset. Since labeled microscopy data is often scarce, we developed training data from a previously published wide-frame MXene image, using customized Gaussian fitting to locate atomic positions. Our trained model was then applied to a large dataset of experimental images, enabling a statistical study of defect configurations across three samples prepared with different HF etchant concentrations (5%, 9.1%, and 12.5%), as shown in Fig. 1. This also allowed us to investigate local strain around vacancies, though we find that we are limited by the precision of measurements using high-angle annular dark field (HAADF) images, as shown in Fig. 2. This study demonstrates how ML enables large-scale, quantitative analysis of atomic defects - an otherwise infeasible task with traditional methods. While our NN was specialized for Ti3C2 MXenes, the pipeline we developed provides a foundation for future ML models tailored to other materials. Ultimately, we envision embedding the NN onto the microscope to give real-time feedback to the user. To make this a reality, continued work is necessary to fully understand the NN's capabilities and limitations. This study gets one step closer to our goals of automated experimentation moving away from traditional methods of manual labeling. As ML capabilities advance, we hope to continue adapting and applying these techniques in microscopy.

2D materials↗

DOE OSTI2025

GPR_calculator: An on-the-fly surrogate model to accelerate massive nudged elastic band calculations

We present GPR_calculator, a package based on Python and C++ programming languages to build an on-the-fly surrogate model using Gaussian Process Regression (GPR) to approximate computationally expensive electronic structure calculations. The key idea is to dynamically train a GPR model during the simulation that can accurately predict energies and forces with uncertainty quantification. When the uncertainty is high, the costly electronic structure calculation is performed to obtain the ground truth data, which is then used to update the GPR model. To illustrate the effectiveness of GPR_calculator, we demonstrate its application in Nudged Elastic Band (NEB) simulations of surface diffusion and reactions, achieving 3-10 times acceleration compared to pure ab initio calculations. The source code is available at https://github.com/MaterSim/GPR_calculator.

Gaussian process regression↗

DOE OSTI2020

Active Learning for Anomaly Detection in Environmental data

Due to the growing amount of data from in-situ sensors in environmental monitoring, it becomes necessary to automatically detect anomalous data points. Nowadays, this is mainly performed using supervised machine learning models, which need a fully labelled data set for their training process. However, the process of labelling data is typically cumbersome and, as a result, a hindrance to the adoption of machine learning methods for automated anomaly detection. In this work, we propose to address this challenge by means of active learning. This method consists of querying the domain expert for the labels of only a selected subset of the full data set. We show that this reduces the time and costs associated to labelling while delivering the same or similar anomaly detection performances. Finally, we also show that machine learning models providing a nonlinear classification boundary are to be recommended for anomaly detection in complex environmental data sets.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2024

A comparative study on deep learning models for condition monitoring of advanced reactor piping systems

Advanced nuclear reactors offer innovative applications due to their portability, reliability, resiliency, and high capacity factors. To operate them on a wider scale, reducing maintenance life-cycle costs while ensuring their integrity is essential. Autonomous operations in advanced nuclear reactors using augmented Digital Twin (DT) technology can serve as a cost-effective solution by increasing awareness about the system’s health. A key component of nuclear DT frameworks is the condition monitoring of safety systems, such as piping-equipment systems, which involves acquiring and monitoring the plant’s sensor data. Here, this research proposes a condition monitoring methodology utilizing deep learning algorithms, such as multilayer perceptions (MLP) and convolutional neural networks (CNNs), to detect degradation and its severity in nuclear piping-equipment systems. Sensor signals are processed to obtain the power spectral density and the Short-Time Fourier transform, and feature extraction methodologies are proposed to develop degradation-sensitive data repositories. The performance of MLP, one-dimensional (1D) CNN, and 2D CNN within the proposed condition monitoring framework is compared using a finite element model of a 3D piping system subjected to seismic loads as the application case study. Various approaches, such as dropout, k-Fold validation, regularization, and early stopping of training the network, are investigated to avoid overfitting the models to the input sensor data. The predictive capability and computational capacity of the deep learning algorithms are also compared to detect degradation in the Z-pipe system of the Experimental Breeder Reactor II (EBRII). The Z-pipe system is subjected to harmonic excitations that represent normal operating loads, such as pump-induced vibrations. The findings of the study indicate that the proposed artificial intelligence (AI)-driven condition monitoring framework demonstrates superior prediction accuracies with a 2D CNN, whereas the MLP exhibits higher computational efficiency.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2022

Accurate parameterization of the kinetic energy functional for calculations using exact-exchange

In this report, electronic structure calculations based on Kohn-Sham density functional theory (KSDFT) that incorporate exact exchange or hybrid functionals are associated with large computational expense, a consequence of the inherent cubic scaling bottleneck and large associated prefactor, which limits the length and time scales that can be accessed. Though orbital-free density functional theory (OFDFT) calculations scale linearly with system size and are associated with significantly smaller prefactor, they are limited by the absence of accurate density-dependent kinetic energy functionals. Therefore, the development of accurate density-dependent kinetic energy functionals is important for OFDFT calculations of large realistic systems. To this end, we propose a method to train kinetic energy functional models at the exact-exchange level of theory by using a dictionary of physically relevant terms that have been proposed in the literature in conjunction with linear or nonlinear regression methods to obtain the fitting coefficients. For our dictionary, we use gradient expansion of the kinetic energy, nonlocal models proposed in the literature and their nonlinear combinations, such as a model that incorporates spatial correlations between higher order derivatives of electron density at two points. The predictive capabilities of these models are assessed by using a variety of model one-dimensional systems that exhibit diverse bonding characteristics, such as a chain of eight hydrogens, LiF, LiH, C 4 H 2 , C 4 N 2 and C 3 O 2 . We show that by using data from model one-dimensional KSDFT calculations performed using the exact-exchange functional for only a few neutral structures, it is possible to generate models with high accuracy for charged systems as well as electron and kinetic energy densities during self-consistent field iterations. In addition, we show that it possible to learn both the orbital dependent terms, i.e., the kinetic energy and the exact-exchange energy, and models that incorporate additional nonlinearities in spatial correlations, such as a quadratic model, are needed to capture subtle features of the kinetic energy density that are present in exact-exchange-based KSDFT calculations.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

DOE OSTI2024

PSInet: a new global water potential network

Abstract Given the pressing challenges posed by climate change, it is crucial to develop a deeper understanding of the impacts of escalating drought and heat stress on terrestrial ecosystems and the vital services they offer. Soil and plant water potential play a pivotal role in governing the dynamics of water within ecosystems and exert direct control over plant function and mortality risk during periods of ecological stress. However, existing observations of water potential suffer from significant limitations, including their sporadic and discontinuous nature, inconsistent representation of relevant spatio-temporal scales and numerous methodological challenges. These limitations hinder the comprehensive and synthetic research needed to enhance our conceptual understanding and predictive models of plant function and survival under limited moisture availability. In this article, we present PSInet (PSI—for the Greek letter Ψ used to denote water potential), a novel collaborative network of researchers and data, designed to bridge the current critical information gap in water potential data. The primary objectives of PSInet are as follows. (i) Establishing the first openly accessible global database for time series of plant and soil water potential measurements, while providing important linkages with other relevant observation networks. (ii) Fostering an inclusive and diverse collaborative environment for all scientists studying water potential in various stages of their careers. (iii) Standardizing methodologies, processing and interpretation of water potential data through the engagement of a global community of scientists, facilitated by the dissemination of standardized protocols, best practices and early career training opportunities. (iv) Facilitating the use of the PSInet database for synthesizing knowledge and addressing prominent gaps in our understanding of plants’ physiological responses to various environmental stressors. The PSInet initiative is integral to meeting the fundamental research challenge of discerning which plant species will thrive and which will be vulnerable in a world undergoing rapid warming and increasing aridification.

Forestry↗

DOE OSTI2023

A Deep Learning-Based Workflow for Fast Prediction of 3D State Variables in Geological Carbon Storage: A Dimension Reduction Approach

In this study, we used deep learning techniques, which are a form of artificial intelligence, to create fast and effective models for predicting how fluids flow in underground geological formations. This is important for managing geological carbon storage, a method used to fight climate change by storing carbon dioxide underground. The challenge lies in the complex nature of these underground spaces and the large amount of data needed to accurately simulate them. To overcome these issues, we developed a new workflow that reduces the data’s complexity before training the deep learning model and then reconstructs the predicted results in their original form. We also proposed a unique approach to handle the specific complexities found in 3D saturation fields, a crucial aspect of fluid flow prediction. We tested our method using real-world data from the Gulf of Mexico. Our results show that our approach not only accurately predicts fluid behavior but also significantly reduces computation time. This will greatly improve real-time decision-making and risk assessment in large-scale geological carbon storage operations.

Wang, Hongsheng↗

DOE OSTI2023

A Machine Learning–Based Approach to Time-series Wave Identification in the Solar Wind

The Wind spacecraft has yielded several decades of high-resolution magnetic field data, a large fraction of which displays small-scale structures. In particular, the solar wind is full of wavelike fluctuations that appear in both the field magnitude and its components. The nature of these fluctuations can be tied to the properties of other structures in the solar wind, such as shocks, that have implications for the time evolution of the solar wind. As such, having a large collection of wave events would facilitate further study of the effects that these fluctuations have on solar wind evolution. Given the large volume of magnetic field data available, machine learning is the most practical approach to classifying the myriad small-scale structures observed. To this end, a subset of Wind data is labeled and used as a training set for a multibranch 1D convolutional neural network aimed at classifying circularly polarized wave modes. Using this algorithm, a preliminary statistical study of 1 yr of data is performed, yielding about 300,000 wave intervals out of about 5,000,000 solar wind intervals. The wave intervals come about more often in the fast solar wind and at higher temperatures, and the number of waves per day is highly periodic. This machine learning–based approach to wave detection has the potential to be a powerful, inexpensive way to catalog waves throughout decades of spacecraft data.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2020

Real-time Intrusion Detection for High-bandwidth Research Networks using Unsupervised Deep Learning

Nowadays, data generated by large-scale scientific experiments are on the scale of petabytes per month. These data are transferred through dedicated high-bandwidth networks across distributed collaboration sites for processing, storage, and analysis. Like general purpose networks, research networks experience attacks. However, monitoring traffic in such high-bandwidth network environments is challenging with conventional deep packet inspection (DPI)- based network intrusion detection systems (NIDS). Recently, machine learning (ML) algorithms have shown potential in detecting anomalous patterns with better generalizability and faster speed. Compared to the general purpose networks, traffic movement in research network is less volatile and more likely to benefit from the ML-based anomaly analysis. We present ThunderSecure, an efficient AI-powered system for detecting anomalies in 100G research networks. ThunderSecure implements a high-throughput packet processing infrastructure using multi-cores and GPUs. It takes time-series statistics from a variety of network measurements and uses 2D Convolutional Neural Network (CNN) to explore both spatial and temporal dependencies in network data stream. Patterns of science data traffic are learned with a one-class neural network, which blends an Adversarial Autoencoder (AAE) with Gaussian mixture density estimation. Testing traffic flows exhibiting significant deviations from the learned baseline of normality are marked as anomalies. We trained ThunderSecure on hundreds of billions of science data packets recorded from a 100G research network at Fermi National Accelerator Laboratory. The detection performance was evaluated on traffic captured from the same research network days and weeks after the training with different types of attack flows injected. To the best of our knowledge, this is the first ML work in the area of network anomaly detection that has been validated on such extreme scale datasets. Results show that ThunderSecure can recognize science data traffic that are captured long after the training and make nearly certain detection on those with anomalous flows injected, even in the case when the anomaly-to-normal mixing ratio is 0.1%.

Gong, Qian↗

DOE OSTI2021

Systems and methods for real-time data processing and for emergency planning

Systems and methods are described herein for real-time data processing and for emergency planning. Scenario test data may be collected in real-time based on monitoring local or regional data to ascertain any anomaly phenomenon that may indicate an imminent danger or of concern. A computer-implemented method may include filtering a plurality of different test scenarios to identify a sub-set of test scenarios from the plurality of different test scenarios that may have similar behavior characteristics. A sub-set of test scenarios is provided to a trained neural network to identify one or more sub-set of test scenarios. The one or more identified sub-set of test scenarios may correspond to one or more anomaly test scenarios from the sub-set of test scenarios that is most likely to lead to an undesirable outcome. The neural network may be one of: a conventional neural network and a modular neural network.

Yilmaz, Alper↗

DOE OSTI2023

Systems and methods for real-time data processing and for emergency planning

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2019

Runtime Concurrency Control and Operation Scheduling for High Performance Neural Network Training

In this paper, we extend an existing runtime system (the TensorFlow runtime) to enable automatic concurrency control and scheduling of operations. We explore performance modeling to predict the performance of operations with various thread- level parallelism. Our performance model is highly accurate and lightweight. Leveraging the performance model, our runtime system employs a set of scheduling strategies that co-run opera- tions to improve hardware utilization and system throughput. Our runtime system demonstrates a significant performance benefit. Comparing with using the recommended configurations for concurrency control and operation scheduling in TensorFlow, our approach achieves 36% performance (execution time) im- provement on average (up to 49%) for four neural network models, and achieves high performance close to the optimal one manually obtained by the user.

Liu, Jiawen↗

DOE OSTI2021

Model-Free Voltage Control of Active Distribution System with PVs Using Surrogate Model-Based Deep Reinforcement Learning

Accurate knowledge of the distribution system topology and parameters is required to achieve good voltage control performance, but this is difficult to obtain in practice. This paper proposes a physical-model-free voltage control method based on a surrogate-model-enabled deep reinforcement learning approach. Specifically, a surrogate model is trained in a supervised manner using the recorded limited number of historical data to learn the relationship between the power injections and voltage fluctuations of each node. Then, the deep reinforcement learning algorithm is applied to learn an optimal control strategy from the experiences obtained by continuous interactions with the surrogate model. The proposed method can achieve physical-model-free control of unbalanced distribution network and inform real-time decisions to deal with fast voltage fluctuations caused by the rapid variation of PV generation. Simulation results on an unbalance IEEE 123-bus system show that the proposed method can achieve similar performance as that of perfect physical-model-based approaches while being advantageous over other traditional methods.

active distribution network↗

DOE OSTI2020

Predicting demand for hydrogen station fueling

Full function hydrogen stations are a reality; fuel cell electric vehicle drivers can pull up to commercial fueling stations and receive 3–5 kg in less than 5 min, for an approximately 300-mile range. The demand for hydrogen is increasing, driven by an increase in the fueling of public and private fuel cell vehicles. This study describes the development and value of a model that simulates stochastic future demand at a hydrogen filling station. The predictive hydrogen demand model described in this article is trained from mathematical models constructed from actual hydrogen fill count, amount, and frequency data. Future fill probabilities inform the hour-by-hour demand profile and the station state of either “available, ready to fill” or “available, filling”. For example, a prediction for a station generally dispensing 5,000 kg a week on a Friday afternoon at 4 p.m. is 16 fills, totaling 48.7 kg, with a 0.52 proportion of time spent in “available, filling” state yielding 31 min of filling time. This is a first-of-its kind, published study on predicting future hydrogen demand by the time of day (e.g., hour-by-hour intervals) and day of week. This study can be used for hydrogen station requirements and operation and maintenance strategies and to assess the impact of demand variations and scenarios. Finally, this article presents the current status of hydrogen demand, the model development methods, a set of sample results. Discussion and conclusions concentrate on the value and use of the proposed model.

08 HYDROGEN↗

DOE OSTI2023

Dynamic optical spectroscopy and pyrometry of static targets under optical and x-ray laser heating at the European XFEL

Experiments accessing extreme conditions at x-ray free electron lasers (XFELs) involve rapidly evolving conditions of temperature. Here, we report time-resolved, direct measurements of temperature using spectral streaked optical pyrometry of x-ray and optical laser-heated states at the High Energy Density instrument of the European XFEL. This collection of typical experiments, coupled with numerical models, outlines the reliability, precision, and meaning of time dependent temperature measurements using optical emission at XFEL sources. Dynamic temperatures above 1500 K are measured continuously from spectrally- and temporally-resolved thermal emission at 450–850 nm, with time resolution down to 10–100 ns for 1–200 μs streak camera windows, using single shot and integrated modes. Targets include zero-pressure foils free-standing in air and in vacuo, and high-pressure samples compressed in diamond anvil cell multi-layer targets. Radiation sources used are 20-fs hard x-ray laser pulses at 17.8 keV, in single pulses or 2.26 MHz pulse trains of up to 30 pulses, and 250-ns infrared laser single pulses. A range of further possibilities for optical measurements of visible light in x-ray laser experiments using streak optical spectroscopy are also explored, including for the study of x-ray induced optical fluorescence, which often appears as background in thermal radiation measurements. We establish several scenarios where combined emissions from multiple sources are observed and discuss their interpretation. Challenges posed by using x-ray lasers as non-invasive probes of the sample state are addressed.

47 OTHER INSTRUMENTATION↗

DOE OSTI2022

Computer Model Calibration with Time Series Data Using Deep Learning and Quantile Regression

Computer models play a key role in many scientific and engineering problems. One major source of uncertainty in computer model experiments is input parameter uncertainty. Computer model calibration is a formal statistical procedure to infer input parameters by combining information from model runs and observational data. The existing standard calibration framework suffers from inferential issues when the model output and observational data are high-dimensional dependent data, such as large time series, due to the difficulty in building an emulator and the nonidentifiability between effects from input parameters and data-model discrepancy. To overcome these challenges, we, in this work, propose a new calibration framework based on a deep neural network (DNN) with long short-term memory layers that directly emulates the inverse relationship between the model output and input parameters. Adopting the “learning with noise” idea, we train our DNN model to filter out the effects from data-model discrepancy on input parameter inference. We also formulate a new way to construct interval predictions for DNN using quantile regression to quantify the uncertainty in input parameter estimates. Through a simulation study and real data application with the Weather Research and Forecasting Model Hydrological modeling system (WRF-Hydro), we show our approach can yield accurate point estimates and well-calibrated interval estimates for input parameters.

97 MATHEMATICS AND COMPUTING↗