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 1,189 records · Page 66

All sources NASA NTRS DOE OSTI

DOE OSTI2022

Predictability and empirical dynamics of fisheries time series in the North Pacific

Previous studies have documented a strong relationship between marine ecosystems and large-scale modes of sea surface height (SSH) and sea surface temperature (SST) variability in the North Pacific such as the Pacific Decadal Oscillation and the North Pacific Gyre Oscillation. In the central and western North Pacific along the Kuroshio-Oyashio Extension (KOE), the expression of these modes in SSH and SST is linked to the propagation of long oceanic Rossby waves, which extend the predictability of the climate system to ~3 years. Using a multivariate physical-biological linear inverse model (LIM) we explore the extent to which this physical predictability leads to multi-year prediction of dominant fishery indicators inferred from three datasets (i.e., estimated biomasses, landings, and catches). We find that despite the strong autocorrelation in the fish indicators, the LIM adds dynamical forecast skill beyond persistence up to 5-6 years. By performing a sensitivity analysis of the LIM forecast model, we find that two main factors are essential for extending the dynamical predictability of the fishery indicators beyond persistence. The first is the interaction of the fishery indicators with the SST/SSH of the North and tropical Pacific. The second is the empirical relationship among the fisheries time series. This latter component reflects stock-stock interactions as well as common technological and human socioeconomic factors that may influence multiple fisheries and are captured in the training of the LIM. These results suggest that empirical dynamical models and machine learning algorithms, such as the LIM, provide an alternative and promising approach for forecasting key ecological indicators beyond the skill of persistence.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2024

AI in Science Communication

Generative AI has brought great innovations across multiple fields, offering great tools for enhanced communication and efficiency. This project focused on developing a custom AI chatbot using OpenAI's Chat GPT (GPT-4o) to support the Fermilab communications team. An analysis identified Chat GPT as the optimal choice, leading to the adoption of its team version and the implementation of a real-time JSON schema for website scanning. Four distinct personas were created to tailor responses to specific audiences, and Fermilab's published content was uploaded to ensure tone consistency. The training involved iterative prompt trials, resulting in a responsive and effective communication assistant. Initial evaluations indicate that the custom GPT shows promise.

Valle, Diego↗

DOE OSTI2025

Machine Learning for Well Log Analysis in Uranium Mining

This project explores the use of Artificial Intelligence (AI) and Machine Learning (ML) techniques to automate well log analysis for uranium mining. Geophysical log data—spontaneous potential, resistivity, and gamma ray—were used to classify lithology, correlate well logs and identify roll front zonation patterns, which are critical for locating uranium ore bodies. Supervised ML algorithms such as eXtreme Gradient Boosting (XGBoost), Categorical Boosting (CatBoost), and Random Forest were trained to classify lithology with high accuracy. Gradient Boosting Machines (GBM), XGBoost, Random Forest, and Neural Networks were also used for role front zone identification. Moreover, a Fast Dynamic Time Warping (FastDTW) algorithm was employed for well log correlation. Additionally, sample lag was addressed using dynamic programming. Results demonstrate the potential of AI and ML to streamline well log analysis and enhance uranium exploration workflows.

11 - NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

DOE OSTI2021

Development of Automated Pipeline for Time-Resolved Link-Wise Vehicular Energy Consumption in the Chattanooga, TN Road Network

The Department of Energy (DOE) has shown strong interest in detecting energy inefficiencies in regional road networks, so as to derive energy consumed at a high spatial temporal resolution. We have developed a workflow to automate the estimation of time-resolved vehicular energy consumption over each link in a road network of interest. The road network used in the current work is centered around the city of Chattanooga, Tennessee and its bordering regions. Utilizing the most mature road network for the Chattanooga, TN region, vehicle speed & count data from TomTom in conjunction with machine learning methods, we have developed an automated pipeline to estimate energy consumption for every link in the network. The first step in the pipeline is ingesting vehicle probe counts and speed estimates from TomTom API. In the next step, the probe counts, speed profiles and other exogenous data (i.e. road types, weather data, ground-truth volume counts and more) were used as input to a supervised learning algorithm to estimate the number of vehicles throughout the entire region for each road segment. These volume estimates were then mapped to a unified road network that contained additional important information such as percentage change in gradient across a link, number of lanes and link lengths that are features in pre-trained single vehicle energy-consumption models available with the RouteE software developed at NREL. The per vehicle energy consumption on each road link predicted using appropriate RouteE vehicular models were multiplied by the volume estimate for the corresponding link over a given time period to predict energy consumed per link for the time interval of interest. Currently, work is underway to improve both the RouteE per vehicle energy estimate and the volume estimates derived from TomTom probe counts. We have also explored the correlation of the link-wise energy estimates with the features of the pre-trained RouteE machine learning model in order to gain insight into what factors contribute most to the link-wise energy consumption.

ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION,↗

DOE OSTI2020

PANTHER: A Programmable Architecture for Neural Network Training Harnessing Energy-Efficient ReRAM

The wide adoption of deep neural networks has been accompanied by ever-increasing energy and performance demands due to the expensive nature of training them. Additionally, numerous special-purpose architectures have been proposed to accelerate training: both digital and hybrid digital-analog using resistive RAM (ReRAM) crossbars. ReRAM-based accelerators have demonstrated the effectiveness of ReRAM crossbars at performing matrix-vector multiplication operations that are prevalent in training. However, they still suffer from inefficiency due to the use of serial reads and writes for performing the weight gradient and update step. A few works have demonstrated the possibility of performing outer products in crossbars, which can be used to realize the weight gradient and update step without the use of serial reads and writes. However, these works have been limited to low precision operations which are not sufficient for typical training workloads. Moreover, they have been confined to a limited set of training algorithms for fully-connected layers only. To address these limitations, we propose a bit-slicing technique for enhancing the precision of ReRAM-based outer products, which is substantially different from bit-slicing for matrix-vector multiplication only. We incorporate this technique into a crossbar architecture with three variants catered to different training algorithms. To evaluate our design on different types of layers in neural networks (fully-connected, convolutional, etc.) and training algorithms, we develop PANTHER, an ISA-programmable training accelerator with compiler support. Our design can also be integrated into other accelerators in the literature to enhance their efficiency. Our evaluation shows that PANTHER achieves up to 8.02×, 54.21×, and 103× energy reductions as well as 7.16×, 4.02×, and 16× execution time reductions compared to digital accelerators, ReRAM-based accelerators, and GPUs, respectively.

42 ENGINEERING↗

DOE OSTI2025

Creation of an Fe 3 P Schreibersite Density Functional Tight Binding Model for Astrobiological Simulations

The mineral schreibersite, e.g., Fe 3 P, is commonly found in iron-rich meteorites and could have served as an abiotic phosphorus source for prebiotic chemistry. However, atomistic calculations of its degradation chemistry generally require quantum simulation approaches, which can be too computationally cumbersome to study sufficient time and length scales for this process. In this regard, we have created a computationally efficient semiempirical quantum density functional tight binding (DFTB) model for iron and phosphorus-containing materials by adopting an existing semiautomated workflow that represents many-body interactions by linear combinations of Chebyshev polynomials. Here, we have utilized a relatively small training set to optimize a DFTB model that is accurate for schreibersite physical and chemical properties, including its bulk properties, surface energies, and water absorption. We then show that our model shows strong transferability to several iron phosphide solids as well as multiple allotropes of iron metal. Our resulting DFTB parametrization will allow us to interrogate schreibersite aqueous decomposition at longer time and length scales than standard quantum approaches, providing for more detailed investigations of its role in prebiotic chemistry on early Earth.

36 MATERIALS SCIENCE↗

DOE OSTI2023

Digital holography for real-time non-invasive monitoring of larval fish at power plant intakes

Effective evaluation of technological and operational approaches to reduce entrainment of marine organisms at cooling water intake structures (CWIS) requires accurate organism-sensing systems. Current detection methods lead to large temporal data gaps, require tedious manual analysis, and are fatal to organisms. In this report we describe integrating deep learning with a non-lethal, non-intrusive imaging method—digital holography—to rapidly detect fish larvae. Laboratory experiments demonstrated that the instrument could successfully image fish larvae at flow rates exceeding ranges seen in CWIS. Holograms of two fish larvae species, in the presence of bubbles and detritus, were collected to build a large database for training a lightweight convolutional neural network. The model achieves 97% extraction accuracy in quantifying larvae, and distinguishing them from other particles, including detritus and bubbles, when applied to a dataset of manually classified images, exceeding previous metrics for non-lethal, accurate, and real-time detection. These results demonstrate the potential of in situ holographic imaging for monitoring endangered larval fish species at power plant intake structures, and for high-fidelity, real-time applications in monitoring aquatic ichthyoplankton.

endangered species↗

DOE OSTI2024

Enabling the broader adoption of fusion simulation on complex geometry

This project addressed a key barrier to advanced fusion and nuclear simulation: the difficulty of performing high-fidelity Monte Carlo neutronics directly on complex, real-world CAD geometry. Traditional workflows require engineers to rebuild CAD models as simplified constructive solid geometry, a time-consuming and error-prone process that limits design iteration and broader adoption of simulation tools. The goal of this Phase I SBIR was to make CAD-based neutronics practical, accessible, and robust for industrial and research users. During the project, Coreform significantly enhanced the Direct Accelerated Geometry Monte Carlo (DAGMC) workflow and fully integrated it into Coreform Cubit as a first-class capability. Major achievements include optimized material assignment and surface meshing workflows, substantial performance improvements to geometry imprinting and preparation, native export of DAGMC models, and new visualization tools to support OpenMC source definition and lost-particle debugging. Coreform also expanded Cubit’s capabilities as a full OpenMC preprocessor, including the ability to convert OpenMC constructive solid geometry models back into CAD for visualization, multiphysics coupling, and debugging. In collaboration with Argonne National Laboratory, the project delivered comprehensive new DAGMC documentation and training materials, transforming DAGMC from a research-oriented tool into a production-ready workflow. Results were disseminated through tutorials, conference training, and multiple well-attended webinars demonstrating integrated CAD-based neutronics and multiphysics workflows. Overall, this project demonstrated that high-fidelity Monte Carlo simulations can be performed directly on complex CAD geometry, reducing setup time, improving usability, and enabling faster, more informed design decisions for fusion and nuclear energy systems.

42 ENGINEERING↗

DOE OSTI2021

Individual Wave Detection and Tracking within a Rotating Detonation Engine through Computer Vision Object Detection applied to High-Speed Images

Known for their simplistic design and continuous detonation, rotating detonation engines (RDEs) constitute a majority of current pressure gain combustion (PGC) research efforts. Experimental RDE operation times have been continuously extended through the use of rig cooling techniques. As the window of observable behavior is expanded, and as the technology matures toward eventual integration within gas turbines, monitoring techniques must evolve to better match industrial diagnostics. High-speed image analysis techniques prove useful to capture and evaluate the unsteady detonation behavior within the RDE. Traditional image analysis techniques, however, require extensive processing times which prohibit simultaneous monitoring. To better address this problem, a computer vision object detection methodology is proposed to quickly detect individual detonation waves within a single down-axis image. Detonation waves are detected in individual images by the implemented computer vision method You Only Look Once (YOLO) object detection network. In order to detect detonation waves, the network must first be trained using RDE images of interest, for which each required phase of network development is outlined. Detection of waves is improved through proper treatment of the collected image set, variation of Intersection over Union (IoU) and confidence thresholding, and through a parametric study of annotation dimensions. Each detected wave is described by its location and rotational direction, and locations are tracked to calculate wave velocity across each frame, leading to a timestep resolution of 20 µs. Wave velocities are also calculated through a series of frames, leading to a suitable average velocity estimation using as few as 10 frames. Uncertainty analysis accounting for variation in camera framerate, pixel width and annotation centroid locations estimates a total uncertainty of ±4.3% for velocity calculations, using the smallest annotation boxes. This method offers great reductions in processing times, as a step toward real-time monitoring of detonation waves within an RDE. Improving on previous studies, this technique is impartial to wave modes not included in the original training set and calculates wave velocities independent of high-speed pressure data. The ability to isolate waves within predicted bounding boxes will likely facilitate analysis of pixel intensity variation as an estimation of wave strength in future work.

Johnson, Kristyn↗

DOE OSTI2021

Individual Wave Detection and Tracking within a Rotating Detonation Engine through Computer Vision Object Detection applied to High-Speed Images

Johnson, Kristyn↗

DOE OSTI2022

Classification and Localization of Fracture-Hit Events in Low-Frequency Distributed Acoustic Sensing Strain Rate with Convolutional Neural Networks

Summary Distributed acoustic sensing (DAS) has been used in the oil and gas industry as an advanced technology for surveillance and diagnostics. Operators use DAS to monitor hydraulic fracturing activities, examine well stimulation efficacy, and estimate complex fracture system geometries. Particularly, low-frequency DAS can detect geomechanical events such as fracture hits because hydraulic fractures propagate and create strain rate variations in the rock. Analysis of DAS data today is mostly done post-job and subject to interpretation methods. However, the continuous and dense data stream generated live by DAS poses the opportunity for more efficient and accurate real-time data-driven analysis. The objective of this study is to develop a machine learning-based workflow that can identify and locate fracture-hit events in simulated strain rate responses correlated with low-frequency DAS data. In this paper, “fracture hit” refers to a hydraulic fracture originating from a stimulated well intersecting an offset well. We start with building a single fracture propagation model to produce strain rate patterns observed at a hypothetical monitoring well. This model is used to generate two sets of strain rate responses with one set containing fracture-hit events. The labeled synthetic data are then used to train a custom convolutional neural network (CNN) model for identifying the presence of fracture-hit events. The same model is trained again for locating the event with the output layer of the model replaced with linear units. We achieved near-perfect predictions for both event classification and localization. These promising results prove the feasibility of using CNN for real-time event detection from fiber-optic sensing data. Additionally, we use edge detection techniques to recognize fracture-hit event patterns in strain rate images. The fracture-hit location can be identified using recognized pixels in the image. The accuracy of edge detection-based location identification is also plausible, but edge detection is dependent on the assumption of pattern shape and image quality, hence it is less robust compared to CNN models. This comparison further supports the need for CNN applications in image-based real-time fiber-optic sensing event detection.

Engineering↗

DOE OSTI2022

Machine-Learning Accelerated Studies of Materials with High Performance and Edge Computing

In the studies of materials, experimental measurements often serve as the reference to verify physics theory and modeling; while theory and modeling provide a fundamental understanding of the physics and principles behind. However, the interactions and cross validation between them have long been a challenge even to-date. Not only that inferring a physics model from experimental data is itself a difficult inverse problem, another major challenge is the orders-of-magnitude longer wall-clock time required to carry out high-fidelity computer modeling to match the timescale of experiments. We envisage that by combining high performance computing, data science, and edge computing technology, the current predicament can be alleviated, and a new paradigm of data-driven physics research will open up. For example, we can accelerate computer simulations by first performing the large-scale modeling on high performance computers and train a machine-learned surrogate model. This computationally inexpensive surrogate model can then be transferred to the computing units residing closely to the experimental facilities to perform high-fidelity simulations at a much higher throughout. The model will also be more amenable to analyzing and validating experimental observations in comparable time scales at a much lower computational cost. Further integration of these accelerated computer simulations with an outer machine learning loop can also inform and direct future experiments, while making the inverse problem of physics model inference more tractable. We will demonstrate a proof-of-concept by using a quantum Monte Carlo application, Dynamical Cluster Approximation (DCA++), to machine-learn a surrogate model and accelerate the study of quantum correlated materials.

Li, Ying Wai↗

DOE OSTI2025

Enhancing Short-Range Weather Forecasts through Temporal Variation Encoding: A Multiperiod Embedding Approach

Machine learning (ML) techniques have emerged as promising approaches to improve regional weather forecast accuracy and reliability through data-driven methods. We propose a novel ML-based weather forecasting model, the Multiperiod Embed Net (MPENet). A key distinguishing feature of MPENet is its explicit utilization of the inherent cyclic nature in weather dynamics, unlike the autoregressive strategies commonly used in other ML weather forecasting approaches. Critical cyclic structures are identified via Fourier analyses of dynamic time series. Cyclicity in the convolutional representation is achieved by transforming one-dimensional time series of meteorological variables into two-dimensional tensors based on identified periods. This approach enables the model to leverage intrinsic weather patterns, enhancing regional forecast performance. To demonstrate the effectiveness of MPENet, we conduct a comparative analysis with Nvidia’s FourCastNet. Both models are trained on High-Resolution Rapid Refresh (HRRR) data from 2015 to 2022, over a 192 km × 192 km region in Tennessee. The comparisons are performed locally at two specific locations known to have different weather dynamics due to orographic effects: Crossville, on the relatively flat Cumberland Plateau with fewer topographic airflow disruptions, and Oak Ridge, in the ridge-and-valley region, where airflow is heavily influenced by surrounding valleys and mountains. Our results indicate that FourCastNet achieves strong accuracy at very short lead times, while MPENet maintains competitive skill and shows advantages in capturing temporal evolution over longer periods. Cross-correlation analyses of MPENet and FourCastNet predictions with the HRRR data suggest that encoding critical cyclicity into the network architecture leads to improvements in the forecasting skill.

Artificial intelligence↗

DOE OSTI2022

Post-hazard condition assessment of nuclear piping-equipment systems: Novel approach to feature extraction and deep learning

Over the past decade, the use of artificial intelligence techniques in the field of health-monitoring has gained significant interest, especially for structures such as building and bridges. However, applications to industrial systems such as equipment-piping systems in nuclear plants have not been explored. Here, in this paper, it is shown that the existing techniques developed for buildings and bridges cannot be extended directly to equipment-piping systems as the response of such systems is governed by multiple localized modes unlike that in buildings and bridges. This paper proposes a new approach that consists of three key aspects: (i) a novel vector of degradation-sensitive features extracted from measured data, (ii) using a deep Artificial Neural Network (ANN) for diagnosis of degradation location and degradation severity, and (iii) consideration of uncertainty in degradation severity when training the ANN. Degradation in piping-equipment systems can occur due to flow-accelerated erosion and corrosion. These locations can potentially exhibit damage such as localized yielding or initiation of cracking due to an external event such as an earthquake. Moreover, such locations can at times go undetected by current inspection techniques. Therefore, a robust framework is needed for detection of degradation after a seismic event. This manuscript proposes a proof-of-concept framework, which utilizes data collected from sensors to generate a deep ANN database for predicting degraded locations and severity in a piping-equipment system. Degradation severity is classified as minor, moderate, and severe. In the suggested methodology, a novel vector of degradation-sensitive features is extracted from the sensor data to train the ANN. A simple piping-equipment system is selected to demonstrate feature extraction as a means to simplify pattern recognition, explore the design and parameters of an ANN, and develop a sensor placement strategy. The effectiveness of the proposed framework is demonstrated on a realistic primary safety system of a two-loop nuclear reactor. It is shown that the proposed post-hazard condition assessment framework is able to detect degraded locations along with the severity levels, including minor degradation, with considerably higher accuracy.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2024

Condition-Based Maintenance of a Circulating Water System of a Canadian Nuclear Power Plant using Machine Learning and Statistical Tools

Canada Deuterium Uranium pressurized-heavy-water reactors (PHWR) are a type of nuclear power plant that generate clean and reliable energy. The scope of this work is to automate data analysis methodologies to inform a condition-based maintenance strategy of a circulating water system (CWS) of a PHWR. The multiunit CWS provides a continuous supply of water to cool steam condensers, even during transient scenarios, thereby improving the thermal efficiency. This work aims to develop a machine learning (ML) based approach to detect anomalies in heterogeneous data of a CWS in a PHWR to help inform a predictive maintenance strategy. The heterogeneous data include textual and numeric time series data for a PHWR. Natural-language-processing (NLP)-based models are used to analyze textual data contained in work orders and operator logs and an event-timeseries correlation detection method is applied to assist anomalies diagnoses for CWS. An ML model Robust Linear Model (RLM) is also used to remove the seasonal variations in the system variable distributions based on distributions of environmental variables. A machine learning model, Density-Based Spatial Clustering of Applications with Noise (DBSCAN), trained on both original data and data without any seasonal variations will then be used to detect if an anomaly exists. Thus, by moving to an automated methodology to detect, classify, and forecast anomalies, the maintenance strategy would be based on component condition instead of a time-based schedule.

97 - MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Physics-Informed Active Learning With Simultaneous Weak-Form Latent Space Dynamics Identification

The parametric greedy latent space dynamics identification (gLaSDI) framework has demonstrated promising potential for accurate and efficient modeling of high-dimensional nonlinear physical systems. However, it remains challenging to handle noisy data. Here, to enhance robustness against noise, we incorporate the weak-form estimation of nonlinear dynamics (WENDy) into gLaSDI. In the proposed weak-form gLaSDI (WgLaSDI) framework, an autoencoder and WENDy are trained simultaneously to discover intrinsic nonlinear latent-space dynamics of high-dimensional data. Compared with the standard sparse identification of nonlinear dynamics (SINDy) employed in gLaSDI, WENDy enables variance reduction and robust latent space discovery, therefore leading to more accurate and efficient reduced-order modeling. Furthermore, the greedy physics-informed active learning in WgLaSDI enables adaptive sampling of optimal training data on the fly for enhanced modeling accuracy. The effectiveness of the proposed framework is demonstrated by modeling various nonlinear dynamical problems, including viscous and inviscid Burgers' equations, time-dependent radial advection, and the Vlasov equation for plasma physics. With data that contains 5%–10% Gaussian white noise, WgLaSDI outperforms gLaSDI by orders of magnitude, achieving 1%–7% relative errors. Compared with the high-fidelity models, WgLaSDI achieves 121 to 1779x speed-up.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Solving high-dimensional inverse problems using amortized likelihood-free inference with noisy and incomplete data

Here, we present a likelihood-free probabilistic inversion method based on normalizing flows for high-dimensional inverse problems. The proposed method is composed of two complementary networks: a summary network for data compression and an inference network for parameter estimation. The summary network encodes raw observations into a fixed-size vector of summary features, while the inference network generates samples of the approximate posterior distribution of the model parameters based on these summary features. The posterior samples are produced in a deep generative fashion by sampling from a latent Gaussian distribution and passing these samples through an invertible transformation. We construct this invertible transformation by sequentially alternating conditional invertible neural network and conditional neural spline flow layers. The summary and inference networks are trained simultaneously. We apply the proposed method to an inversion problem in groundwater hydrology to estimate the posterior distribution of the log-conductivity field conditioned on spatially sparse time-series observations of the system’s hydraulic head responses. The conductivity field is represented with 706 degrees of freedom in the considered problem. Comparison with the likelihood-based iterative ensemble smoother PEST-IES method demonstrates that the proposed method accurately estimates the parameter posterior distribution and the observations’ predictive posterior distribution at a fraction of the inference time of PEST-IES.

conditional invertible neural network↗

DOE OSTI2022

Time series anomaly detection in power electronics signals with recurrent and ConvLSTM autoencoders

The anomalies in the high voltage converter modulator (HVCM) remain a major down time for the spallation neutron source facility, that delivers the most intense neutron beam in the world for scientific materials research. In this work, we propose neural network architectures based on Recurrent AutoEncoders (RAE) to detect anomalies ahead of time in the power signals coming from the HVCM. Bi-directional gated recurrent unit, bi-directional long-short term memory (LSTM), and convolutional LSTM (ConvLSTM) are developed, trained, and tested using real experimental signals from the HVCM module. The results show a good performance of the proposed RAE models, achieving precision up to 91%, recall up to 88%, false omission rate as low as 20% (i.e. 80% of the anomalies were detected), and area under the ROC curve up to 0.9. The three RAE models provide very comparable performance, with LSTM showing slightly better performance than GRU and ConvLSTM. The RAE models are benchmarked against other anomaly detection methods, including isolation forest, support vector machine, local outlier factor, feedforward and convolutional autoencoders, and others; showing a better performance. Here, the results of this study demonstrate the promising potential of RAE in anomaly detection for real-world power systems, and for increasing the reliability of the HVCM modules in the spallation neutron source.

42 ENGINEERING↗