Search NASA⌕ Search

SEARCH · Search NASA

Results for “Time Series Prediction”

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 253 records · Page 14
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

A review of machine learning in building load prediction

The surge of machine learning in recent years has been empowering engineer modeling in various fields. The decreasing hardware cost, increasing data accessibility, and advances of building automation system (BAS) allow the collection and storage of a significant amount of building operation data. The two facts provide great opportunities of applying machine learning to building energy systems modeling and analysis. There are a great number of research papers on this topic but there lacks a comprehensive and general review to summarize the current development, limitations, gaps and future trend. In this review paper series, machine learning techniques in building energy system modeling and analysis are reviewed under the organization and logic of the machine learning definition by Tom M. Mitchell: a computer program is said to learn from experience E with respect to some class of tasks T and performance measure P if its performance at tasks in T, as measured by P, improves with experience E. This paper is the first part of the review paper series, which focuses on building load prediction. First, the applications of building load prediction model (task T) are reviewed. Then, the modeling algorithms improving machine learning performance and accuracy (performance P) are reviewed. At the same time, the literature on the data perspective for modeling (experience E), including data engineering from sensors level to data level, pre-processing, feature extraction and selection, is reviewed. Finally, what is well-studied and what is lacking but with great potential are concluded; the gaps between present and future utilization of machine learning techniques are identified; the future trend and development are also predicted. The target readers of this paper are not only researchers from the building side who can get exposed to cutting edge machine learning tools, but also those from machine learning side who can understand the potential and challenge to apply machine learning in buildings.

Liang, Zhang↗
DOE OSTI2025

Machine Learning for Anomaly Detection in Neural Network Security and SRF Cavities

This dissertation explores the development and deployment of machine learning approaches to address critical challenges in anomaly detection across two distinct domains: neural network security in federated learning settings and cavity behavior analysis in particle accelerator operations at Jefferson Lab in Newport News, Virginia. Anomaly detection identifies deviations from expected patterns, safeguarding systems in cybersecurity, industry, and research against malicious activities and failures. This dissertation demonstrates how our machine learning approaches enhance detection accuracy and efficiency in both neural network security and industrial applications. First, we investigate vulnerabilities in deep neural networks deployed in federated learning. Although federated learning preserves user privacy by training models locally, it remains vulnerable to backdoor attacks, in which malicious participants embed hidden triggers that induce targeted misbehavior. We propose a self-supervised contrastive learning framework to detect and mitigate such backdoor attacks. In our experiments, this method achieves higher detection accuracy and lower false positive rates than existing defenses, while operating without access to local model updates or original training data and thus preserving the privacy guarantees of the federated setting. Second, we address the operational reliability of superconducting radio-frequency (SRF) cavities at the Continuous Electron Beam Accelerator Facility (CEBAF). Our research leverages an unsupervised learning approach, combined with Principal Component Analysis (PCA) and k-means clustering, to identify anomalous behaviors in SRF cavities. Our method detects subtle anomalous behavior by analyzing SRF signal data. This knowledge allows for the early detection and resolution of potential faults, significantly improving the efficiency and reliability of operations. Third, we extend these insights to time-series anomaly detection more broadly. We design a contrastive-learning based model tailored to increasingly dynamic environments and academic research. This model improves detection accuracy in settings that require real-time monitoring and predictive maintenance. Our research underscores the broader applicability and impact of advanced machine learning techniques in anomaly detection. By extracting meaningful patterns from complex data, machine learning can significantly enhance security in distributed neural networks and improve the efficiency of particle accelerator operations. This dissertation serves as a stepping stone for future investigations into the vast possibilities of anomaly detection, inspiring further exploration and development of machine learning techniques in this field.

Ferguson, Hal [Old Dominion University]↗
DOE OSTI2022

Supernova-driven Turbulent Metal Mixing in High-redshift Galactic Disks: Metallicity Fluctuations in the Interstellar Medium and its Imprints on Metal-poor Stars in the Milky Way

The extent to which turbulence mixes gas in the face of recurrent infusions of fresh metals by supernovae (SN) could help provide important constraints on the local star formation conditions. This includes predictions of the metallicity dispersion among metal-poor stars, which suggests that the interstellar medium was not very well mixed at these early times. The purpose of this Letter is to help isolate, via a series of numerical experiments, some of the key processes that regulate turbulent mixing of SN elements in galactic disks. We study the gas interactions in small simulated patches of a galaxy disk with the goal of resolving the small-scale mixing effects of metals at parsec scales, which enables us to measure the turbulent diffusion coefficient in various galaxy environments. By investigating the statistics of variations of α elements in these simulations, we are able to derive constraints not only on the allowed range of intrinsic yield variations in SN explosions but also on the star formation history of the Milky Way. We argue that the observed dispersion of [Mg/Fe] in metal-poor halo stars is compatible with the star-forming conditions expected in dwarf satellites or in an early low-star-forming Milky Way progenitor. In particular, metal variations in stars that have not been phase-mixed can be used to infer the star-forming conditions of disrupted dwarf satellites.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

Data-Driven State of Health Estimation for Second-Life Batteries Using Interpolated Synthetic Data and Feature Selection

Accurate estimation of the State of Health (SOH) for second-life batteries (SLBs) is crucial given their increasing use in energy storage applications. Precise SOH prediction is essential for safe operation and robust battery management systems. A major challenge is the limited availability of datasets for building reliable degradation models. To address this, synthetic data generation through linear interpolation is performed to extend the available data, making it more representative of real-world battery operating conditions. By analyzing feature correlation with SOH, the most relevant features are selected for the model. The proposed approach employs a convolutional neural network (CNN) model trained on this interpolated, feature-selected dataset, using time series data of voltage, temperature, and current over a cycle. By focusing on highly correlated features, the model achieves over 95% accuracy, with mean absolute error and root mean squared error up to 2.27% and 2.64%, respectively, in SOH estimation for two battery datasets tested. These results highlight the potential of combining synthetic data generation and feature selection to enhance SOH predictions, showcasing the superior performance of the proposed CNN model for both new batteries and SLBs.

feature selection↗
DOE OSTI2021

25-Pin metallic fuel performance benchmark case based on the EBR-II X430 experiments series

A metallic fuel benchmark case was developed for the fuel performance code BISON based on 25 uranium-zirconium and uranium-plutonium-zirconium pins of the Experimental Breeder Reactor II X430 experiment series. Results of the benchmarks were compared with measurements and calculations made at the time of the experiment as well as subsequent measurements reported in 2019. The comparisons were used to quantify the accuracy of the BISON predictions and to identify patterns in the BISON differences.BISON predicted burnup, plenum pressure, and fission gas release fractions accurately. BISON temperature predictions were somewhat cooler than the temperatures determined at the time of the experiment but appeared to be reasonably accurate considering uncertainties in the legacy temperature calculations, uncertainties in the legacy linear heat rate calculations, and the high sensitivities of the BISON-predicted temperatures to BISON inputs. Fuel axial elongation predictions had errors correlated to fuel composition; BISON tended to underpredict the elongation of binary fuels and overpredict the elongation of ternary fuels. BISON cladding radial dilation predictions were also significantly lower than legacy PIE measurements.Recommendations were made to improve the BISON fuel gaseous swelling model to account for fuel composition, to add additional capabilities to the coolant channel temperature model to ease benchmark development, and to continue developing benchmark cases based on a wide range of experiments in several reactors. Once a wide array of benchmarks is developed, an attempt can be made to enhance or calibrate BISON models to improve the cladding dilation predictions.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2022

Separating Sensor Anomalies From Process Anomalies in Data-Driven Anomaly Detection

Data-driven anomaly detection over time series data is studied from the perspective of separating data anomalies—corresponding to sensor failures—from process anomalies—that arise from equipment or operational failures. Herein, a semi-supervised approach is proposed that utilizes two predictive models trained on non-anomalous data using two different sensor groups as inputs, and a nested hypothesis test to reliably classify data or process anomalies. Conditions are derived on choice of sensor groups to guarantee reliable detection, and a case study is presented to demonstrate the proposed classification approach.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2021

Subsurface Characterization and Machine Learning Predictions at Brady Hot Springs Results

Geothermal power plants typically show decreasing heat and power production rates over time. Mitigation strategies include optimizing the management of existing wells - increasing or decreasing the fluid flow rates across the wells - and drilling new wells at appropriate locations. The latter is expensive, time-consuming, and subject to many engineering constraints, but the former is a viable mechanism for periodic adjustment of the available fluid allocations. Data and supporting literature from a study describing a new approach combining reservoir modeling and machine learning to produce models that enable strategies for the mitigation of decreased heat and power production rates over time for geothermal power plants. The computational approach used enables translation of sets of potential flow rates for the active wells into reservoir-wide estimates of produced energy and discovery of optimal flow allocations among the studied sets. In our computational experiments, we utilize collections of simulations for a specific reservoir (which capture subsurface characterization and realize history matching) along with machine learning models that predict temperature and pressure timeseries for production wells. We evaluate this approach using an "open-source" reservoir we have constructed that captures many of the characteristics of Brady Hot Springs, a commercially operational geothermal field in Nevada, USA. Selected results from a reservoir model of Brady Hot Springs itself are presented to show successful application to an existing system. In both cases, energy predictions prove to be highly accurate: all observed prediction errors do not exceed 3.68% for temperatures and 4.75% for pressures. In a cumulative energy estimation, we observe prediction errors that are less than 4.04%. A typical reservoir simulation for Brady Hot Springs completes in approximately 4 hours, whereas our machine learning models yield accurate 20-year predictions for temperatures, pressures, and produced energy in 0.9 seconds. This paper aims to demonstrate how the models and techniques from our study can be applied to achieve rapid exploration of controlled parameters and optimization of other geothermal reservoirs. Includes a synthetic, yet realistic, model of a geothermal reservoir, referred to as open-source reservoir (OSR). OSR is a 10-well (4 injection wells and 6 production wells) system that resembles Brady Hot Springs (a commercially operational geothermal field in Nevada, USA) at a high level but has a number of sufficiently modified characteristics (which renders any possible similarity between specific characteristics like temperatures and pressures as purely random). We study OSR through CMG simulations with a wide range of flow allocation scenarios. Includes a dataset with 101 simulated scenarios that cover the period of time between 2020 and 2040 and a link to the published paper about this project, where we focus on the Machine Learning work for predicting OSR's energy production based on the simulation data, as well as a link to the GitHub repository where we have published the code we have developed (please refer to the repository's readme file to see instructions on how to run the code). Additional links are included to associated work led by the USGS to identify geologic factors associated with well productivity in geothermal fields. Below are the high-level steps for applying the same modeling + ML process to other geothermal reservoirs: 1. Develop a geologic model of the geothermal field. The location of faults, upflow zones, aquifers, etc. need to be accounted for as accurately as possible 2. The geologic model needs to be converted to a reservoir model that can be used in a reservoir simulator, such as, for instance, CMG STARS, TETRAD, or FALCON 3. Using native state modeling, the initial temperature and pressure distributions are evaluated, and they become the initial conditions for dynamic reservoir simulations 4....

15 GEOTHERMAL ENERGY↗
DOE OSTI2021

Projecting the number of new HIV infections to formulate the "Getting to Zero" strategy in Illinois, USA

Objectives: Getting to Zero (GTZ) initiatives focus on expanding use of antiretroviral treatment (ART) and pre-exposure prophylaxis (PrEP) to eliminate new HIV infections. Computational models help inform policies for implementation of ART and PrEP continuums. Such models, however, vary in their design, and may yield inconsistent predictions. Using multiple approaches can help assess the consistency in results obtained from varied modeling frameworks, and can inform optimal implementation strategies. Methods: A study using three different modeling approaches is conducted. Two approaches use statistical time series analysis techniques that incorporate temporal HIV incidence data. A third approach uses stochastic stimulation, conducted using an agent-based network model (ABNM). All three approaches are used to project HIV incidence among a key population, young Black MSM (YBMSM), over the course of the GTZ implementation period (2016-2030). Results: All three approaches suggest that simultaneously increasing PrEP and ART uptake is likely to be more effective than increasing only one, but increasing ART and PrEP by 20% points may not eliminate new HIV infections among YBMSM. The results further suggest that a 20% increase in ART is likely to be more effective than a 20% increase in PrEP. All three methods consistently project that increasing ART and PrEP by 30% simultaneously can help reach GTZ goals. Conclusions: Increasing PrEP and ART uptake by about 30% might be necessary to accomplish GTZ goals. Such scale-up may require addressing psychosocial and structural barriers to engagement in HIV and PrEP care continuums. ABNMs and other flexible modeling approaches can be extended to examine specific interventions that address these barriers and may provide important data to guide the successful intervention implementation.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2021

High-dimensional Data-driven Energy optimization for Multi-Modal Transit Agencies (HD-EMMA) (Final Technical Report)

Public bus transit services in the U.S. are responsible for at least 19.7 million metric tons of CO 2 emission annually. Electric vehicles (EVs) can have a much lower environmental impact than comparable internal combustion engine vehicles (ICEVs), especially in urban areas. Unfortunately, EVs are also much more expensive than ICEVs. As a result, many public transit agencies can afford only mixed fleets of transit vehicles, consisting of EVs, hybrids (HEVs), and ICEVs. Transit agencies that operate such mixed fleets of vehicles face a challenging optimization problem: these agencies need to decide which vehicles are assigned to serving which transit trips. Since the advantage of EVs over ICEVs varies depending on the route and time of day (e.g., the benefit of EVs is higher in slower traffic with frequent stops and lower on highways), the assignment can have a significant effect on energy use and, hence, environmental impact. Through this project, we have developed reference data about energy collections and constructed a set of machine learning models that can accurately predict the energy consumption for the whole fleet at the level of each trip. We have used these models to develop a scheduling and assignment strategy that can rotate the different vehicle types across the transit agencies’ routes. The optimization algorithm ensures that the vehicles are matched to trips considering weather patterns, expected congestion, and road gradients to minimize the overall energy usage. We list the key observations from our project for other practitioners below. Details are available in the report, and the list of source code and our publications are included in the appendix. 1. We have demonstrated the feasibility of collecting, merging and analyzing large volumes of high-resolution real-world telemetry data from a mixed vehicle fleet. To mitigate the inherent noise of the recorded GPS points, the team developed an algorithm that filters data and maps the points onto a street. The algorithm considers previous and subsequent location measurements and different characteristics of nearby streets to determine how likely the vehicle travels on them. Then, the team segmented the time series into disjoint contiguous samples based on adjacent road segments and repeated the outlier detection and removal. For each data point, the team added features corresponding to elevation changes within the samples, weather features, such as temperature, and traffic data, such as speed ratio between actual speed and free-flow speed. 2. We have developed two forms of machine learning models that be used to understand and analyze the energy operations of a mixed vehicle transit fleet. The micro prediction model provides estimates of instantaneous energy prediction for all types of buses (diesel, hybrid, and electric). Such a model is important in evaluating the energy impacts of real-time bus operation strategies, but it is challenging due to diversified driving cycles of transit buses. The model can help the drivers understand the impact of their driving behaviors and short-term congestions. The macro prediction models estimate average energy consumption across the whole trip considering the features: distance traveled, various road-type features, elevation change, day of the week, time of day, various weather features (temperature, humidity, etc.), and traffic features (speed ratio and jam factor). 3. We have demonstrated that it is possible to transfer the machine learning models we have developed in this project to other teams and cities by using inductive transfer learning. We also showed that the performance of the macro energy prediction models can be improved using a multi-task learning approach where the learning parameters are shared between the models being developed for different vehicle types. The advantage of this approach is improved learning performance as the models can exploit common spatio-temporal and environmental characteristics. 4. Finally, we have developed trip and vehicle assignment and scheduling algorithms that use the energy prediction models and develop a trip to vehicle type (diesel, electric, hybrid) assignment for the whole operation to reduce overall emissions and cost. We have shown through simulations that the proposed algorithms can save $\$$ 48,910 in energy costs and 175 metric tons of CO 2 emission annually for CARTA.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2022

Path sampling of recurrent neural networks by incorporating known physics

Recurrent neural networks have seen widespread use in modeling dynamical systems in varied domains such as weather prediction, text prediction and several others. Often one wishes to supplement the experimentally observed dynamics with prior knowledge or intuition about the system. While the recurrent nature of these networks allows them to model arbitrarily long memories in the time series used in training, it makes it harder to impose prior knowledge or intuition through generic constraints. In this work, we present a path sampling approach based on principle of Maximum Caliber that allows us to include generic thermodynamic or kinetic constraints into recurrent neural networks. We show the method here for a widely used type of recurrent neural network known as long short-term memory network in the context of supplementing time series collected from different application domains. These include classical Molecular Dynamics of a protein and Monte Carlo simulations of an open quantum system continuously losing photons to the environment and displaying Rabi oscillations. Our method can be easily generalized to other generative artificial intelligence models and to generic time series in different areas of physical and social sciences, where one wishes to supplement limited data with intuition or theory based corrections.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Uncertainty Quantification of Metal Additive Manufacturing Processing Conditions Through the use of Exascale Computing

Metal additive manufacturing (AM) is a disruptive manufacturing technology that opens the design space for parts outside those possible from traditional manufacturing methods. In order to accelerate industry and R&D needs to certify AM parts, the Exascale Additive Manufacturing project (ExaAM) has developed a suite of exascale-ready computational tools to model the process-to-structure-to-properties (PSP) relationship for additively manufactured metal components. One such tool is an uncertainty quantification (UQ) pipeline to quantify the effect that uncertainty in processing conditions has on local mechanical responses. We present an overview of this pipeline and its required simulation and workflow codes. Using the Oak Ridge National Laboratory’s (ORNL) exascale computer, Frontier, we utilize this pipeline to cross multiple length and time scales to predict the local mechanical response of a location within a complex AM bridge part, AMB2018-01 produced by the National Institute of Standards and Technology (NIST) as part of their 2018 AM-Bench test series. Our results are then compared to experimental mechanical tests of parts from the NIST build to quantify the error in the ExaAM UQ workflow.

Carson, Robert↗
DOE OSTI2019

A two-phase substrate model for enzymatic hydrolysis of lignocellulose: application to batch and continuous reactors

Abstract Background Enzymatic hydrolysis continues to have a significant projected production cost for the biological conversion of biomass to fuels and chemicals, motivating research into improved enzyme and reactor technologies in order to reduce enzyme usage and equipment costs. However, technology development is stymied by a lack of accurate and computationally accessible enzymatic-hydrolysis reaction models. Enzymatic deconstruction of cellulosic materials is an exceedingly complex physico-chemical process. Models which elucidate specific mechanisms of deconstruction are often too computationally intensive to be accessible in process or multi-physics simulations, and empirical models are often too inflexible to be effectively applied outside of their batch contexts. In this paper, we employ a phenomenological modeling approach to represent rate slowdown due to substrate structure (implemented as two substrate phases) and feedback inhibition, and apply the model to a continuous reactor system. Results A phenomenological model was developed in order to predict glucose and solids concentrations in batch and continuous enzymatic-hydrolysis reactors from which liquor is continuously removed by ultrafiltration. A series of batch experiments were performed, varying initial conditions (solids, enzyme, and sugar concentrations), and best-fit model parameters were determined using constrained nonlinear least-squares methods. The model achieved a good fit for overall sugar yield and insoluble solids concentration, as well as for the reduced rate of sugar production over time. Additionally, without refitting model coefficients, good quantitative agreement was observed between results from continuous enzymatic-hydrolysis experiments and model predictions. Finally, the sensitivity of the model to its parameters is explored and discussed. Conclusions Although the phenomena represented by the model correspond to behaviors that emerge from clusters of mechanisms, and hence a set of model coefficients are unique to the substrate and the enzyme system, the model is efficient to solve and may be applied to novel reactor schema and implemented in computational fluid dynamics (CFD) simulations. Hence, this modeling approach finds the right balance between model complexity and computational efficiency. These capabilities have broad application to reactor design, scale-up, and process optimization.

09 BIOMASS FUELS↗
DOE OSTI2021

Immobilization of Cyanines in DNA Produces Systematic Increases in Fluorescence Intensity

Cyanines are useful fluorophores for a myriad of biological labeling applications, but their interactions with biomolecules are unpredictable. Cyanine fluorescence intensity can be highly variable due to complex photoisomerization kinetics, which are exceedingly sensitive to the surrounding environment. This introduces large errors in Förster resonance energy transfer (FRET)-based experiments where fluorescence intensity is the output parameter. However, this environmental sensitivity is a strength from a biological sensing point of view if specific relationships between biomolecular structure and cyanine photophysics can be identified. We describe a set of DNA structures that modulate cyanine fluorescence intensity through the insertion of adenine or thymine bases. These structures simultaneously provide photophysical predictability and tunability. We characterize these structures using steady-state fluorescence measurements, fluorescence correlation spectroscopy (FCS), and time-resolved photoluminescence (TRPL). Here, we find that the photoisomerization rate decreases over an order of magnitude across the adenine series, which is consistent with increasing immobilization of the cyanine moiety by the surrounding DNA structure.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Deep learning-based spatio-temporal estimate of greenhouse gas emissions using satellite data

Accurate estimation of greenhouse gases (GHGs) emissions is very important for developing mitigation strategies to climate change by controlling and reducing GHG emissions. This project aims to develop multiple deep learning approaches to estimate anthropogenic greenhouse gas emissions using multiple types of satellite data. NO2 concentration is chosen as an example of GHGs to evaluate the proposed approach. Two sentinel satellites (sentinel-2 and sentinel-5P) provide multiscale observations of GHGs from 10-60m resolution (sentinel-2) to ~kilometer scale resolution (sentinel-5P). Among multiple deep learning (DL) architectures evaluated, two best DL models demonstrate that key features of spatio-temporal satellite data and additional information (e.g., observation times and/or coordinates of ground stations) can be extracted using convolutional neural networks and feed forward neural networks, respectively. In particular, irregular time series data from different NO 2 observation stations limit the flexibility of long short-term memory architecture, requiring zero-padding to fill in missing data. However, deep neural operator (DNO) architecture can stack time-series data as input, providing the flexibility of input structure without zero-padding. As a result, the DNO outperformed other deep learning architectures to account for time-varying features. Overall, temporal patterns with smooth seasonal variations were predicted very well, while frequent fluctuation patterns were not predicted well. In addition, uncertainty quantification using conformal inference method is performed to account for prediction ranges. Overall, this research will lead to a new groundwork for estimating greenhouse gas concentrations using multiple satellite data to enhance our capability of tracking the cause of climate change and developing mitigation strategies.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Advancing the Understanding of Snow Accumulation, Melting, and Associated Thermal Insulation Using Spatially Dense Snow Depth and Temperature Time Series

Snow thermal insulation is a critical factor influencing ground thermal dynamics and associated biogeochemical processes. We analyzed the spatiotemporal variability of snow accumulation, melting, and thermal insulation dynamics using spatially dense, collocated snow depth and ground interface temperature time series over two consecutive years. We demonstrated that considering late‐winter snow depth alone was insufficient to fully capture the complexity in snow and insulation dynamics. The influence of vegetation and topography on snow depth distribution varied over the season, across sites and years. We found that deep snow with a long melting period had a substantial impact on thawing n‐factors. To better predict snow insulation effects, we proposed a new weighted snow depth metric that integrates mean daily snow depth and air temperature throughout the cold season. Our results provide insights for developing space‐time remote sensing products and evaluating the representation of snow and permafrost processes in Earth system models.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

The hidden structure of hydrodynamic transport in random fracture networks

We study the large-scale dynamics and prediction of hydrodynamic transport in random fracture networks. The flow and transport behaviour is characterized by first passage times and displacement statistics, which show heavy tails and anomalous dispersion with a strong dependence on the injection condition. The origin of these behaviours is investigated in terms of Lagrangian velocities sampled equidistantly along particle trajectories, unlike classical sampling strategies at a constant rate. The velocity series are analysed by their copula density, the joint distribution of the velocity unit scores, which reveals a simple, albeit hidden, correlation structure that can be described by a Gaussian copula. Based on this insight, we derive a Langevin equation for the evolution of equidistant particle speeds. In this framework, particle motion is quantified by a stochastic time-domain random walk, the joint density of particle position, and speed satisfies a Klein–Kramers equation. The upscaled theory quantifies particle motion in terms of the characteristic fracture length scale and the distribution of Eulerian flow velocities. That is, it is predictive in the sense that it does not require the a priori knowledge of transport attributes. The upscaled model captures non-Fickian transport features, and their dependence on the injection conditions in terms of the velocity point statistics and average fracture length. It shows that the first passage times and displacement moments are dominated by extremes occurring at the first step. The presented approach integrates the interaction of flow and structure into a predictive model for large-scale transport in random fracture networks.

42 ENGINEERING↗
DOE OSTI2020

Predicting Emission Source Terms in a Reduced-Order Fire Spread Model—Part 1: Particulate Emissions

A simple, easy-to-evaluate, surrogate model was developed for predicting the particle emission source term in wildfire simulations. In creating this model, we conceptualized wildfire as a series of flamelets, and using this concept of flamelets, we developed a one-dimensional model to represent the structure of these flamelets which then could be used to simulate the evolution of a single flamelet. A previously developed soot model was executed within this flamelet simulation which could produce a particle size distribution. Executing this flamelet simulation 1200 times with varying conditions created a data set of emitted particle size distributions to which simple rational equations could be tuned to predict a particle emission factor, mean particle size, and standard deviation of particle sizes. These surrogate models (the rational equation) were implemented into a reduced-order fire spread model, QUIC-Fire. Using QUIC-Fire, an ensemble of simulations were executed for grassland fires, southeast U.S. conifer forests, and western mountain conifer forests. Resulting emission factors from this ensemble were compared against field data for these fire classes with promising results. Also shown is a predicted averaged resulting particle size distribution with the bulk of particles produced to be on the order of 1 μm in size.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

One-Step Ahead Prediction of Thermal Mixing Tee Sensors with Long Short Term Memory (LSTM) Neural Networks

High-temperature advanced reactors under development, such as sodium fast reactors (SFR) and molten salt cooled reactors (MSCR), are expected to offer lower levelized cost of energy (LCOE) compared to existing light water reactor (LWR’s). In the existing light water reactors (LWR’s), operation and maintenance (O&M) expenses constitute the largest fraction of the total operating cost. Some of the O&M costs are related maintenance of sensors which can fail due to exposure to harsh environment in a reactor. The O&M costs of Advanced Reactor (AR)’s are expected to constitute a significant fraction of the total cost as well, because of high temperature and radiation level in AR are likely to cause material fatigue and premature failure of sensors and components. The O&M costs in AR’s could be reduced through integration of advanced informatics of performance-related sensors into a digital twin designed for reactor monitoring. For example, machine learning (ML) could be employed for real-time validation and correction of performance-related sensors, and reducing the number of performance-related physical sensor units through virtual sensing. As part of the effort, we investigate real-time validation of thermal hydraulic sensors through one-step ahead forecasting of sensor values using long short-term memory (LSTM) recurrent neural networks (RNN). The sensors are installed in a flow loop containing a thermal mixing tee, which is a common experimental model to study thermal fatigue in a thermal hydraulic loop. In addition, nonlinear transients generated in a thermal mixing tee constitute a good challenge data set for training and validation of ML algorithms. Sensors in this study include thermocouples, flow meters, and optical fibers for distributed temperature sensing. In one experiment, measurement data sets were obtained for a loop was filled with water, and in another experiment, measurements were performed on a loop filled with liquid metal Galinstan. We have also conducted preliminary investigation of one-step ahead prediction of fiber optics-based distributed temperature sensing with LSTM networks. In predicting fiber-based temperature measurements, we treated each gauge pitch of the fiber as an independent sensor. Accuracy of one-step ahead forecasting was estimated by calculating root mean square error (RMSE) for the test segment of time series of each sensor. RMSE’s for temperature sensors in water loop were, for the most part, lower than for the same sensors in Galinstan loop. The RMSE’s for flow meters were similar for both loops. The RMSE’s for distributed temperature measured with the fiber optic sensor were similar to those of the point sensors. Results of this study demonstrated the capability of LSTM one-step ahead forecasting with RMSE comparable to uncertainty in sensor measurements.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗