Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “prediction methods”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

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

At least 1,297 records · Page 72
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

From classical thermodynamics to phase-field method

Phase-field method is a density-based computational method at the mesoscale for modeling and predicting the temporal microstructure and property evolution during materials processes. The focus of this article is on connecting the most common phase-field equations to the very basic first and second laws of classical thermodynamics through rudimentary irreversible thermodynamics. It briefly discusses the relations of the continuum phase-field equations to their counter parts at the microscopic and atomic levels. It attempts to clarify the contributions of long-range elastic, electrostatic, and magnetic interactions to domain structure evolution during structural, ferroelectric, and ferromagnetic phase transformations by separating order parameter changes due to the presence of quasi-static fields and those arising from phase transformations. A few examples are presented to demonstrate the possibility of employing the phase-field method to provide guidance to designing materials for optimum properties or discovering novel mesoscale phenomena or new materials functionalities. Here, the article ends with a brief perspective on a number of potential future directions on the development and applications of phase-field method beyond its traditional applications to structural alloys.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Urban Flood Modeling: Uncertainty Quantification and Physics‐Informed Gaussian Processes Regression Forecasting

Abstract Estimating uncertainty in flood model predictions is important for many applications, including risk assessment and flood forecasting. We focus on uncertainty in physics‐based urban flooding models. We consider the effects of the model's complexity and uncertainty in key input parameters. The effect of rainfall intensity on the uncertainty in water depth predictions is also studied. As a test study, we choose the Interconnected Channel and Pond Routing (ICPR) model of a part of the city of Minneapolis. The uncertainty in the ICPR model's predictions of the floodwater depth is quantified in terms of the ensemble variance using the multilevel Monte Carlo (MC) simulation method. Our results show that uncertainties in the studied domain are highly localized. Model simplifications, such as disregarding the groundwater flow, lead to overly confident predictions, that is, predictions that are both less accurate and uncertain than those of the more complex model. We find that for the same number of uncertain parameters, increasing the model resolution reduces uncertainty in the model predictions (and increases the MC method's computational cost). We employ the multilevel MC method to reduce the cost of estimating uncertainty in a high‐resolution ICPR model. Finally, we use the ensemble estimates of the mean and covariance of the flood depth for real‐time flood depth forecasting using the physics‐informed Gaussian process regression method. We show that even with few measurements, the proposed framework results in a more accurate forecast than that provided by the mean prediction of the ICPR model.

Kohanpur, Amir H.↗
DOE OSTI2026

Multidimensional Distributional Neural Network Output Demonstrated in Super‐Resolution of Surface Wind Speed

Accurate quantification of uncertainty in neural network predictions remains a central challenge for scientific applications involving high-dimensional, correlated data. While existing methods capture either aleatoric or epistemic uncertainty, few offer closed-form, multidimensional distributions that preserve spatial correlation while remaining computationally tractable. In this work, we present a framework for training neural networks with a multidimensional Gaussian loss, generating a closed-form predictive distribution over outputs informed by non-identically distributed training data. Our approach captures aleatoric uncertainty by iteratively estimating the means and covariance matrices, and is demonstrated on a super-resolution example out-of-training-sample. We leverage a Fourier representation of the covariance matrix to stabilize network training and preserve spatial correlation. We introduce a novel regularization strategy—referred to as information sharing—that interpolates between image-specific and global covariance estimates, enabling convergence of the super-resolution downscaling network trained on image-specific distributional loss functions. This framework allows for efficient sampling, explicit correlation modeling, and extensions to more complex distribution families all without disrupting prediction performance. We demonstrate the method on a surface wind speed downscaling task and discuss its broader applicability to uncertainty-aware prediction in scientific models.

17 WIND ENERGY↗
DOE OSTI2020

Science-informed Machine Learning to Increase Recovery Efficiency in Unconventional Reservoirs

Production of hydrocarbons from fractured, unconventional reservoirs is inherently inefficient. But machine learning offers a pathway both to increasing recovery efficiency at a site and to improving forecasts of production, thereby improving the economics of operations in unconventional reservoirs. Los Alamos—in partnership with DOE, NETL, and WVU—has been developing a science-informed workflow and platform for optimizing pressure-drawdown at a site, which will allow an operator to make reservoir-management decisions that optimize recovery in consideration of future production. This work relies on a hybridization of physics-based prediction and machine learning, whereby accurate synthetic data (in combination with available site data) can enable the application of machine learning methods for rapid forecasting and optimization. The physics-based prediction is built upon experimental and theoretical work to determine transport characteristics in shale at various scales, with an emphasis on materials from MSEEL-I; this fundamental shale R&D was conducted in partnership with DOE, NETL, and several other national labs. This work has resulted from a coordinated leveraging of developments across several projects within DOE FE30, along with internal investments from Los Alamos via LDRD. The development has utilized data from the MSEEL–I site for calibration and demonstration; however, the workflow and platform are readily extendable to operations at other sites, plays, and basins. This machine-learning method can aid operators to improve both recovery efficiency and competitiveness; to this end, future work would quantify processes for other plays/basins and integrate production details with economics.

04 OIL SHALES AND TAR SANDS↗
DOE OSTI2024

Machine learning for accuracy in density functional approximations

Machine learning techniques have found their way into computational chemistry as indispensable tools to accelerate atomistic simulations and materials design. In addition, machine learning approaches hold the potential to boost the predictive power of computationally efficient electronic structure methods, such as density functional theory, to chemical accuracy and to correct for fundamental errors in density functional approaches. In this paper, recent progress in applying machine learning to improve the accuracy of density functional and related approximations is reviewed. Promises and challenges in devising machine learning models transferable between different chemistries and materials classes are discussed with the help of examples applying promising models to systems far outside their training sets.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2021

Desalination metamodels and a framework for cross-comparative performance simulations

There is an opportunity to save energy and reduce operational expenses when choosing a suitable desalination method aided by computational modeling. Existing models are not conducive to generalized comparisons between different desalination methods. Therefore, the work in this study developed metamodels for six desalination methods, grouped them into thermal and molecular transport families, and validated their predictive performance within 9% difference from published data. This validated framework allowed comparisons of desalination methods at their prescribed ranges of operational conditions that they were designed for. These conditions specify feed salinity ranges of 1.6 to 2.4 g/kg for Capacitive Deionization and Reverse Osmosis (RO), 2.8 to 4.2 g/kg for Electrodialysis, 28 to 42 g/kg for Thermovapor Compression and Humidification-Dehumidification, and 37 to 55 g/kg for Multi-Effect Distillation (MED). Despite different operational conditions, all models exhibit non-linear, positive correlation between energy consumption and system size in response to feed salinity and production rate. The framework is also employed in a cross-comparative analysis between MED and RO whose results suggest that energy intensity for MED is an order of magnitude greater than RO for the same operational conditions, but actual operational costs are comparable. Overall, the framework is ready for deployment in case studies of actual desalination plants.

42 ENGINEERING↗
DOE OSTI2022

Improving net ecosystem CO2 flux prediction using memory-based interpretable machine learning

Terrestrial ecosystems play a central role in the global carbon cycle and affect climate change. However, our predictive understanding of these systems is still limited due to their complexity and uncertainty about how key drivers and their legacy effects influence carbon fluxes. Here, we propose an interpretable Long Short-Term Memory (iLSTM) network for predicting net ecosystem CO 2 exchange (NEE) and interpreting the influence on the NEE prediction from environmental drivers and their memory effects. We consider five drivers and apply the method to three forest sites in the United States. Besides performing the prediction in each site, we also conduct transfer learning by using the iLSTM model trained in one site to predict at other sites. Results show that the iLSTM model produces good NEE predictions for all three sites and, more importantly, it provides reasonable interpretations on the input driver's importance as well as their temporal importance on the NEE prediction. Additionally, the iLSTM model demonstrates good across-site transferability in terms of both prediction accuracy and interpretability. The transferability can improve the NEE prediction in unobserved forest sites, and the interpretability advances our predictive understanding and guides process-based model development.

Liu, Siyan↗
DOE OSTI2024

Physics-constrained fault diagnosis framework for monitoring a standalone component of a thermal hydraulic system

A method for diagnosing faults includes receiving a description of a component of a thermal hydraulic system, where the description also indicates one or more sensors of the component. The method also includes constructing, based on a physical conservation law and using the description, a physics-based model describing operation of the component, the physics-based model including one or more unknown parameters. The method further includes calibrating the physics-based model by calculating the one or more unknown parameters using historical measurements to produce a calibrated model. Further, the method includes receiving sensor measurements captured by the one or more sensors, and calculating residuals corresponding to differences between measurements predicted by the calibrated model and the sensor measurements. The method also includes determining, based on the calculated residuals, a fault of the component or of a sensor of the one or more sensors, and generating an alert indicating the fault.

Nguyen, Tat Nghia↗
DOE OSTI2024

Testing hadronic-model predictions of depth of maximum of air-shower profiles and ground-particle signals using hybrid data of the Pierre Auger Observatory

We test the predictions of hadronic interaction models regarding the depth of maximum of air-shower profiles, X max , and ground-particle signals in water-Cherenkov detectors at 1000 m from the shower core, S ( 1000 ) , using the data from the fluorescence and surface detectors of the Pierre Auger Observatory. The test consists of fitting the measured two-dimensional ( S ( 1000 ) , X max ) distributions using templates for simulated air showers produced with hadronic interaction models pos-, et--04, 2.3d and leaving the scales of predicted X max and the signals from hadronic component at ground as free-fit parameters. The method relies on the assumption that the mass composition remains the same at all zenith angles, while the longitudinal shower development and attenuation of ground signal depend on the mass composition in a correlated way. The analysis was applied to 2239 events detected by both the fluorescence and surface detectors of the Pierre Auger Observatory with energies between 10 18.5 eV to 10 19.0 eV and zenith angles below 60°. We found, that within the assumptions of the method, the best description of the data is achieved if the predictions of the hadronic interaction models are shifted to deeper X max values and larger hadronic signals at all zenith angles. Given the magnitude of the shifts and the data sample size, the statistical significance of the improvement of data description using the modifications considered in the paper is larger than 5 σ even for any linear combination of experimental systematic uncertainties. Published by the American Physical Society 2024

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

Super-Resolution for Renewable Energy Resource Data with Wind from Reanalysis Data and Application to Ukraine

With a potentially increasing share of the electricity grid relying on wind to provide generating capacity and energy, there is an expanding global need for historically accurate, spatiotemporally continuous, high-resolution wind data. Conventional downscaling methods for generating these data based on numerical weather prediction have a high computational burden and require extensive tuning for historical accuracy. In this work, we present a novel deep learning-based spatiotemporal downscaling method using generative adversarial networks (GANs) for generating historically accurate high-resolution wind resource data from the European Centre for Medium-Range Weather Forecasting Reanalysis version 5 data (ERA5). In contrast to previous approaches, which used coarsened high-resolution data as low-resolution training data, we use true low-resolution simulation outputs. We show that by training a GAN model with ERA5 as the low-resolution input and Wind Integration National Dataset Toolkit (WTK) data as the high-resolution target, we achieved results comparable in historical accuracy and spatiotemporal variability to conventional dynamical downscaling. This GAN-based downscaling method additionally reduces computational costs over dynamical downscaling by two orders of magnitude. We applied this approach to downscale 30 km, hourly ERA5 data to 2 km, 5 min wind data for January 2000 through December 2023 at multiple hub heights over Ukraine, Moldova, and part of Romania. With WTK coverage limited to North America from 2007–2013, this is a significant spatiotemporal generalization. The geographic extent centered on Ukraine was motivated by stakeholders and energy-planning needs to rebuild the Ukrainian power grid in a decentralized manner. This 24-year data record is the first member of the super-resolution for renewable energy resource data with wind from the reanalysis data dataset (Sup3rWind).

17 WIND ENERGY↗
DOE OSTI2022

Development of Short-Term Forecasting Models Using Plant Asset Data and Feature Selection

Nuclear power plants collect and store large volumes of heterogeneous data from various components and systems. With recent advances in machine learning (ML) techniques, these data can be leveraged to develop diagnostic and short-term forecasting models to better predict future equipment condition. Maintenance operations can then be planned in advance whenever degraded performance is predicted, thus resulting in fewer unplanned outages and the optimization of maintenance activities. This enables lower maintenance costs and improves the overall economics of nuclear power. This paper focuses on developing a short-term forecasting process that leverages a feature selection process to distill large volumes of heterogeneous data and predict specific equipment parameters. A variety of feature selection methods, including Shapley Additive Explanations (SHAP) and variance inflation factor (VIF), were used to select the optimal features as inputs for three ML methods: long short-term memory (LSTM) networks, support vector regression (SVR), and random forest (RF). Each combination of model and input features was used to predict a pump bearing temperature both 1 and 24 hours in advance, based on actual plant system data. The optimal inputs for the LSTM and SVR were selected using the SHAP values, while the optimal input for the RF consisted solely of the response variable itself. Each model produced similar 1-hour-ahead predictions, with root mean square errors (RMSEs) of roughly 0.006. For the 24-hour-ahead predictions, differences could be seen between LSTM, SVR, and RF, as reflected by model performances of 0.036 +- 0.014, 0.0026 +- 0, and 0.063 +- 0.004 RMSE, respectively. As big data and continuous online monitoring become more widely available, the proposed feature selection process can be used for many applications beyond the prediction of process parameters within nuclear infrastructure.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2021

Learning-Accelerated ADMM for Distributed DC Optimal Power Flow

We propose a novel data-driven method to accelerate the convergence of Alternating Direction Method of Multipliers (ADMM) for solving distributed DC optimal power flow (DC-OPF) where lines are shared between independent network partitions. Using previous observations of ADMM trajectories for a given system under varying load, the method trains a recurrent neural network (RNN) to predict the converged values of dual and consensus variables. Given a new realization of system load, a small number of initial ADMM iterations is taken as input to infer the converged values and directly inject them into the iteration. We empirically demonstrate that the online injection of these values into the ADMM iteration accelerates convergence by a significant factor for partitioned 14-, 118- and 2848-bus test systems under differing load scenarios. The proposed method has several advantages: it maintains the security of private decision variables inherent in consensus ADMM; inference is fast and so may be used in online settings; RNN-generated predictions can dramatically improve time to convergence but, by construction, can never result in infeasible ADMM subproblems; it can be easily integrated into existing software implementations. While we focus on the ADMM formulation of distributed DC-OPF in this paper, the ideas presented are naturally extended to other distributed optimization problems.

alternating direction method of multipliers↗
DOE OSTI2020

Learning-Accelerated ADMM for Distributed DC Optimal Power Flow

We suggest a novel data-driven method to accelerate the convergence of Alternating Direction Method of Multipliers (ADMM) for solving distributed DC optimal power flow (DC-OPF) where lines are shared between independent network partitions. Using previous observations of ADMM trajectories for a given system under varying load, the method trains a recurrent neural network (RNN) to predict the converged values of dual and consensus variables. Given a new realization of system load, a small number of initial ADMM iterations is taken as input to infer the converged values and directly inject them into the iteration. We empirically demonstrate that the online injection of these values into the ADMM iteration accelerates convergence by a significant factor for partitioned 14-, 118-and 2848-bus test systems under differing load scenarios. The proposed method has several advantages: it maintains the security of private decision variables inherent in consensus ADMM; inference is fast and so may be used in online settings; RNN-generated predictions can dramatically improve time to convergence but, by construction, can never result in infeasible ADMM subproblems; it can be easily integrated into existing software implementations. While we focus on the ADMM formulation of distributed DC-OPF in this paper, the ideas presented are naturally extended to other distributed optimization problems.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2020

Infrared spectroscopic method for uranium isotopic analysis

A high performance infrared (HPIR) system was developed and demonstrated for the infrared absorption analysis of {sup 235}U and {sup 238}U isotopes in uranium hexafluoride gas samples. Sweeping the quantum cascade laser light source over the spectral range and sampling via a high-rate analog-to-digital converter provided 0.0005 cm-1 spectral resolution, which allowed for high-precision measurements of the isotopic peak shift. A data analysis method was developed using principal component analysis to predict the isotope weight % content of {sup 235}U. The HPIR precision, accuracy, and error were evaluated for a wide range of isotopic ratio samples (0.287 – 93.7 weight % {sup 235}U), and the results were compared to the International Target Values (ITVS) set forth by the International Atomic Energy Agency (IAEA) for non-destructive and destructive analytical techniques. The method meets or surpasses the IAEA ITVs for non-destructive analysis of samples with isotopic content of depleted to highly enriched. The results also demonstrated the capability of the HPIR system to correctly predict the {sup 235}U weight % content of a mislabeled sample whose isotopic distribution was validated by mass spectroscopic measurements. The HPIR measurement is nondestructive and, thus, allows for confirmatory analyses of the exact sample at a designated IAEA lab if higher-resolution or a certified analysis is needed. (author)

07 ISOTOPE AND RADIATION SOURCES↗
DOE OSTI2021

Toward Predictive RANS and SRS Computations of Turbulent External Flows of Practical Interest

In this work, we investigate the main challenges to prediction of turbulent external flows of practical interest with Reynolds-Averaged Navier–Stokes equations (RANS) and Scale-Resolving Simulation (SRS) models. This represents a crucial step toward further developing and establishing these formulations so they can be confidently utilized in engineering problems without reference data. The study initiates by identifying the major challenges to prediction. A literature review is performed to illustrate their effects in RANS and SRS computations. Afterward, we evaluate the impact of the challenges to prediction by analyzing representative statistically steady and unsteady flows with prominent RANS and SRS methods. These include multiple turbulent viscosity and second-moment RANS closures, and hybrid and bridging SRS models. The results demonstrate the potential of the selected SRS models to predict engineering flows. Yet, they also show the importance of considering the challenges to prediction during the setup and conduction of numerical experiments. These can suppress the advantages of using SRS formulations. The data also indicate that only SRS models can confidently predict statistically unsteady flows. In contrast, the results demonstrate that mean-flow quantities of statistically steady flows can be efficiently calculated with RANS closures, especially second-moment closures. Among the selected SRS methods, bridging models reveal better suited for prediction due to their ability to prevent commutation errors and enable the robust evaluation of numerical and modeling errors. This last property allows the use of a new validation technique that does not require reference data.

42 ENGINEERING↗
DOE OSTI2024

A Comprehensive Investigation of Active Learning Strategies for Conducting Anti-Cancer Drug Screening

It is well-known that cancers of the same histology type can respond differently to a treatment. Thus, computational drug response prediction is of paramount importance for both preclinical drug screening studies and clinical treatment design. To build drug response prediction models, treatment response data need to be generated through screening experiments and used as input to train the prediction models. In this study, we investigate various active learning strategies of selecting experiments to generate response data for the purposes of (1) improving the performance of drug response prediction models built on the data and (2) identifying effective treatments. Here, we focus on constructing drug-specific response prediction models for cancer cell lines. Various approaches have been designed and applied to select cell lines for screening, including a random, greedy, uncertainty, diversity, combination of greedy and uncertainty, sampling-based hybrid, and iteration-based hybrid approach. All of these approaches are evaluated and compared using two criteria: (1) the number of identified hits that are selected experiments validated to be responsive, and (2) the performance of the response prediction model trained on the data of selected experiments. The analysis was conducted for 57 drugs and the results show a significant improvement on identifying hits using active learning approaches compared with the random and greedy sampling method. Active learning approaches also show an improvement on response prediction performance for some of the drugs and analysis runs compared with the greedy sampling method.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2021

Assessing Decadal Predictability in an Earth-System Model Using Explainable Neural Networks

We show that explainable neural networks can identify regions of oceanic variability that contribute predictability on decadal timescales in a fully coupled Earth-system model. The neural networks learn to use sea-surface temperature anomalies to predict future continental surface temperature anomalies. We then use a neural-network explainability method called layerwise relevance propagation to infer which oceanic patterns lead to accurate predictions made by the neural networks. In particular, regions within the North Atlantic Ocean and North Pacific Ocean lend the most predictability for surface temperature across continental North America. We apply the proposed methodology to decadal variability, although the concept is generalizable to other timescales of predictability. Furthermore, while our approach focuses on predictable patterns of internal variability within climate models, it should be generalizable to observational data as well. Our study contributes to the growing evidence that explainable neural networks are important tools for advancing geoscientific knowledge.

58 GEOSCIENCES↗
DOE OSTI2022

Assessment of the Phase-to-Ground Fault Apparent Admittance Method with Phase/Ground Boundaries to Detect Types of Electrical Faults for Protective Relays Using Signature Library and Simulated Events

Protective relays in electric power grids recognize the types of electrical faults in a few seconds. The most common detection method to detect the types of electrical faults is based on measuring the angle between the zero and negative sequence currents. However, it is not completely accurate because the phase-to-phase-ground and phase-to-ground electrical faults could have the same detection conditions. Therefore, engineers need to plot the events after an electrical fault to observe the nature of the incidents in detail. In this study, the phase-to-ground fault apparent (PGFA) admittance method with phase/ground boundaries identified the types of electrical faults located in distribution power lines and feeders. This method was based on measuring the PGFA admittance magnitudes for the faulted and nonfaulted phases, resulting in greater than zero and near zero, respectively. The PGFA admittance algorithm was built with MATLAB/Simulink software and tested with signature library and grid simulation events. The PGFA method with phase/ground boundaries was evaluated with the confusion matrix. The measured and predicted values matched in more than 90% of the tests, and the PGFA admittance method with phase/ground boundaries presented an accuracy of 94.3% and a precision of 100%.

42 ENGINEERING↗