Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Predictive Modeling”

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 397 records · Page 22
All sourcesNASA NTRSDOE OSTI
DOE OSTI2015

TU-G-303-00: Radiomics: Advances in the Use of Quantitative Imaging Used for Predictive Modeling

‘Radiomics’ refers to studies that extract a large amount of quantitative information from medical imaging studies as a basis for characterizing a specific aspect of patient health. Radiomics models can be built to address a wide range of outcome predictions, clinical decisions, basic cancer biology, etc. For example, radiomics models can be built to predict the aggressiveness of an imaged cancer, cancer gene expression characteristics (radiogenomics), radiation therapy treatment response, etc. Technically, radiomics brings together quantitative imaging, computer vision/image processing, and machine learning. In this symposium, speakers will discuss approaches to radiomics investigations, including: longitudinal radiomics, radiomics combined with other biomarkers (‘pan-omics’), radiomics for various imaging modalities (CT, MRI, and PET), and the use of registered multi-modality imaging datasets as a basis for radiomics. There are many challenges to the eventual use of radiomics-derived methods in clinical practice, including: standardization and robustness of selected metrics, accruing the data required, building and validating the resulting models, registering longitudinal data that often involve significant patient changes, reliable automated cancer segmentation tools, etc. Despite the hurdles, results achieved so far indicate the tremendous potential of this general approach to quantifying and using data from medical images. Specific applications of radiomics to be presented in this symposium will include: the longitudinal analysis of patients with low-grade gliomas; automatic detection and assessment of patients with metastatic bone lesions; image-based monitoring of patients with growing lymph nodes; predicting radiotherapy outcomes using multi-modality radiomics; and studies relating radiomics with genomics in lung cancer and glioblastoma. Learning Objectives: Understanding the basic image features that are often used in radiomic models. Understanding requirements for reliable radiomic models, including robustness of metrics, adequate predictive accuracy, and generalizability. Understanding the methodology behind radiomic-genomic (’radiogenomics’) correlations. Research supported by NIH (US), CIHR (Canada), and NSERC (Canada)

60 APPLIED LIFE SCIENCES↗
DOE OSTI2024

Acceleration of Graph Neural Network-Based Prediction Models in Chemistry via Co-Design Optimization on Intelligence Processing Units

Atomic structure prediction and associated property calculations are the bedrock of chemical physics. Since high-fidelity ab initio modeling techniques for computing the structure and properties can be prohibitively expensive, this motivates the development of machine-learning (ML) models that make these predictions more efficiently. Training graph neural networks over large atomistic databases introduces unique computational challenges such as the need to process millions of small graphs with variable size and support communication patterns that are distinct from learning over large graphs such as social networks. We demonstrate a novel hardware-software co-design approach to scale up the training of atomistic graph neural networks (GNN) for structure and property prediction. First, to eliminate redundant computation and memory associated with alternative padding techniques and to improve throughput via minimizing communication, we formulate the effective coalescing of the batches of variable-size atomistic graphs as the bin packing problem and introduce a hardware-agnostic algorithm to pack these batches. In addition, we propose hardware-specific optimizations including a planner and vectorization for the gather-scatter operations targeted for Graphcore’s Intelligence Processing Unit (IPU), as well as model-specific optimizations such as merged communication collectives and optimized softplus. Putting these all together, we demonstrate the effectiveness of the proposed co-design approach by providing an implementation of a well-established atomistic GNN on the Graphcore IPUs. We evaluate the training performance on multiple atomistic graph databases with varying degrees of graph counts, sizes and sparsity. Here, we demonstrate that such a co-design approach can reduce the training time of atomistic GNNs and can improve the performance by up to 1.5× compared to the baseline implementation of the model on the IPUs. Additionally, we compare our IPU implementation with a Nvidia GPU-based implementation and show that our atomistic GNN implementation on the IPUs can run 1.8× faster on average compared to the execution time on the GPUs.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2019

Validation of Wichner Predictive Model for Chronic Oxidation by Moisture of Nuclear Graphite

This document reports the results of multi-year extensive research on chronic oxidation of nuclear graphite by traces of moisture that might be present in the helium coolant of high-temperature gas-cooled reactors (HTGRs). The research focuses on four grades of nuclear graphite that are considered potential candidates for component fabrication in advanced nuclear reactors. The four grades are (1) PCEA (medium-fine grain, extruded, manufactured by GrafTech Inc., USA); (2) NBG-17 (medium-fine grain, vibrationally molded, manufactured by SGL Carbon, Germany/France); (3) IG-110 (microfine grain, isostatically molded, manufactured by Toyo Tanso, Japan); and (4) 2114 (microfine grain, isostatically pressed, manufactured by Mersen, USA). The experimental part of this research comprised three objectives that were consistently pursued for each graphite material: (1) accelerated oxidation tests in well-controlled conditions (temperature, gas composition) and analysis of chemical kinetic models and of their parameters for each graphite grade; (2) measurements of water vapor transport rates from H 2 O/He mixtures through thin graphite slabs for estimation of the water effective diffusivity specific to each material; (3) controlled oxidation of graphite specimens in H 2 O/He mixtures and characterization of the effects of oxidation temperatures on the density profiles of oxidized layers. These three groups of experimental results were interpreted using the model developed by Wichner et al. for predicting the penetration depth of oxidants (moisture or oxygen) as a function of oxidation conditions. Basically, starting from the kinetic and transport properties of each graphite grade, the ultimate goal was predicting the stable density profile in the oxidized layer and its dependence on the oxidation temperature. The profiles obtained this way were then compared against direct observations of oxidized layers in specimens obtained in well-controlled oxidation conditions. The general agreement between predictions and observations validated the general applicability of the Wichner model. The results obtained in this project were presented at annual Department of Energy–Advanced Reactor Technologies program reviews and at specialist meetings and conferences and were published in Oak Ridge National Laboratory (ORNL) reports and in professional journals. The results published in 2018 had an immediate impact in 2019, when a group from three US universities used ORNL kinetic data as input information in a complex simulation of chronic oxidation by moisture using the same graphite grades during long-time operation in a modular high-temperature gas-cooled reactor. Their conclusion, in line with the conclusions obtained at the end of this project, was that chronic graphite oxidation by moisture during normal operation conditions of an HTGR will be limited to a thin surface layer of graphite blocks at the reactor bottom, where the highest temperatures are. That will not affect the integrity of graphite components and reactor safety, provided the impurity concentration in the helium coolant is rigorously controlled and maintained at the design specifications.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2025

Developing predictive models for µ opioid receptor binding using machine learning and deep learning techniques

Opioids exert their analgesic effect by binding to the µ opioid receptor (MOR), which initiates a downstream signaling pathway, eventually inhibiting pain transmission in the spinal cord. However, current opioids are addictive, often leading to overdose contributing to the opioid crisis in the United States. Therefore, understanding the structure-activity relationship between MOR and its ligands is essential for predicting MOR binding of chemicals, which could assist in the development of non-addictive or less-addictive opioid analgesics. This study aimed to develop machine learning and deep learning models for predicting MOR binding activity of chemicals. Chemicals with MOR binding activity data were first curated from public databases and the literature. Molecular descriptors of the curated chemicals were calculated using software Mold2. The chemicals were then split into training and external validation datasets. Random forest, k-nearest neighbors, support vector machine, multi-layer perceptron, and long short-term memory models were developed and evaluated using 5-fold cross-validations and external validations, resulting in Matthews correlation coefficients of 0.528–0.654 and 0.408, respectively. Furthermore, prediction confidence and applicability domain analyses highlighted their importance to the models’ applicability. Our results suggest that the developed models could be useful for identifying MOR binders, potentially aiding in the development of non-addictive or less-addictive drugs targeting MOR.

Research & Experimental Medicine↗
DOE OSTI2018

Competitive docking model for prediction of the human nicotinic acetylcholine receptor α7 binding of tobacco constituents

The detrimental health effects associated with tobacco use constitute a major public health concern. The addiction associated with nicotine found in tobacco products has led to difficulty in quitting among users. Nicotinic acetylcholine receptors (nAChRs) are the targets of nicotine and are responsible for addiction to tobacco products. However, it is unknown if the other >8000 tobacco constituents are addictive. Since it is time-consuming and costly to experimentally assess addictive potential of such larger number of chemicals, computationally predicting human nAChRs binding is important for in silico evaluation of addiction potential of tobacco constituents and needs structures of human nAChRs. Therefore, we constructed three dimensional structures of the ligand binding domain of human nAChR α7 subtype and then developed a predictive model based on the constructed structures to predict human nAChR α7 binding activity of tobacco constituents. The predictive model correctly predicted 11 out of 12 test compounds to be binders of nAChR α7. The model is a useful tool for high-throughput screening of potential addictive tobacco constituents. These results could inform regulatory science research by providing a new validated predictive tool using cutting-edge computational methodology to high throughput screen tobacco additives and constituents for their binding interaction with the human α7 nicotinic receptor. The tool represents a prediction model capable of screening thousands of chemicals found in tobacco products for addiction potential, which improves the understanding of the potential effects of additives.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2020

Framework For Spatial Agricultural Crop Yield Prediction Model Development

This framework was developed to provide data preprocessing for spatiotemporal agricultural yield data and remote sensing data for modelling using artificial neural networks (ANNs) to predict subfield crop yield estimates. The software includes methods to train, validate, and test ANN models. It also include methods to infer on new remote sensing data.

Griffel, LloydM.↗
DOE OSTI2018

Level density of the sd-nuclei—Statistical shell-model predictions

Accurate knowledge of the nuclear level density is important both from a theoretical viewpoint as a powerful instrument for studying nuclear structure and for numerous applications. For example, astrophysical reactions responsible for the nucleosynthesis in the universe can be understood only if we know the nuclear level density. We use the configuration-interaction nuclear shell model to predict nuclear level density for all nuclei in the sd-shell, both total and for individual spins (only with positive parity). To avoid the diagonalization in large model spaces we use the moments method based on statistical properties of nuclear many-body systems. In the cases where the diagonalization is possible, the results of the moments method practically coincide with those from the shell-model calculations. Using the computed level densities, we fit the parameters of the Constant Temperature phenomenological model, which can be used by practitioners in their studies of nuclear reactions at excitation energies appropriate for the sd-shell nuclei.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2015

Two-dimensional NMR measurement and point dipole model prediction of paramagnetic shift tensors in solids

A new two-dimensional Nuclear Magnetic Resonance (NMR) experiment to separate and correlate the first-order quadrupolar and chemical/paramagnetic shift interactions is described. This experiment, which we call the shifting-d echo experiment, allows a more precise determination of tensor principal components values and their relative orientation. It is designed using the recently introduced symmetry pathway concept. A comparison of the shifting-d experiment with earlier proposed methods is presented and experimentally illustrated in the case of {sup 2}H (I = 1) paramagnetic shift and quadrupolar tensors of CuCl{sub 2}⋅2D{sub 2}O. The benefits of the shifting-d echo experiment over other methods are a factor of two improvement in sensitivity and the suppression of major artifacts. From the 2D lineshape analysis of the shifting-d spectrum, the {sup 2}H quadrupolar coupling parameters are 〈C{sub q}〉 = 118.1 kHz and 〈η{sub q}〉 = 0.88, and the {sup 2}H paramagnetic shift tensor anisotropy parameters are 〈ζ{sub P}〉 = − 152.5 ppm and 〈η{sub P}〉 = 0.91. The orientation of the quadrupolar coupling principal axis system (PAS) relative to the paramagnetic shift anisotropy principal axis system is given by (α,β,γ)=((π)/2 ,(π)/2 ,0). Using a simple ligand hopping model, the tensor parameters in the absence of exchange are estimated. On the basis of this analysis, the instantaneous principal components and orientation of the quadrupolar coupling are found to be in excellent agreement with previous measurements. A new point dipole model for predicting the paramagnetic shift tensor is proposed yielding significantly better agreement than previously used models. In the new model, the dipoles are displaced from nuclei at positions associated with high electron density in the singly occupied molecular orbital predicted from ligand field theory.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2021

A Predictive Model for Offgas Composition in Waste Glass Melters - Spring 2021 SULI General Audience Abstract

Approximately 56 million gallons of nuclear waste are currently stored in 177 underground storage tanks at the Hanford site in Washington state. A portion of the tank waste is targeted for immobilization by converting the nuclear waste to borosilicate glass through a process called vitrification. During vitrification, emissions are produced in addition to the intended glass product. These emissions, contained in a volume above the molten glass called the plenum, are composed of water vapor, air components, aerosols, particulates, and other gaseous species that result from evaporation, reactions, and air influx. The formation of these gasses causes the surface of the glass to foam. To reduce foaming, sucrose is added to the waste stream before the conversion to glass. Sucrose also reduces the formation of hazardous gasses in the plenum including nitrous oxides, NOx, and carboxides, COx. However, if excess sucrose is present, the reactions that produce the gasses in the plenum will be incomplete, and increased levels of NOx and COx can be observed. The Waste Treatment and Immobilization Plant at the Hanford site is equipped with the technology to treat the plenum emissions. Though many tests have been run to determine the presence of particulates in the plenum emissions, there is does not exist an established method to confidently predict the composition of the gaseous species in the plenum prior to treatment without physical testing. A model was created in the process modeling software Aspen Plus to predict the composition of NOx and COx in the plenum. The model employs a constant stirred tank reactor and user-defined reaction chemistry to determine the plenum composition. To verify the model, the offgas predicted by the model were compared to available offgas data for ten different feed compositions. It is demonstrated that the developed Aspen Plus model is capable of predicting the composition of NOx and COx in the plenum.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2021

Assessing boundary condition and parametric uncertainty in numerical-weather-prediction-modeled, long-term offshore wind speed through machine learning and analog ensemble

To accurately plan and manage wind power plants, not only does the time-varying wind resource at the site of interest need to be assessed but also the uncertainty connected to this estimate. Numerical weather prediction (NWP) models at the mesoscale represent a valuable way to characterize the wind resource offshore, given the challenges connected with measuring hub-height wind speed. The boundary condition and parametric uncertainty associated with modeled wind speed is often estimated by running a model ensemble. However, creating an NWP ensemble of long-term wind resource data over a large region represents a computational challenge. Here, we propose two approaches to temporally extrapolate wind speed boundary condition and parametric uncertainty using a more convenient setup in which a mesoscale ensemble is run over a short-term period (1 year), and only a single model covers the desired long-term period (20 year). We quantify hub-height wind speed boundary condition and parametric uncertainty from the short-term model ensemble as its normalized across-ensemble standard deviation. Then, we develop and apply a gradient-boosting model and an analog ensemble approach to temporally extrapolate such uncertainty to the full 20-year period, for which only a single model run is available. As a test case, we consider offshore wind resource characterization in the California Outer Continental Shelf. Both of the proposed approaches provide accurate estimates of the long-term wind speed boundary condition and parametric uncertainty across the region (R 2 >0.75), with the gradient-boosting model slightly outperforming the analog ensemble in terms of bias and centered root-mean-square error. At the three offshore wind energy lease areas in the region, we find a long-term median hourly uncertainty between 10 % and 14 % of the mean hub-height wind speed values. Finally, we assess the physical variability in the uncertainty estimates. In general, we find that the wind speed uncertainty increases closer to land. Also, neutral conditions have smaller uncertainty than the stable and unstable cases, and the modeled wind speed in winter has less boundary condition and parametric sensitivity than summer.

17 WIND ENERGY↗
DOE OSTI2016

Predictive models of radiative neutrino masses

We discuss two models of radiative neutrino mass generation. The first model features one–loop Zee model with Z{sub 4} symmetry. The second model is the two–loop neutrino mass model with singly- and doubly-charged scalars. These two models fit neutrino oscillation data well and predict some interesting rates for lepton flavor violation processes.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2022

Hybrid AI-ML and FE-based Digital Twin Predictive Modeling Framework for a PWR Coolant System Components: Updates on Multi-Time-Series-3D-Location Dependent Usages Factor Prediction

The long-term operation (LTO) of nuclear power plants (NPP) beyond their original design life of 40 years can lead to more material damage associated with cyclic fatigue under thermal-mechanical loading cycles and associated long-term exposure of reactor material to the deleterious reactor-coolant environments. However, under this LTO condition, the reactor components can still safely operate but may require more frequent Nondestructive Evaluation (NDE) of reactor components. Requiring frequent NDE inspections may lead to frequent NPP shutdowns which can lead to power outages and additional NDE inspection cost-related economic loss. The economic loss can be minimized by reducing uncertainty in life estimation of safety-critical pressure boundary components and by implementing a more digital approach such as using upcoming digital-twin (DT) technology for predicting the structural states (e.g., time and location dependent inside/outside thickness temperature, stress, strain, plastic deformation, etc.) and associated fatigue life of a component in real time. The DT framework is based on limited experimental data, Artificial-intelligence (AI)-Machine-Learning (ML) and multiphysics-computationalmechanics such as finite element- (FE) based models. Given the real-time thermal-hydraulic process measurements from several existing plant sensors, the overall goal of the DT framework is to predict the cumulative usages factors or equivalent fatigue lives in real time and at any random 3D location of the components. This includes inaccessible locations such as inside the thickness or location of a component. This prediction can be at thousands to millions of 3D point clouds or locations like conventional FE-based models, but without running an FE model in real time.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2019

Machine-Learning-Based Predictive Modeling of Glass Transition Temperatures: A Case of Polyhydroxyalkanoate Homopolymers and Copolymers

Polyhydroxyalkanoate-based polymers—being ecofriendly, biosynthesizable, and economically viable and possessing a broad range of tunable properties—are currently being actively pursued as promising alternatives for petroleum-based plastics. The vast chemical complexity accessible within this class of polymers gives rise to challenges in the rational discovery of novel polymer chemistries for specific applications. Here, the burgeoning field of polymer informatics addresses this challenge via providing tools and strategies for accelerated property prediction and materials design via surrogate machine-learning models built on reliable past data. In this contribution, we use glass transition temperature T g as an example target property to demonstrate promise of the data-enabled route to accelerated learning of accurate structure–property mappings in PHA-based polymers. Our analysis uses a data set of experimentally measured T g values, polymer molecular weights, and a polydispersity index for PHA-based homo- and copolymers that was carefully assembled from the literature. A fingerprinting scheme that captures key properties based on topology, shape, and charge/polarity of specific chemical units or motifs forming the polymer backbone was devised to numerically represent the polymers. A validated statistical learning model is then developed to allow for a mapping of the polymer fingerprints onto the property space in a physically meaningful and reliable manner. Once developed, the model can not only rapidly predict the property of new PHA polymers but also provide uncertainties underlying the predictions. The model is further combined with an evolutionary-algorithm-based search strategy to efficiently identify multicomponent polymer compositions with a prespecified T g . While the present contribution is focused specifically on T g , the surrogate model development approach put forward here is general and can, in principle, be extended to a range of other properties.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗