Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Local regression”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2019

Integrating Hybrid-Clustering and Localized Regression for Time Synchronization of a Hierarchical Underwater Acoustic Sensor Array

Time synchronization is a critical requirement for the application of underwater acoustic sensor network (UWSN). Although a number of time synchronization protocols have been proposed for UWSN, none of them can be directly applied to autonomous acoustic receivers due to lack of hardware platform to communicate with each other. In this paper, we propose a machine learning-based time synchronization framework for autonomous receiver arrays, using the Juvenile Salmon Acoustic Telemetry System as a case study. The proposed framework consists of array partition and time synchronization. Using detections of receiver attached beacons as input, this framework synchronizes all receiver clocks to a root receiver clock. The framework has been successfully used in a field study at Trevallyn Dam forebay in Tasmania, Australia.

Fu, Tao↗
DOE OSTI2022

Automated and efficient local adaptive regression for principal component-based reduced-order modeling of turbulent reacting flows

Principal Component Analysis can be used to reduce the cost of Computational Fluid Dynamics simulations of turbulent reacting flows by reducing the dimensionality of the transported variables through projection of the thermochemical state onto a lower-dimensional manifold. However, because of the nonlinearity of the principal component source terms, nonlinear regression techniques must be utilized for the source terms in terms of the principal components. Unfortunately, widely available and utilized nonlinear regression techniques can have prohibitive computational requirements and/or accuracy that is highly dependent on user experience in ad hoc tuning of model architecture and hyperparameters. Here, in this work, a new nonlinear regression approach is proposed that is both computationally efficient and automated so does not require any user input. The approach is evaluated through a priori prediction of principal component source terms using data from a Direct Numerical Simulation of a turbulent nonpremixed n-heptane/air jet flame. In particular, the proposed framework consists of local regressions whose complexity is adapted according to the local nonlinearity of the data: local linear regression when accurate enough and local Artificial Neural Networks when nonlinear regression is required. The number of local clusters for local regression is determined automatically using the Davies-Bouldin index. In addition, Bayesian optimization is utilized for model training (i.e., to select the best architectures and hyperparameters of the nonlinear regressions in an unsupervised fashion), eliminating ad hoc hand-tuning and/or expensive grid searches. Overall, compared to a single, global neural network, the new local adaptive regression approach is shown to have comparable accuracy but 69% less training time due to the utilization of local linear regression and faster training of local neural networks.

42 ENGINEERING↗
DOE OSTI2024

Three-Stage Adjusted Regression Forecasting for Software Defect Prediction

In this paper, a three-stage adjusted regression forecasting model is proposed to forecast the local regression model [6]. This is a growth curve approximation model that predicts the parameters for a future linear model based on a sliding window of previous linear models. The three stages of the model are as follows: • Initial fit: train regression models on a sliding window of the date and record model coefficients. • Prediction: fit new regression models to the coefficient lists and predict the value of the next coefficient. • Error correction: correct coefficient prediction error using the residual of the last point of the coefficient list and moving average. The resulting model from the multi-stage process is a forecast of the local regression model that represents the future window of data and is referred to as the predicted line. Results suggest the three-stage model demonstrates better prediction capability compared to existing solutions.

Pritchard, Shadow↗
DOE OSTI2024

Surface Structure of Reacting Solid Ramjet Fuels

Solid fuel ramjets are a developing technology that will enable extended range for supersonic vehicles. The simplicity of the system in terms of moving parts results in the performance being dictated by the solid fuel combustion processes. The physics near the surface, particularly in the fuel-rich recirculation zone, are challenging to resolve due to flow opacity. Here, regression rate measurements of hydroxyl-terminated polybutadiene from a miniature, portable slab burner are reported. Mass-averaged regression rates agree with correlations from the literature, suggesting that the proper physics in the burner are captured. Synchrotron-based phase-contrast imaging is used to quantify local surface features, including a multiphase froth layer, molten polymer transport, and local regression rate measurements in the recirculation zone. Regression rates near the inlet are less than the mass-averaged values, whereas near the reattachment point the local value exceeds the mass-averaged values. Further, the observed froth layer is as large as 2 mm near the inlet and decreases to sub-millimeter thicknesses near the reattachment point. An analytical heat transfer model is used to quantify the influence of the surface froth layer on the regression rates. Results indicate that the froth layer has an insulating effect and will reduce the local regression rate.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2021

Dispersion curve regression – assisted wideband local wavenumber analysis for characterizing three-dimensional (3D) profile of hidden corrosion damage

Corrosion as common damage in civil, petrochemical, nuclear, and aerospace structures affects the integrity and safety of the structures and may lead to catastrophic failures. This paper presents dispersion curve regression-assisted local wavenumber analysis method, which can analyze the time–space wavefield containing wideband information of wave-damage interaction and further extract the structural information carried by such wavefield for characterizing hidden corrosion damage in an isotropic plate. To acquire the time–space wavefield, a noncontact scanning laser Doppler vibrometer is used. In our analysis method, the acquired time–space wavefield is firstly processed to generate a local wavenumber function. The derived wavenumber function is further analyzed with a dispersion curve regression step, which searches in a set of theoretical frequency-wavenumber dispersion curves for different plate thicknesses and identifies the optimal plate thickness whose theoretical curve best matches the frequency-wavenumber relation contained in the local wavenumber function. By this means, a 3D profile including both in plane and thickness dimensions of the structure can be constructed for corrosion visualization and quantification. The experimental study demonstrates that our method can quantify the profile of hidden uniform corrosion in metal plates in terms of its in-plane shape and size as well as its out-of-plane depth in the subwavelength scale. Moreover, compared to previous Lamb wave-based corrosion inspection methods, our technique allows for noncontact 3D characterization of hidden corrosion from a far distance to the structure. Finally, we believe this work will inspire new 3D damage quantification methods that are based on wavefield analysis as well as enable potential applications for the quantification of hidden corrosion in civil, petrochemical, nuclear, and aerospace structures.

42 ENGINEERING↗
DOE OSTI2023

Characterization of the In Vivo Deuteration of Native Phospholipids by Mass Spectrometry Yields Guidelines for Their Regiospecific Customization

Customization of deuterated biomolecules is vital for many advanced biological experiments including neutron scattering. However, because it is challenging to control the proportion and regiospecificity of deuterium incorporation in live systems, often only two or three synthetic lipids are mixed together to form simplistic model membranes. This limits the applicability and biological accuracy of the results generated with these synthetic membranes. Despite some limited prior examination of deuterating Escherichia coli lipids in vivo, this approach has not been widely implemented. In this report an extensive mass spectrometry-based profiling of E. coli phospholipid deuteration states with several different growth media was performed, and a computational method to describe deuterium distributions with a one-number summary is introduced. The deuteration states of 36 lipid species were quantitatively profiled in 15 different growth conditions, and tandem mass spectrometry was used to reveal deuterium localization. Regressions were employed to enable the prediction of lipid deuteration for untested conditions. Small-angle neutron scattering was performed on select deuterated lipid samples, which validated the deuteration states calculated from the mass spectral data. Based on these experiments, guidelines for the design of specifically deuterated phospholipids are described. This unlocks even greater capabilities from neutron-based techniques, enabling experiments that were formerly impossible.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Refining T c Prediction in Hydrides via Symbolic‐Regression‐Enhanced Electron‐Localization‐Function‐Based Descriptors

Hydrogen‐based materials are able to possess extremely high superconducting critical temperatures, T c s , due to hydrogen's low atomic mass and strong electron–phonon interaction. Recently, a descriptor based on the Electron Localization Function (ELF) has enabled the rapid estimation of the T c of hydrogen‐containing compounds from electronic networking properties, but its applicability has been limited by the small size and homogeneity of the training dataset used. Herein, the model is re‐examined, compiling a publicly available combined dataset of 244 binary and ternary hydride superconductors. The analysis shows that though ELF‐based networking remains a valuable descriptor, its predictive power declines with increasing compositional complexity. However, by introducing the molecularity index, defined as the highest value of the ELF at which two hydrogen atoms connect, and applying symbolic regression, the accuracy of the predictions can be substantially enhanced. These results establish a more robust framework for assessing superconductivity in hydride materials, facilitating accelerated screening of novel candidates through integration with crystal structure prediction methods or high‐throughput searches.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Geographical Insights into Suicide Mortality Through Spatial Machine Learning

Suicide mortality is a leading cause of death in the United States, with an upward trend that emphasizes its significance as a public health issue. Previous research has employed global models like ordinary least squares (OLS) regression and local models such as geographically weighted regression (GWR). While local models are useful for analyzing spatial variations in suicide mortality, they share limitations with traditional global models, particularly about their inability to handle multi-collinearity and non-linear relationships. Machine learning approaches, like random forests (RF), can address some of these limitations but often fail to account for spatial variability. This gap highlights the need for spatial ML models specifically designed to tackle suicide mortality. This research seeks to fill this void by using a geographically weighted random forest model (GWRF) to examine the associations between county-level suicide mortality in the U.S. from 2010 to 2020 and various social and environmental determinants of health. A key aspect of our methodology is disciplined feature selection, which reduces the pool of explanatory variables by about 90%. This refinement enhances the explanatory power of both global (R2 improved from 0.59 to 0.67) and local (R2 improved from 0.64 to 0.67) RF models while reducing their run times. An analysis of the importance scores for these selected features reveals that the drivers of suicide mortality vary by context. Thus, to effectively address regional disparities and inform targeted public health interventions, a holistic approach that incorporates multiple county-level characteristics is essential.

Lebakula, Viswadeep [ORNL] (ORCID:0000000152935914↗
DOE OSTI2022

Photometry on Structured Backgrounds: Local Pixel-wise Infilling by Regression

Photometric pipelines struggle to estimate both the flux and flux uncertainty for stars in the presence of structured backgrounds such as filaments or clouds. However, it is exactly stars in these complex regions that are critical to understanding star formation and the structure of the interstellar medium. We develop a method, similar to Gaussian process regression, which we term local pixel-wise infilling (LPI). Using a local covariance estimate, we predict the background behind each star and the uncertainty of that prediction in order to improve estimates of flux and flux uncertainty. We show the validity of our model on synthetic data and real dust fields. We further demonstrate that the method is stable even in the crowded field limit. While we focus on optical-IR photometry, this method is not restricted to those wavelengths. We apply this technique to the 34 billion detections in the second data release of the Dark Energy Camera Plane Survey. In addition to removing many >3σ outliers and improving uncertainty estimates by a factor of ~2–3 on nebulous fields, we also show that our method is well behaved on uncrowded fields. The entirely post-processing nature of our implementation of LPI photometry allows it to easily improve the flux and flux uncertainty estimates of past as well as future surveys.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

Quantification of Raman-Interfering Polyoxoanions for Process Analysis: Comparison of Different Chemometric Models and a Demonstration on Real Hanford Waste

The Hanford site represents a complicated environmental remediation challenge, remaining from the production of nuclear weapons. Over 100 million gallons of liquid radioactive waste of unknown composition will be chemically processed and vitrified, but the varying chemical composition and highly radioactive nature of the waste preclude the implementation of more developed, offline technologies to determine the composition. The only practical approach to waste treatment will require the significant utilization of real-time, chemometric modeling approaches. Although chemometric approaches have been applied to the analysis of Hanford waste, the models developed were highly tank-specialized, and limited discussion was provided on how models fared with interfering signals. As the tank waste is largely composed of oxoanions, which tend to have interfering Raman spectra, the general question was posed as to what chemometric approach is best suited to accurately quantify analytes in the presence of interfering signals. This was carried out by examining the ability of classical least square (CLS), principal component regression (PCR), partial least square (PLS), and locally weighted regression (LWR) to quantify NO 3 – and CO 3 2– using their bands around 1050 cm –1 . Finally, for all samples, the PLS-based model was found to be the most efficient approach from a model building and application perspective.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Adaptive Online Multivariate Signal Extraction With Locally Weighted Robust Polynomial Regression

High-frequency, multivariate data collected in real-time and used to control or make decisions regarding a process’ operation often contain some noise and outliers. Thus, a method to extract the signal is needed in order to reduce the number and magnitude of control-based adjustments that are implemented. Such a method must be (i) online, depending only on past and current observations; (ii) fast, producing a smooth value more quickly than the measurement frequency; (iii) robust, ignoring brief bursts of erroneously measured values; (iv) multivariate, ignoring observations that are jointly unusual; (v) adaptive, adjusting to periods of rapid fluctuation in the signal versus periods of stability; and (vi) purely data-driven, not incorporating any information about the process from which the data are collected. Most existing methods are only able to address a subset of these six features. Furthermore, we also require the method to be nonlinear, providing a local nonlinear estimate of the signal. In this work, we propose a novel, real-time signal extraction method based on a local, robust polynomial fit. We demonstrate the performance of our method compared to a state-of-the-art competitor through simulation. For illustration, the methodology is applied to data collected from a reverse osmosis water treatment process.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

PCAfold 2.0—Novel tools and algorithms for low-dimensional manifold assessment and optimization

We describe an update to our open-source Python package, PCAfold, designed to help researchers generate, analyze and improve low-dimensional data manifolds. In the current version, PCAfold 2.0, we introduce novel tools and algorithms for assessing and optimizing low-dimensional manifolds. This includes a method that generates a “map” of local feature sizes that can help pinpoint researchers to problematic regions on a manifold. We introduce a novel cost function that characterizes the quality of a manifold topology with a single number. We develop two algorithms for feature selection based on principal component analysis (PCA) that use the cost function as an objective function to minimize. We introduce a quantity of interest (QoI)-aware dimensionality reduction strategy where data projections are computed using an artificial neural network and are directly optimized towards representing various projection-independent and projection-dependent QoIs. We also introduce an implementation of partition of unity networks (POUnets) for efficient reconstruction of QoIs from low-dimensional manifolds based on combining neural network classification with localized polynomial regression. Our software can be broadly applicable in all domains of science and engineering that aim to reduce data dimensionality, as well as in the fundamental research on representation learning.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Raman Spectroscopy Coupled with Chemometric Analysis for Speciation and Quantitative Analysis of Aqueous Phosphoric Acid Systems

Complex chemical systems that exhibit varied and matrix-dependent speciation are notoriously difficult to monitor and characterize on-line and in real-time. Optical spectroscopy is an ideal tool for in situ characterization of chemical species that can enable quantification as well as species identification. Chemometric modeling, a multivariate method, has been successfully paired with optical spectroscopy to enable measurement of analyte concentrations even in complex solutions where univariate methods such as Beer’s law analysis fail. Here, Raman spectroscopy is used to quantify the concentration of phosphoric acid and its three deprotonated forms during a titration. In this system, univariate approaches would be difficult to apply due to multiple species being present simultaneously within the solution as pH is varied. Locally Weighted Regression (LWR) modeling was used to determine phosphate concentration from spectral signature. LWR results, in tandem with Multivariate Curve Resolution modeling, provide direct measurement of the concentration of each phosphate species using only the Raman signal. Furthermore, results are presented within the context of fundamental solution chemistry, including Pitzer equations to compensate for activity coefficients and non-idealities associated with high ionic strength systems.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2020

Learning to Count Grave Sites for Cemetery Observation Models With Satellite Imagery

Understanding how people occupy open spaces is important for research in support of population modeling, policy, national security, emergency response, and sustainability. For the past decade, there has been an increase in research toward capturing and reporting population dynamics and patterns of life at the building level and in some open public spaces such as cemeteries and parks. This is done through observation models developed from local sociocultural information acquired at various spatiotemporal scales to inform night, day, and episodic population occupancy estimates (people/1000 sq ft). Sociocultural information for cemeteries and parks is scarcely available and often collected manually. The process is not only marred by inconsistencies but is laborious and time consuming. In this study, we leverage convolutional neural networks (CNNs) and satellite imagery to derive grave site counts as proxy variables to support scalable and accurate sociocultural data required in a population observation model. Through a hybrid workflow (weak localization plus regression model), we characterize a large scale automation process to counting of grave sites. We evaluate and demonstrate the efficacy of proposed workflow using out-of-data set large satellite imagery and establish its broader impact on cemetery observation models.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2021

The Swan: Data-driven Inference of Stellar Surface Gravities for Cool Stars from Photometric Light Curves

Stellar light curves are well known to encode physical stellar properties. Precise, automated, and computationally inexpensive methods to derive physical parameters from light curves are needed to cope with the large influx of these data from space-based missions such as Kepler and TESS. Here we present a new methodology that we call “The Swan,” a fast, generalizable, and effective approach for deriving stellar surface gravity (logg) for main-sequence, subgiant, and red giant stars from Kepler light curves using local linear regression on the full frequency content of Kepler long-cadence power spectra. With this inexpensive data-driven approach, we recover logg to a precision of ~0.02 dex for 13,822 stars with seismic logg values between 0.2 and 4.4 dex and ~0.11 dex for 4646 stars with Gaia-derived logg values between 2.3 and 4.6 dex. We further develop a signal-to-noise metric and find that granulation is difficult to detect in many cool main-sequence stars (T {sub eff} ≲ 5500 K), in particular K dwarfs. By combining our logg measurements with Gaia radii, we derive empirical masses for 4646 subgiant and main-sequence stars with a median precision of ~7%. Finally, we demonstrate that our method can be used to recover logg to a similar mean absolute deviation precision for a TESS baseline of 27 days. Our methodology can be readily applied to photometric time series observations to infer stellar surface gravities to high precision across evolutionary states.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2022

Lightweight jet reconstruction and identification as an object detection task

We apply object detection techniques based on deep convolutional blocks to end-to-end jet identification and reconstruction tasks encountered at the CERN large hadron collider (LHC). Collision events produced at the LHC and represented as an image composed of calorimeter and tracker cells are given as an input to a Single Shot Detection network. The algorithm, named PFJet-SSD performs simultaneous localization, classification and regression tasks to cluster jets and reconstruct their features. This all-in-one single feed-forward pass gives advantages in terms of execution time and an improved accuracy w.r.t. traditional rule-based methods. A further gain is obtained from network slimming, homogeneous quantization, and optimized runtime for meeting memory and latency constraints of a typical real-time processing environment. We experiment with 8-bit and ternary quantization, benchmarking their accuracy and inference latency against a single-precision floating-point. We show that the ternary network closely matches the performance of its full-precision equivalent and outperforms the state-of-the-art rule-based algorithm. Finally, we report the inference latency on different hardware platforms and discuss future applications.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2021

Plateau Phenomenon in Gradient Descent Training of RELU Networks: Explanation, Quantification, and Avoidance

The ability of neural networks to provide ‘best in class’ approximation across a wide range of applications is well-documented. Nevertheless, the powerful expressivity of neural networks comes to naught if one is unable to effectively train (choose) the parameters defining the network. In general, neural networks are trained by gradient descent type optimization methods,a stochastic variant thereof. In practice, such methods result in the loss function decreases rapidly at the beginning of training but then, after a relatively small number of steps, significantly slow down. The loss may even appear to stagnate over the period of a large number of epochs, only to then suddenly start to decrease fast again for no apparent reason. This so-called plateau phenomenon manifests itself in many learning tasks. The present work aims to identify and quantify the root causes of plateau phenomenon.analysis is carried out in the setting of univariate ReLU networks. No assumptions are made on the number of neurons relative to the number of training data, and our results hold for both the lazy and adaptive regimes. Here, the main findings are: plateaux correspond to periods during which activation patterns remain constant, where activation pattern refers to the number of data points that activate a given neuron; quantification of convergence of the gradient flow dynamics; and, characterization stationary points in terms solutions of local least squares regression lines over subsets of the training data. Based on these conclusions, we propose a new iterative training method, the Active Neuron Least Squares (ANLS), characterised by the explicit adjustment of the activation pattern at each step, which is designed to enable a quick exit from a plateau. Illustrative numerical examples are included throughout.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

ConductorIdentification [SWR-21-58]

This is a novel data-driven model that can identify power system model impedance for local utilities. The model builds a multi-category logistic regression that is trained on local utility secondary system partial GIS data, and then the model can be used to predict the conductor types/impedance for the local utilities secondary models.

Wang, Wenbo↗