Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “robust 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 127 records · Page 7

A Robust State Estimation Framework Considering Measurement Correlations and Imperfect Synchronization

This paper develops a robust power system state estimation framework with the consideration of measurement correlations and imperfect synchronization. In the framework, correlations of SCADA and PMU measurements are calculated separately through unscented transformation and a vector autoregression (VAR) model. In particular, PMU measurements during the waiting period of two SCADA measurement scans are buffered to develop the VAR model. The latter takes into account the temporal and spatial correlations of PMU measurements and provides redundant measurements to suppress bad data and mitigate imperfect synchronization. In case of synchronization issues between SCADA and PMU measurements, either forecasted PMU measurements or prior SCADA measurements from the last estimation run are leveraged to restore system observability. After that, robust generalized maximum-likelihood (GM)-estimator is developed to integrate full measurement correlations and handle bad data in SCADA and PMU measurements. Thanks to the robustness and flexibility of the proposed robust estimator, bad data as well as imperfect measurement synchronization are mitigated, yielding high statistical efficiency. Comprehensive comparison results with other alternatives under various conditions demonstrate the benefits of the proposed framework.

Zhao, Junbo (ORCID:0000000284989666)↗

Residuals-based distributionally robust optimization with covariate information

We consider data-driven approaches that integrate a machine learning prediction model within distributionally robust optimization (DRO) given limited joint observations of uncertain parameters and covariates. Our framework is flexible in the sense that it can accommodate a variety of regression setups and DRO ambiguity sets. We investigate asymptotic and finite sample properties of solutions obtained using Wasserstein, sample robust optimization, and phi-divergence-based ambiguity sets within our DRO formulations, and explore cross-validation approaches for sizing these ambiguity sets. Through numerical experiments, we validate our theoretical results, study the effectiveness of our approaches for sizing ambiguity sets, and illustrate the benefits of our DRO formulations in the limited data regime even when the prediction model is misspecified.

97 MATHEMATICS AND COMPUTING↗

Residuals-based distributionally robust optimization with covariate information

We consider data-driven approaches that integrate a machine learning prediction model within distributionally robust optimization (DRO) given limited joint observations of uncertain parameters and covariates. Our framework is flexible in the sense that it can accommodate a variety of regression setups and DRO ambiguity sets. We investigate asymptotic and finite sample properties of solutions obtained using Wasserstein, sample robust optimization, and phi-divergence-based ambiguity sets within our DRO formulations, and explore cross-validation approaches for sizing these ambiguity sets. Through numerical experiments, we validate our theoretical results, study the effectiveness of our approaches for sizing ambiguity sets, and illustrate the benefits of our DRO formulations in the limited data regime even when the prediction model is misspecified.

97 MATHEMATICS AND COMPUTING↗

Discovering nuclear models from symbolic machine learning

Numerous phenomenological nuclear models have been proposed to describe specific observables within different regions of the nuclear chart. However, developing a unified model that describes the complex behavior of all nuclei remains an open challenge. Here, we explore whether symbolic Machine Learning (ML) can rediscover traditional nuclear physics models or identify alternatives with improved simplicity, fidelity, and predictive power. To address this challenge, we developed a Multi-objective Iterated Symbolic Regression approach that handles symbolic regressions over multiple target observables, accounts for experimental uncertainties and is robust against high-dimensional problems. As a proof of principle, we applied this method to describe the nuclear binding energies and charge radii of light and medium mass nuclei. Our approach identified simple analytical relationships based on the number of protons and neutrons, providing interpretable models with precision comparable to state-of-the-art nuclear models. Additionally, we integrated this ML-discovered model with an existing complementary model to estimate the limits of nuclear stability. These results highlight the potential of symbolic ML to develop accurate nuclear models and guide our description of complex many-body problems.

Nuclear structure↗

Data-Driven Mean-Corrected Recursive Estimation-Based Optimal DER Dispatch for Distribution System Voltage Control

Recent advances in smart inverters offer opportunities to mitigate adverse grid impacts caused by high penetrations of distributed photovoltaics (PV) in distribution grids, such as voltage violations. Here, this paper proposes a novel measurement-driven optimal power flow (OPF)-based distributed energy resource management system (DERMS) voltage regulation via recursive sensitivity estimation informed coordinated control of distributed PV inverters. The proposed approach leverages available grid and controllable DER measurements, eliminating reliance on system model information while being adaptive and robust to volatile operating conditions. A mean-corrected recursive ridge regression (MCRRR) algorithm is proposed for sensitivity estimation, continuously refining the sensitivity model through a closed-form solution. It effectively manages varying grid operating conditions, such as changes in power injections and topology reconfiguration, to facilitate a time-varying update of the Load Sensitivity Factors (LSF). The proposed approach is formulated as a linear programming (LP) problem and is thus scalable to larger-scale distribution systems. Its effectiveness and efficiency are demonstrated on a realistic distribution feeder with high PV penetrations in Southern California, USA.

14 SOLAR ENERGY↗

Efficient Probabilistic Prediction and Uncertainty Quantification of Tropical Cyclone–Driven Storm Tides and Inundation

Abstract This study proposes and assesses a methodology to obtain high-quality probabilistic predictions and uncertainty information of near-landfall tropical cyclone–driven (TC-driven) storm tide and inundation with limited time and resources. Forecasts of TC track, intensity, and size are perturbed according to quasi-random Korobov sequences of historical forecast errors with assumed Gaussian and uniform statistical distributions. These perturbations are run in an ensemble of hydrodynamic storm tide model simulations. The resulting set of maximum water surface elevations are dimensionality reduced using Karhunen–Loève expansions and then used as a training set to develop a polynomial chaos (PC) surrogate model from which global sensitivities and probabilistic predictions can be extracted. The maximum water surface elevation is extrapolated over dry points incorporating energy head loss with distance to properly train the surrogate for predicting inundation. We find that the surrogate constructed with third-order PCs using elastic net penalized regression with leave-one-out cross validation provides the most robust fit across training and test sets. Probabilistic predictions of maximum water surface elevation and inundation area by the surrogate model at 48-h lead time for three past U.S. landfalling hurricanes (Irma in 2017, Florence in 2018, and Laura in 2020) are found to be reliable when compared to best track hindcast simulation results, even when trained with as few as 19 samples. The maximum water surface elevation is most sensitive to perpendicular track-offset errors for all three storms. Laura is also highly sensitive to storm size and has the least reliable prediction. Significance Statement The purpose of this study is to develop and evaluate a methodology that can be used to provide high-quality probabilistic predictions of hurricane-induced storm tide and inundation with limited time and resources. This is important for emergency management purposes during or after the landfall of hurricanes. Our results show that sampling forecast errors using quasi-random sequences combined with machine learning techniques that fit polynomial functions to the data are well suited to this task. The polynomial functions also have the benefit of producing exact sensitivity indices of storm tide and inundation to the forecasted hurricane properties such as path, intensity, and size, which can be used for uncertainty estimation. The code implementing the presented methodology is publicly available on GitHub.

54 ENVIRONMENTAL SCIENCES↗

Spirometric traits show quantile-dependent heritability, which may contribute to their gene-environment interactions with smoking and pollution

Background: “Quantile-dependent expressivity” refers to a genetic effect that is dependent upon whether the phenotype (e.g., spirometric data) is high or low relative to its population distribution. Forced vital capacity (FVC), forced expiratory volume in 1 second (FEV 1 ), and the FEV 1 /FVC ratio are moderately heritable spirometric traits. The aim of the analyses is to test whether their heritability (h 2 ) is constant over all quantiles of their distribution. Methods: Quantile regression was applied to the mean age, sex, height and smoking-adjusted spirometric data over multiple visits in 9,993 offspring-parent pairs and 1,930 sibships from the Framingham Heart Study to obtain robust estimates of offspring-parent (β OP ), offspring-midparent (β OM ), and full-sib regression slopes (β FS ). Nonparametric significance levels were obtained from 1,000 bootstrap samples. β OP s were used as simple indicators of quantile-specific heritability (i.e.,h 2 = 2β OP /(1+r spouse ), where r spouse was the correlation between spouses). Results: β OP ± standard error (SE) decreased by 0.0009 ± 0.0003 (P = 0.003) with every one-percent increment in the population distribution of FEV 1 /FVC, i.e., β OP ± SE were: 0.182 ± 0.031, 0.152 ± 0.015; 0.136 ± 0.011; 0.121 ± 0.013; and 0.099 ± 0.013 at the 10th, 25th, 50th, 75th, and 90th percentiles of the FEV 1 /FVC distribution, respectively. These correspond to h 2 ± SEs of 0.350 ± 0.060 at the 10th, 0.292 ± 0.029 at the 25th, 0.262 ± 0.020 at the 50th, 0.234 ± 0.025 at the 75th, and 0.191 ± 0.025 at the 90th percentiles of the FEV 1 /FVC ratio. Maximum mid-expiratory flow (MMEF) h 2 ± SEs increased 0.0025 ± 0.0007 (P = 0.0004) with every one-percent increment in its distribution, i.e.: 0.467 ± 0.046, 0.467 ± 0.033, 0.554 ± 0.038, 0.615 ± 0.042, and 0.675 ± 0.060 at the 10th, 25th, 50th, 75th, and 90th percentiles of its distribution. This was due to forced expiratory flow at 75% of FVC (FEF75%), whose quantile-specific h 2 increased an average of 0.0042 ± 0.0008 for every one-percent increment in its distribution. It is speculated that previously reported gene-environment interactions may be partially attributable to quantile-specific h 2 , i.e., greater heritability in individuals with lower FEV 1 /FVC due to smoking or airborne particles exposure vs. nonsmoking, unexposed individuals. Conclusion: Heritabilities of FEV 1 /FVC, MMEF, and FEF75% from quantile-regression of offspring-parent and sibling spirometric data suggest their quantile-dependent expressivity.

59 BASIC BIOLOGICAL SCIENCES↗

The dissolution behavior of borosilicate glasses in far-from equilibrium conditions

In far-from-equilibrium conditions, the dissolution of borosilicate glasses used to immobilize nuclear waste is known to be a function of both temperature and pH. The aim of this paper is to study effects of these variables on three model waste glasses (SON68, ISG, AFCI). To do this, experiments were conducted at temperatures of 23, 40, 70, and 90 °C and pH(RT) values of 9, 10, 11, and 12 with the single-pass flow-through (SPFT) test method. The results from these tests were then used to parameterize a kinetic rate model based on transition state theory. Both the absolute dissolution rates and the rate model parameters are compared with previous results. Discrepancies in the absolute dissolution rates as compared to those obtained using other test methods are discussed. Rate model parameters for the three glasses studied here are nearly equivalent within error and in relative agreement with previous studies. The results were analyzed with a linear multivariate regression (LMR) and a nonlinear multivariate regression performed with the use of the Glass Corrosion Modeling Tool (GCMT), which is capable of providing a robust uncertainty analysis. This robust analysis highlights the high degree of correlation of various parameters in the kinetic rate model. As more data are obtained on borosilicate glasses with varying compositions, the effect of glass composition on the rate parameter values could possibly be obtained. This would allow for the possibility of predicting the forward dissolution rate of glass based solely on composition

Neeway, James J.↗

Gaussian processes with built-in dimensionality reduction: Applications to high-dimensional uncertainty propagation

Uncertainty quantification (UQ) tasks, such as model calibration, uncertainty propagation, and optimization under uncertainty, typically require several thousand evaluations of the underlying computer codes. To cope with the cost of simulations, one replaces the real response surface with a cheap surrogate based, e.g., on polynomial chaos expansions, neural networks, support vector machines, or Gaussian processes (GP). However, the number of simulations required to learn a generic multivariate response grows exponentially as the input dimension increases. This curse of dimensionality can only be addressed, if the response exhibits some special structure that can be discovered and exploited. A wide range of physical responses exhibit a special structure known as an active subspace (AS). An AS is a linear manifold of the stochastic space characterized by maximal response variation. The idea is that one should first identify this low dimensional manifold, project the high-dimensional input onto it, and then link the projection to the output. If the dimensionality of the AS is low enough, then learning the link function is a much easier problem than the original problem of learning a high-dimensional function. The classic approach to discovering the AS requires gradient information, a fact that severely limits its applicability. Furthermore, and partly because of its reliance to gradients, it is not able to handle noisy observations. The latter is an essential trait if one wants to be able to propagate uncertainty through stochastic simulators, e.g., through molecular dynamics codes. In this work, we develop a probabilistic version of AS which is gradient-free and robust to observational noise. Our approach relies on a novel Gaussian process regression with built-in dimensionality reduction. In particular, the AS is represented as an orthogonal projection matrix that serves as yet another covariance function hyper-parameter to be estimated from the data. To train the model, we design a two-step maximum likelihood optimization procedure that ensures the orthogonality of the projection matrix by exploiting recent results on the Stiefel manifold, i.e., the manifold of matrices with orthogonal columns. The additional benefit of our probabilistic formulation, is that it allows us to select the dimensionality of the AS via the Bayesian information criterion. We validate our approach by showing that it can discover the right AS in synthetic examples without gradient information using both noiseless and noisy observations. We demonstrate that our method is able to discover the same AS as the classical approach in a challenging one-hundred-dimensional problem involving an elliptic stochastic partial differential equation with random conductivity. Finally, we use our approach to study the effect of geometric and material uncertainties in the propagation of solitary waves in a one dimensional granular system.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Predictive Equations for Adult Pulmonary Function in Zhejiang Province, China

Background. Accurate interpretation of lung function tests requires appropriate spirometry reference values derived from large-scale population-specific epidemiological surveys. The aim of this cross-sectional study was to establish normal spirometric values for the population of healthy, nonsmoking Han Chinese adults residing in Zhejiang province, China. Methods. We measured lung function parameters such as forced expiratory volume in 1 s, forced vital capacity, peak expiratory flow, maximal midexpiratory flow, and diffusion capacity for carbon monoxide and considered age, height, and weight as independent factors that may modify these parameters. The clinical data were divided into the study arm and validation group. The study arms were used to construct predictive equations using stepwise multiple linear regression, and data from the validation group were used to assess the robustness of the equations. Results. The 3866 participants were randomized into a study arm (n = 1,949) and a validation arm (n = 1,917). Lung function parameters had a negative association with age and a positive association with height. Data from the two groups were similar. Predictive equations were constructed from the study arm, and the validation group was used to test the feasibility of the reference equations. Conclusions. The reference values we derived can be used to evaluate lung function in this cohort in both epidemiological studies and clinical practice.

Dong, Li↗

The Impact of City-level Permitting Processes on Residential Photovoltaic Installation Prices and Development Times: An Empirical Analysis of Solar Systems in California Cities

Business process or “soft” costs account for well over 50% of the installed price of residential photovoltaic (PV) systems in the United States, so understanding these costs is crucial for identifying PV cost-reduction opportunities. Among these costs are those imposed by city-level permitting processes, which may add both expense and time to the PV development process. Building on previous research, this study evaluates the effect of city-level permitting processes on the installed price of residential PV systems and on the time required to develop and install those systems. The study uses a unique dataset from the U.S. Department of Energy’s Rooftop Solar Challenge Program, which includes city-level permitting process “scores,” plus data from the California Solar Initiative and the U.S. Census. Econometric methods are used to quantify the price and development-time effects of city-level permitting processes on more than 3,000 PV installations across 44 California cities in 2011. Results indicate that city-level permitting processes have a substantial and statistically significant effect on average installation prices and project development times. The results suggest that cities with the most favorable (i.e., highest-scoring) permitting practices can reduce average residential PV prices by $0.27–$0.77/W (4%–12% of median PV prices in California) compared with cities with the most onerous (i.e., lowest-scoring) permitting practices, depending on the regression model used. Though the empirical models for development times are less robust, results suggest that the most streamlined permitting practices may shorten development times by around 24 days on average (25% of the median development time). These findings illustrate the potential price and development-time benefits of streamlining local permitting procedures for PV systems.

14 SOLAR ENERGY↗

Joint Modeling of Quasar Variability and Accretion Disk Reprocessing Using Latent Stochastic Differential Equations

Quasars are bright active galactic nuclei powered by the accretion of matter around supermassive black holes at the center of galaxies. Their stochastic brightness variability depends on the physical properties of the accretion disk and black hole. The upcoming Rubin Observatory Legacy Survey of Space and Time (LSST) is expected to observe tens of millions of quasars, so there is a need for efficient techniques like machine learning that can handle the large volume of data. Quasar variability is believed to be driven by an X-ray corona, which is reprocessed by the accretion disk and emitted as UV/optical variability. We are the first to introduce an auto-differentiable simulation of the accretion disk and reprocessing. We use the simulation as a direct component of our neural network to jointly model the driving variability and reprocessing, trained with supervised learning on simulated LSST-like 10 yr quasar light curves. We encode the light curves using a transformer encoder, and the driving variability is reconstructed using latent stochastic differential equations, a physically motivated generative deep learning method that can model continuous-time stochastic dynamics. By embedding the physical processes of the driving signal and reprocessing into our network, we achieve a model that is more robust and interpretable. We demonstrate that our model outperforms a Gaussian process regression baseline and can infer accretion disk parameters and time delays between wave bands, even for out-of-distribution driving signals. Our approach provides a powerful framework that can be adapted to solve other inverse problems in multivariate time series.

Fagin, Joshua [City Univ. of New York (CUNY), NY (↗

Data-Driven Security Assessment of Power Grids Based on Machine Learning Approach: Preprint

Data-driven security assessment provides key indicators on power system stability using simulations on scheduling models, as opposed to dynamic simulations that are more time-consuming. This paper investigates data-driven security assessment of power grids based on machine learning. Multivariate random forest regression is used as the machine learning algorithm due to its high robustness to the input data. Three stability issues are analyzed using the proposed machine learning tool, including transient stability, frequency stability and small signal stability. The estimation values from machine learning tool are compared with those from dynamic simulations. Results show that the proposed machine learning tool can effectively predict the stability margins for the three stability metrics.

14 SOLAR ENERGY↗

Fuzzy Integration of Support Vector Regression Models for Anticipatory Control of Complex Energy Systems

Anticipatory control systems are a class of systems whose decisions are based on predictions for the future state of the system under monitoring. Anticipation denotes intelligence and is an inherent property of humans that make decisions by projecting in future. Likewise, artificially intelligent systems equipped with predictive functions may be utilized for anticipating future states of complex systems, and therefore facilitate automated control decisions. Anticipatory control of complex energy systems is paramount to their normal and safe operation. In this paper a new intelligent methodology integrating fuzzy inference with support vector regression is introduced. Our proposed methodology implements an anticipatory system aiming at controlling energy systems in a robust way. Initially a set of support vector regressors is adopted for making predictions over critical system parameters. Furthermore, the predicted values are fed into a two stage fuzzy inference system that makes decisions regarding the state of the energy system. The inference system integrates the individual predictions into a single one at its first stage, and outputs a decision together with a certainty factor computed at its second stage. The certainty factor is an index of the significance of the decision. The proposed anticipatory control system is tested on a real world set of data obtained from a complex energy system, describing the degradation of a turbine. Results exhibit the robustness of the proposed system in controlling complex energy systems.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

A data-driven approach to real-time vertical position estimation for NSTX-U vertical stability control

In this paper, a database of 77 996 plasma equilibrium reconstructions from 727 discharges during the initial operation of the NSTX-U spherical tokamak is analyzed to develop a statistically robust model of the plasma vertical position for real-time control. A variety of regression models are developed and tested, ranging in complexity from linear models to deep neural networks, and including input signals ranging from the four pairs of flux loops used historically on NSTX-U up to the full set of 389 real-time signals available to the plasma control system. A linear model based on 140 real-time magnetics signals is found to offer excellent accuracy, with a coefficient of determination R 2 = 0.906. The robustness of this model to limited training data, new operating scenarios, and signal errors is tested, and a procedure is demonstrated to tune the model parameters to optimize its robustness. A time-dependent plasma equilibrium solver, TokaMaker, is used to simulate vertical stability control in NSTX-U, demonstrating that it should be possible to iteratively tune the parameters of a linear vertical position model to stabilize both positive and negative triangularity plasmas in future experiments.

magnetic diagnostics↗

Signatures of naturally induced variability in the atmosphere using multiple reanalysis datasets

A multiple linear regression analysis of nine different reanalysis datasets has been performed to test the robustness of variability associated with volcanic eruptions, the El Niño Southern Oscillation, the Quasi-Biennial Oscillation and with a specific focus on the 11-year solar cycle. The analysis covers both the stratosphere and troposphere and extends over the period 1979–2009. The characteristic signals of all four sources of variability are remarkably consistent between the datasets and confirm the responses seen in previous analyses. In general, the solar signatures reported are primarily due to the assimilation of observations, rather than the underlying forecast model used in the reanalysis system. Analysis of the 11-year solar response in the lower stratosphere confirms the existence of the equatorial temperature maximum, although there is less consistency in the upper stratosphere, probably reflecting the reduced level of assimilated data there. The solar modulation of the polar jet oscillation is also evident, but only significant during February. In the troposphere, vertically banded anomalies in zonal mean zonal winds are seen in all the reanalyses, with easterly anomalies at 30°N and 30°S suggesting a weaker and possibly broader Hadley circulation under solar maximum conditions. This structure is present in the annual signal and is particularly evident in NH wintertime. As well as the ‘top-down’ solar contribution to Northern Annular Mode variability, we show the potential contribution from the surface conditions allowing for a ‘bottom-up’ pathway. Finally, the reanalyses are compared with both observed global-mean temperatures from the Stratospheric Sounding Unit (SSU) and from the latest general circulation models from CMIP-5. The SSU samples the stratosphere over three different altitudes, and the 11-year solar cycle fingerprint is identified in these observations using detection and attribution techniques.

54 ENVIRONMENTAL SCIENCES↗

Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentials

We present a new interatomic potential for solids and liquids called Spectral Neighbor Analysis Potential (SNAP). The SNAP potential has a very general form and uses machine-learning techniques to reproduce the energies, forces, and stress tensors of a large set of small configurations of atoms, which are obtained using high-accuracy quantum electronic structure (QM) calculations. The local environment of each atom is characterized by a set of bispectrum components of the local neighbor density projected onto a basis of hyperspherical harmonics in four dimensions. The bispectrum components are the same bond-orientational order parameters employed by the GAP potential [1]. The SNAP potential, unlike GAP, assumes a linear relationship between atom energy and bispectrum components. The linear SNAP coefficients are determined using weighted least-squares linear regression against the full QM training set. This allows the SNAP potential to be fit in a robust, automated manner to large QM data sets using many bispectrum components. The calculation of the bispectrum components and the SNAP potential are implemented in the LAMMPS parallel molecular dynamics code. We demonstrate that a previously unnoticed symmetry property can be exploited to reduce the computational cost of the force calculations by more than one order of magnitude. We present results for a SNAP potential for tantalum, showing that it accurately reproduces a range of commonly calculated properties of both the crystalline solid and the liquid phases. In addition, unlike simpler existing potentials, SNAP correctly predicts the energy barrier for screw dislocation migration in BCC tantalum.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Evaluating 239 Pu(n,f) cross sections via machine learning using experimental data, covariances, and measurement features

In this paper, the neutron-induced 239 Pu fission cross section, 239 Pu(n,f), is evaluated from 1–20 MeV using experimental data and associated covariances while also considering information on the measurement, termed features here. For instance, methods to determine the background, sample backing material, or impurities in the sample, are explicitly taken into account in the evaluation process. To this end, outliers in the experimental data are identified with a modified version of the Hybrid Robust Support Vector Machine. In a second step, two machine learning methods (logistic regression with elastic net regularization and random forest regression with SHAP feature importance metric) are used to highlight measurement features that are common among many of the outlying data points. Based on this analysis, penalty uncertainties are added to the experimental covariances of outlying data points that have outlier measurement features and are put through the generalized-least-squares evaluation. The resulting evaluated mean values and covariances differ distinctly from those data evaluated without the penalty uncertainties. These results highlight that certain measurement features should be more closely examined.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗