Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Multivariate 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 OSTI2023

Large-Scale Inference of Multivariate Regression for Heavy-Tailed and Asymmetric Data

Large-scale multivariate regression is a fundamental statistical tool with a wide range of applications. Here, this study considers the problem of simultaneously testing a large number of general linear hypotheses, encompassing covariate-effect analysis, analysis of variance, and model comparisons. The challenge that accompanies a large number of tests is the ubiquitous presence of heavy-tailed and/or highly skewed measurement noise, which is the main reason for the failure of conventional least squares-based methods. For large-scale multivariate regression, we develop a set of robust inference methods to explore data features such as heavy tailedness and skewness, which are not visible to least squares methods. The new testing procedure is based on the data-adaptive Huber regression and a new covariance estimator of regression estimates. Under mild conditions, we show that our methods produce consistent estimates of the false discovery proportion. Extensive numerical experiments and an empirical study on quantitative linguistics demonstrate the advantage of the proposed method over many state-of-the-art methods when the data are generated from heavy-tailed and/or skewed distributions.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Estimating Sparse Direct Effects in Multivariate Regression With the Spike-and-Slab LASSO

The multivariate regression interpretation of the Gaussian chain graph model simultaneously parametrizes (i) the direct effects of p predictors on q outcomes and (ii) the residual partial covariances between pairs of outcomes. We introduce a new method for fitting sparse versions of these models with spike-and-slab LASSO (SSL) priors. We develop an Expectation Conditional Maximization algorithm to obtain sparse estimates of the p × q matrix of direct effects and the q × q residual precision matrix. Our algorithm iteratively solves a sequence of penalized maximum likelihood problems with self-adaptive penalties that gradually filter out negligible regression coefficients and partial covariances. Because it adaptively penalizes individual model parameters, our method is seen to outperform fixed-penalty competitors on simulated data. We establish the posterior contraction rate for our model, buttressing our method’s excellent empirical performance with strong theoretical guarantees. Using our method, we estimated the direct effects of diet and residence type on the composition of the gut microbiome of elderly adults.

EM algorithm↗
DOE OSTI2021

Fast and Non-Destructive Determination of Water Content in Ionic Liquids at Varying Temperatures by Raman Spectroscopy and Multivariate Regression Analysis

Imidazolium acetate ionic liquids (ILs) have been utilized as promising solvents in many applications that involve varying water content and temperature. These experimental variables affect the anion-cation intermolecular interactions, which in turn influence the performance of the ILs in these applications. Here, this paper shows Raman spectroscopy can be used as an operando method to measure water content in IL solvents when simultaneous temperature changes may occur. The Raman spectra of 1-alkyl-3-methylimidazolium acetate ILs (alkyl chain length n = 2, 4, 6, 8) with varying water content (from 0.028 to 0.899 water mole fraction) and temperature (from 78.1 K to 423.1 K) were measured. Increasing the water content or decreasing the temperature of the tested ILs weakens the anion-cation intermolecular interactions. The water content of these ILs can be quantified even in conditions when the temperature is changing using Raman spectroscopy combined with multivariate regression analysis, including principal component regression (PCR), partial-least-squares regression (PLSR), and artificial neural networks (ANNs). The ANN model combined with partial-least-squares (PLS) achieves the highest prediction accuracy of water content in ILs at varying temperatures (RMSECV = 0.017, R 2 CV = 99.1%, RMSEP = 0.019, R 2 P = 98.8%, RPD = 8.93). Raman spectroscopy provides a potential fast non-destructive operando method to monitor the water content of ILs even in applications when the temperature may be simultaneously altered; this information can lead to the optimized use of these ILs in many applications.

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

Uncertainty quantification in multivariable regression for material property prediction with Bayesian neural networks

With the increased use of data-driven approaches and machine learning-based methods in material science, the importance of reliable uncertainty quantification (UQ) of the predicted variables for informed decision-making cannot be overstated. UQ in material property prediction poses unique challenges, including multi-scale and multi-physics nature of materials, intricate interactions between numerous factors, limited availability of large curated datasets, etc. In this work, we introduce a physics-informed Bayesian Neural Networks (BNNs) approach for UQ, which integrates knowledge from governing laws in materials to guide the models toward physically consistent predictions. To evaluate the approach, we present case studies for predicting the creep rupture life of steel alloys. Experimental validation with three datasets of creep tests demonstrates that this method produces point predictions and uncertainty estimations that are competitive or exceed the performance of conventional UQ methods such as Gaussian Process Regression. Additionally, we evaluate the suitability of employing UQ in an active learning scenario and report competitive performance. The most promising framework for creep life prediction is BNNs based on Markov Chain Monte Carlo approximation of the posterior distribution of network parameters, as it provided more reliable results in comparison to BNNs based on variational inference approximation or related NNs with probabilistic outputs.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Supervised machine learning-based multivariate regression of parallel closures for a high-collisionality deuterium-carbon plasma

Many plasmas of interest in laboratory experiments and space consist of multiple ion species. In tokamak edge plasmas, for instance, ionized impurities expelled from the vessel wall influence plasma transport. When describing multi-species plasmas using fluid equations, we need accurate closure relations to close the set of fluid equations. In this study, we introduce the development of fitting formulas for parallel closures using supervised machine learning, in conjunction with the recent closure theory, considering multi-ion collisions and arbitrary ion temperatures. We apply this approach to a high-collisionality deuterium-carbon plasma and demonstrate its effectiveness. As a result, the machine learning-based method for developing practical and accurate closures can be extended to a wider range of plasmas.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

Comparing Designed Training Sets to Optimize Multivariate Regression Models for Pr, Nd, and Nitric Acid Using Spectrophotometry

Chemometric regression models were developed for the quantification of praseodymium (Pr, 0–1000 µg/mL), neodymium (Nd, 0–1000 µg/mL), and nitric acid (HNO 3 , 0.1–5 M) using spectrophotometry. Designed calibration sets were composed of 20 samples each: 10 model points and 10 lack-of-fit (LOF) points. The D-optimal designs effectively minimized the number of samples required to build models, and each design resulted in similar prediction performance, suggesting that statistical design of experiments can provide a reliable framework for selecting training set samples in three-variable systems. Partial least squares regression (PLSR) models were validated against a one-factor-at-a-time validation set composed of 125 samples (three variables, five levels). The top PLS-1 models resulted in average percent root mean square error of prediction error values of 3.5%, 1.7%, and 1.2% for Pr(III), Nd(III), and HNO 3 , respectively. Power set augmentations of the model and LOF samples were investigated to optimize the number of training set samples. PLSR models built using just required model points (10) had similar predictive capabilities as models including the LOF points (20) but with fewer samples. The number of validation samples was also varied systematically to learn how many samples are needed to validate regression models. This work addresses long-standing questions in the field of chemometrics to help make this approach amenable to the near-real-time quantification of hazardous species in remote settings.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Multivariate regression modelling for gender prediction using volatile organic compounds from hand odor profiles via HS-SPME-GC-MS

The efficacy of using human volatile organic compounds (VOCs) as a form of forensic evidence has been well demonstrated with canines for crime scene response, suspect identification, and location checking. Although the use of human scent evidence in the field is well established, the laboratory evaluation of human VOC profiles has been limited. This study used Headspace-Solid Phase Microextraction-Gas Chromatography-Mass Spectrometry (HS-SPME-GC-MS) to analyze human hand odor samples collected from 60 individuals (30 Females and 30 Males). The human volatiles collected from the palm surfaces of each subject were interpreted for classification and prediction of gender. The volatile organic compound (VOC) signatures from subjects’ hand odor profiles were evaluated with supervised dimensional reduction techniques: Partial Least Squares-Discriminant Analysis (PLS-DA), Orthogonal-Projections to Latent Structures Discriminant Analysis (OPLS-DA), and Linear Discriminant Analysis (LDA). The PLS-DA 2D model demonstrated clustering amongst male and female subjects. The addition of a third component to the PLS-DA model revealed clustering and minimal separation of male and female subjects in the 3D PLS-DA model. The OPLS-DA model displayed discrimination and clustering amongst gender groups with leave one out cross validation (LOOCV) and 95% confidence regions surrounding clustered groups without overlap. The LDA had a 96.67% accuracy rate for female and male subjects. The culminating knowledge establishes a working model for the prediction of donor class characteristics using human scent hand odor profiles.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Assessing heterogeneity of patient and health system delay among TB in a population with internal migrants in China

Backgrounds The diagnostic delay of tuberculosis (TB) contributes to further transmission and impedes the implementation of the End TB Strategy. Therefore, we aimed to describe the characteristics of patient delay, health system delay, and total delay among TB patients in Shanghai, identify areas at high risk for delay, and explore the potential factors of long delay at individual and spatial levels. Method The study included TB patients among migrants and residents in Shanghai between January 2010 and December 2018. Patient and health system delays exceeding 14 days and total delays exceeding 28 days were defined as long delays. Time trends of long delays were evaluated by Joinpoint regression. Multivariable logistic regression analysis was employed to analyze influencing factors of long delays. Spatial analysis of delays was conducted using ArcGIS, and the hierarchical Bayesian spatial model was utilized to explore associated spatial factors. Results Overall, 61,050 TB patients were notified during the study period. Median patient, health system, and total delays were 12 days (IQR: 3–26), 9 days (IQR: 4–18), and 27 days (IQR: 15–43), respectively. Migrants, females, older adults, symptomatic visits to TB-designated facilities, and pathogen-positive were associated with longer patient delays, while pathogen-negative, active case findings and symptomatic visits to non-TB-designated facilities were associated with long health system delays (LHD). Spatial analysis revealed Chongming Island was a hotspot for patient delay, while western areas of Shanghai, with a high proportion of internal migrants and industrial parks, were at high risk for LHD. The application of rapid molecular diagnostic methods was associated with reduced health system delays. Conclusion Despite a relatively shorter diagnostic delay of TB than in the other regions in China, there was vital social-demographic and spatial heterogeneity in the occurrence of long delays in Shanghai. While the active case finding and rapid molecular diagnosis reduced the delay, novel targeted interventions are still required to address the challenges of TB diagnosis among both migrants and residents in this urban setting.

Sun, Ruoyao↗
DOE OSTI2025

Data and code from: Multivariate bayesian regression model for predicting disposed ash composition at U.S. coal fired power stations

This dataset contains the code and data files needed for implementation of a Multivariate Bayesian Regression model, described in Jin et al. (2025), for the historical prediction of the chemical composition of disposed coal ash at U.S. coal fired power plants as a function of annualized coal purchase data. The integrated coal supply data file (CoalSupplyDataset.csv) represents a compilation of monthly fuel purchase records for the period 1973-2022 at major U.S. power stations. These records were obtained from the U.S. Energy Information Administration. The CSV file also contains, for each coal purchase record, the coal region of the mine as defined by the U.S. Geological Survey. Data entry errors and data gaps in the EIA records were corrected as described in Jin et al. This CSV file represents the integrated coal supply data after corrections were made. The model structure and fitting parameters are encoded in pickle file format (Bayesian.pkl). The model was developed with the coal supply data and coal ash composition data, apportioned according to the Stratified Shuffle Split for training and testing subsets. The model was built using Python and the PyMC library. Reference Publication: Jin, Z.; Huang, J.; Hower, J.C.; Hsu-Kim, H.(2025). Predictive Assessment of the Chemical Composition of Coal Ash in Reserve at U.S. Disposal Sites. Environmental Science & Technology.

Coal ash composition↗
DOE OSTI2025

Multiclass Classification Using Bayesian Multivariate Adaptive Regression Splines

We present a new Bayesian model for the problem of multiclass classification. In this model, the probabilities of class membership of a given observation are determined by the mean of a latent Gaussian distribution. The mean functions of this latent distribution consist of combinations of highly flexible basis functions of the inputs: multivariate adaptive regression splines (MARS), first developed for multiple regression. We use reversible jump Markov chain Monte Carlo to make inference on the classification model, including the number of basis functions. We compare the probabilistic classification performance of our proposed approach to existing methods on simulated and benchmark data, and compare uncertainty estimates on simulated data. Our proposed method compares favorably with existing Bayesian and frequentist multiclass classification methods in out-of-sample probabilistic classification, and uncertainty estimation of these probabilistic classifications. We examine the fit of the proposed method to a data set of hurricane storm surge levels near Delaware Bay, US, and conclude that sea level rise is a key contributor to damage delivered by storm surge.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Remote quantification of Cm(III) and HNO 3 by fluorescence spectroscopy and chemometrics

A unique approach to remotely quantify Cm(III) (0–100 µg mL −1 ) in HNO 3 (1–12 M) using steady-state laser fluorescence spectroscopy and multivariate regression models was developed. Photoluminescence is amenable to remote measurements using fiber-optic cables and is sensitive to numerous lanthanide and actinide species. In-line measurements can provide feedback to support complex processing in harsh environments (e.g., hot cells) to help guide and optimize radiochemical separations. In this work, Cm(III) spectra were acquired remotely in a glove box as a function of HNO 3 concentration to better understand spectral characteristics and evaluate the utility of multivariate regression models in this system. Furthermore, the Cm(III) fluorescence peak shape, width, position, and intensity changed significantly as a function of HNO 3 concentration, likely because of the displacement of emission quenching inner-sphere water molecules and complexation with nitrate ions. Despite significant covariance and nonlinearity in the data, a D-optimal design strategy successfully minimized training set sample size and was used to build effective partial least squares regression models for Cm(III) and HNO 3 concentrations without a priori knowledge of solution conditions. Chemometrics for modeling complex fluorescence spectra are promising and may find widespread applicability for online analysis in numerous chemical systems found in the nuclear field.

Actinide↗
DOE OSTI2022

Responsiveness of miscanthus and switchgrass yields to stand age and nitrogen fertilization: A meta‐regression analysis

Abstract Optimal management of the perennial bioenergy crops, miscanthus and switchgrass, requires an understanding of their responsiveness to nitrogen (N) fertilizer at different maturity stages across locations and growing conditions. Earlier studies that have examined the yield response of these crops to N and stand age using field experiments or meta‐analysis techniques provide mixed evidence. We extend earlier studies by applying a multi‐level mixed‐effects (MLME) meta‐regression model to conduct a more extensive multivariate regression of yield response of these crops to N and stand age, while controlling for climate and location conditions and unobserved factors related to study design. Our findings are based on 1403 and 2811 yield observations for miscanthus and switchgrass, respectively, from experiments conducted between 2002 and 2019 across the rainfed region in the United States. We find statistically significant evidence that an additional year of maturity increases miscanthus and switchgrass yields but at a decreasing rate; yields peak at the 7th and 6th year respectively, for the observed range of applied N rates and stands. We also find that an increase in N application increases yield by a statistically significant level, but at a declining rate; the magnitude of the yield response to N is, however, small and varies with the age of the crop. The impact of N is larger on older compared to younger and middle‐aged stands of miscanthus. In contrast, the impact of N on switchgrass is larger on middle‐aged compared to younger and older stands of switchgrass. We do not find a statistically significant effect of soil productivity on yield for either crop. This analysis provides a basis for developing N application recommendations and optimal rotation age for miscanthus and switchgrass and shows that these energy crops can grow just as productively on low productivity land as on high productivity land.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Post-landing major element quantification using SuperCam laser induced breakdown spectroscopy

The SuperCam instrument on the Perseverance Mars 2020 rover uses a pulsed 1064 nm laser to ablate targets at a distance and conduct laser induced breakdown spectroscopy (LIBS) by analyzing the light from the resulting plasma. SuperCam LIBS spectra are preprocessed to remove ambient light, noise, and the continuum signal present in LIBS observations. Prior to quantification, spectra are masked to remove noisier spectrometer regions and spectra are normalized to minimize signal fluctuations and effects of target distance. In some cases, the spectra are also standardized or binned prior to quantification. To determine quantitative elemental compositions of diverse geologic materials at Jezero crater, Mars, we use a suite of 1198 laboratory spectra of 334 well-characterized reference samples. The samples were selected to span a wide range of compositions and include typical silicate rocks, pure minerals (e.g., silicates, sulfates, carbonates, oxides), more unusual compositions (e.g., Mn ore and sodalite), and replicates of the sintered SuperCam calibration targets (SCCTs) onboard the rover. For each major element (SiO 2 , TiO 2 , Al 2 O 3 , FeO T , MgO, CaO, Na 2 O, K 2 O), the database was subdivided into five “folds” with similar distributions of the element of interest. One fold was held out as an independent test set, and the remaining four folds were used to optimize multivariate regression models relating the spectrum to the composition. We considered a variety of models, and selected several for further investigation for each element, based primarily on the root mean squared error of prediction (RMSEP) on the test set, when analyzed at 3 m. In cases with several models of comparable performance at 3 m, we incorporated the SCCT performance at different distances to choose the preferred model. Shortly after landing on Mars and collecting initial spectra of geologic targets, we selected one model per element. Subsequently, with additional data from geologic targets, some models were revised to ensure results that are more consistent with geochemical constraints. The calibration discussed here is a snapshot of an ongoing effort to deliver the most accurate chemical compositions with SuperCam LIBS.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Risk Ratio and Risk Difference Estimation in Case-cohort Studies

Background: In case-cohort studies with binary outcomes, ordinary logistic regression analyses have been widely used because of their computational simplicity. However, the resultant odds ratio estimates cannot be interpreted as relative risk measures unless the event rate is low. The risk ratio and risk difference are more favorable outcome measures that are directly interpreted as effect measures without the rare disease assumption. Methods: We provide pseudo-Poisson and pseudo-normal linear regression methods for estimating risk ratios and risk differences in analyses of case-cohort studies. These multivariate regression models are fitted by weighting the inverses of sampling probabilities. Also, the precisions of the risk ratio and risk difference estimators can be improved using auxiliary variable information, specifically by adapting the calibrated or estimated weights, which are readily measured on all samples from the whole cohort. Finally, we provide computational code in R (R Foundation for Statistical Computing, Vienna, Austria) that can easily perform these methods. Results: Through numerical analyses of artificially simulated data and the National Wilms Tumor Study data, accurate risk ratio and risk difference estimates were obtained using the pseudo-Poisson and pseudo-normal linear regression methods. Also, using the auxiliary variable information from the whole cohort, precisions of these estimators were markedly improved. Conclusion: The ordinary logistic regression analyses may provide uninterpretable effect measure estimates, and the risk ratio and risk difference estimation methods are effective alternative approaches for case-cohort studies. These methods are especially recommended under situations in which the event rate is not low.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2025

Monitoring Sulfuric Acid and Temperature Using Raman Spectroscopy and Multivariate Chemometrics

Multivariate regression models were optimized for the quantification of sulfuric acid (H 2 SO 4 ) [0–8 M] and temperature (20 °C–80 °C) in the presence of ammonium sulfate ((NH 4 ) 2 SO 4 [0–0.6 M]) using Raman spectroscopy. Optical vibrational spectroscopy is a useful nondestructive technique for the in situ analysis of complex chemical systems notoriously difficult to monitor in situ and in real-time. Multivariate analysis, a chemometrics method, can be paired with these nondestructive optical methods for determining analyte concentration and speciation in complex solutions, such as dissociated species in polyprotic acids, e.g., H 2 SO 4 . The effect of temperature is often overlooked although it can have a major influence on speciation and the corresponding Raman spectra. Here, in this study, partial least squares regression models were optimized for the quantification of H 2 SO 4 and its two deprotonated forms as a function of temperature. Measuring bisulfate as a function of temperature is particularly challenging owing to changes in the second dissociation constant. A designed training set effectively minimized the sample set size and trained a robust predictive model with percent root mean square error of <3% for H 2 SO 4 . The practical strategy employed here was demonstrated to be effective for building chemometric models that directly account for dynamic temperatures with static samples and is shown to be amenable to flow cell analysis applications with a simple calibration transfer for process monitoring applications.

D-optimal design↗
DOE OSTI2020

An Exploratory Approach Using Regression and Machine Learning in the Analysis of Mass Absorption Cross Section of Black Carbon Aerosols: Model Development and Evaluation

Mass absorption cross-section of black carbon (MAC BC ) describes the absorptive cross-section per unit mass of black carbon, and is, thus, an essential parameter to estimate the radiative forcing of black carbon. Many studies have sought to estimate MAC BC from a theoretical perspective, but these studies require the knowledge of a set of aerosol properties, which are difficult and/or labor-intensive to measure. We therefore investigate the ability of seven data analytical approaches (including different multivariate regressions, support vector machine, and neural networks) in predicting MAC BC for both ambient and biomass burning measurements. Our model utilizes multi-wavelength light absorption and scattering as well as the aerosol size distributions as input variables to predict MAC BC across different wavelengths. We assessed the applicability of the proposed approaches in estimating MAC BC using different statistical metrics (such as coefficient of determination (R 2 ), mean square error (MSE), fractional error, and fractional bias). Overall, the approaches used in this study can estimate MAC BC appropriately, but the prediction performance varies across approaches and atmospheric environments. Based on an uncertainty evaluation of our models and the empirical and theoretical approaches to predict MAC BC , we preliminarily put forth support vector machine (SVM) as a recommended data analytical technique for use. We provide an operational tool built with the approaches presented in this paper to facilitate this procedure for future users.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Simultaneous quantification of uranium( VI ), samarium, nitric acid, and temperature with combined ensemble learning, laser fluorescence, and Raman scattering for real-time monitoring

In this work, laser-induced fluorescence spectroscopy (LIFS), Raman spectroscopy, and a stacked regression ensemble was developed for near real-time quantification of uranium(VI) (1–100 μg mL –1 ), samarium (0–200 μg mL –1 ) and nitric acid (0.1–4 M) with varying temperature (20 °C–45 °C). LIFS applications range from fundamental lab-scale studies to real-time process monitoring at industrial levels, such as nuclear reprocessing applications, provided the phenomena affecting the fluorescence spectrum are accounted for (e.g., absorption, quenching, complexation). Multiple chemometric models were examined and compared to a more traditional multivariate regression approach called partial least squares (PLS). Results obtained on synthetic samples selected using D-optimal experimental design indicated that a stacked regression method, which included ridge regression, random forest, PLS, and an eXtreme gradient boost algorithm, successfully measured uranium(VI) concentrations directly in nitric acid without measuring luminescence lifetimes or standard addition. The top model resulted in percent root-mean-square error of prediction values of 5.2, 1.9, 3.0, and 2.3% for U(VI), Sm 3+ , HNO 3 , and temperature, respectively. The approach may be useful for quantifying fluorescent fission products (e.g., Sm 3+ ) to provide information on burnup of irradiated nuclear fuel. This novel framework reinforces the applicability of LIFS for real-time applications in nuclear fuel cycle applications.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗
DOE OSTI2021

Cross-national analysis of food security drivers: comparing results based on the Food Insecurity Experience Scale and Global Food Security Index

Abstract The second UN Sustainable Development Goal establishes food security as a priority for governments, multilateral organizations, and NGOs. These institutions track national-level food security performance with an array of metrics and weigh intervention options considering the leverage of many possible drivers. We studied the relationships between several candidate drivers and two response variables based on prominent measures of national food security: the 2019 Global Food Security Index (GFSI) and the Food Insecurity Experience Scale’s (FIES) estimate of the percentage of a nation’s population experiencing food security or mild food insecurity (FI ). We compared the contributions of explanatory variables in regressions predicting both response variables, and we further tested the stability of our results to changes in explanatory variable selection and in the countries included in regression model training and testing. At the cross-national level, the quantity and quality of a nation’s agricultural land were not predictive of either food security metric. We found mixed evidence that per-capita cereal production, per-hectare cereal yield, an aggregate governance metric, logistics performance, and extent of paid employment work were predictive of national food security. Household spending as measured by per-capita final consumption expenditure (HFCE) was consistently the strongest driver among those studied, alone explaining a median of 92% and 70% of variation (based on out-of-sample R 2 ) in GFSI and FI , respectively. The relative strength of HFCE as a predictor was observed for both response variables and was independent of the countries used for model training, the transformations applied to the explanatory variables prior to model training, and the variable selection technique used to specify multivariate regressions. The results of this cross-national analysis reinforce previous research supportive of a causal mechanism where, in the absence of exceptional local factors, an increase in income drives increase in food security. However, the strength of this effect varies depending on the countries included in regression model fitting. We demonstrate that using multiple response metrics, repeated random sampling of input data, and iterative variable selection facilitates a convergence of evidence approach to analyzing food security drivers.

42 ENGINEERING↗