Doctor of Philosophy / Department of Statistics / Juan Du / Spatio-temporal and/or multivariate dependence naturally occur in datasets obtained in various disciplines; such as atmospheric sciences, meteorology, engineering and agriculture. There is a great deal of need to effectively model the complex dependence and correlated structure exhibited in these datasets. For this purpose, this dissertation studies methods and application of the spatio-temporal modeling and multivariate computation. First, a collection of spatio-temporal functions is proposed to model spatio-temporal processes which are continuous in space and discrete over time. Theoretically, we derived the necessary and sufficient conditions to ensure the model validity. On the other hand, the possibility of taking the advantage of well-established time series and spatial statistics tools makes it relatively easy to identify and fit the proposed model in practice. The spatio-temporal models with some ARMA discrete temporal margin are fitted to Kansas precipitation and Irish wind datasets for estimation or prediction, and compared with some general existing parametric models in terms of likelihood and mean squared prediction error. Second, to deal with the immense computational burden of statistical inference for multi- ple attributes recorded at a large number of locations, we develop Wendland-type compactly supported covariance matrix function models and propose multivariate covariance tapering technique with those functions for computation reduction. Simulation studies and US tem- perature data are used to illustrate applications of the proposed multivariate tapering and computational gain in spatial cokriging. Finally, to study the impact of weather change on corn yield in Kansas, we develop a spatial functional linear regression model accounting for the fact that weather data were recorded daily or hourly as opposed to the yearly crop yield data and the underlying spatial autocorrelation. The parameter function is estimated under the functional data analysis framework and its characteristics are investigated to show the influential factor and critical period of weather change dictating crop yield during the growing season.

This thesis focuses on two topics, computational methods for large spatial datasets and functional data ranking. Both are tackling the challenges of big and high-dimensional data. The first topic is motivated by the prohibitive computational burden in fitting Gaussian process models to large and irregularly spaced spatial datasets. Various approximation methods have been introduced to reduce the computational cost, but many rely on unrealistic assumptions about the process and retaining statistical efficiency remains an issue. We propose a new scheme to approximate the maximum likelihood estimator and the kriging predictor when the exact computation is infeasible. The proposed method provides different types of hierarchical low-rank approximations that are both computationally and statistically efficient. We explore the improvement of the approximation theoretically and investigate the performance by simulations. For real applications, we analyze a soil moisture dataset with 2 million measurements with the hierarchical low-rank approximation and apply the proposed fast kriging to fill gaps for satellite images. The second topic is motivated by rank-based outlier detection methods for functional data. Compared to magnitude outliers, it is more challenging to detect shape outliers as they are often masked among samples. We develop a new notion of functional data depth by taking the integration of a univariate depth function. Having a form of the integrated depth, it shares many desirable features. Furthermore, the novel formation leads to a useful decomposition for detecting both shape and magnitude outliers. Our simulation studies show the proposed outlier detection procedure outperforms competitors in various outlier models. We also illustrate our methodology using real datasets of curves, images, and video frames. Finally, we introduce the functional data ranking technique to spatio-temporal statistics for visualizing and assessing covariance properties, such as separability and full symmetry. We formulate test functions as functions of temporal lags for each pair of spatial locations and develop a rank-based testing procedure induced by functional data depth for assessing these properties. The method is illustrated using simulated data from widely used spatio-temporal covariance models, as well as real datasets from weather stations and climate model outputs.

Response of flexible structures — such as cable-supported bridges and aircraft wings — is associated with a number of uncertainties in structural and flow parameters. This thesis is aimed at efficient uncertainty quantification in a few such flow and flow-induced structural response problems. First, the uncertainty quantification in the lift force exerted on a submerged body in a potential flow is considered. To this end, a new method — termed here as semi-intrusive stochastic perturbation (SISP) — is proposed. A sensitivity analysis is also performed, where for the global sensitivity analysis (GSA) the Sobol’ indices are used. The polynomial chaos expansion (PCE) is used for estimating these indices. Next, two stability problems —divergence and flutter — in the aeroelasticity are studied in the context of reliability based design optimization (RBDO). Two modifications are proposed to an existing PCE-based metamodel to reduce the computational cost, where the chaos coefficients are estimated using Gauss quadrature to gain computational speed and GSA is used to create nonuniform grid to reduce the cost even further. The proposed method is applied on a rectangular unswept cantilever wing model. Next, reliability computation in limit cycle oscillations (LCOs) is considered. While the metamodel performs poorly in this case due to bimodality in the distribution, a new simulation-based scheme proposed to this end. Accordingly, first a reduced-order model (ROM) is used to identify the critical region in the random parameter space. Then the full-scale expensive model is run only over a this critical region. This is applied to the rectangular unswept cantilever wing with cubic and fifth order stiffness terms in its equation of motion. Next, the wind speed is modeled as a spatio-temporal process, and accordingly new representations of spatio-temporal random processes are proposed based on tensor decompositions of the covariance kernel. These are applied to three problems: a heat equation, a vibration, and a readily available covariance model for wind speed. Finally, to assimilate available field measurement data on wind speed and to predict based on this assimilation, a new framework based on the tensor decompositions is proposed. The framework is successfully applied to a set of measured data on wind speed in Ireland, where the prediction based on simulation is found to be consistent with the observed data.