In time-series analyses, particularly for finance, generalized autoregressive conditional heteroscedasticity (GARCH) models are widely applied statistical tools for modelling volatility clusters (i.e., periods of increased or decreased risk). In contrast, it has not been considered to be of critical importance until now to model spatial dependence in the conditional second moments. Only a few models have been proposed for modelling local clusters of increased risks. In this paper, we introduce novel spatial GARCH and exponential GARCH processes in a unified spatial and spatiotemporal GARCH-type model, which also covers all previously proposed spatial ARCH models as well as time-series GARCH models. For this common modelling framework, estimators are derived based on nonlinear least squares and on the maximum-likelihood approach. In addition to the theoretical contributions of this paper, we suggest a model selection strategy that is verified by a series of Monte Carlo simulation studies. Eventually, the use of the unified model is demonstrated by an empirical example that focuses on real estate prices from 1995 to 2014 across the ZIP-Code areas of Berlin. A spatial autoregressive model is applied to the data to illustrate how locally varying model uncertainties can be captured by the spatial GARCH-type models.
In this paper, we introduce a new spatial model that incorporates heteroscedastic variance depending on neighboring locations. The proposed process is regarded as the spatial equivalent to the temporal autoregressive conditional heteroscedasticity (ARCH) model. We show additionally how the introduced spatial ARCH model can be used in spatiotemporal settings. In contrast to the temporal ARCH model, in which the distribution is known given the full information set of the prior periods, the distribution is not straightforward in the spatial and spatiotemporal setting. However, it is possible to e…
This paper introduces a multivariate spatiotemporal autoregressive conditional heteroscedasticity (ARCH) model based on a vec-representation. The model includes instantaneous spatial autoregressive spill-over effects in the conditional variance, as they are usually present in spatial econometric applications. Furthermore, spatial and temporal cross-variable effects are explicitly modelled. We transform the model to a multivariate spatiotemporal autoregressive model using a log-squared transformation and derive a consistent quasi-maximum-likelihood estimator (QMLE). For finite samples and diffe…
Large-scale behavior of a wide class of spatial and spatiotemporal processes is characterized in terms of informational measures. Specifically, subordinated random fields defined by non-linear transformations on the family of homogeneous and isotropic Lancaster-Sarmanov random fields are studied under long-range dependence (LRD) assumptions. In the spatial case, it is shown that Shannon mutual information beween marginal distributions for infinitely increasing distance, which can be properly interpreted as a measure of macroscale structural complexity and diversity, has an asymptotic power dec…
In this paper, we propose a two-step lasso estimation approach to estimate the full spatial weights matrix of spatiotemporal autoregressive models. In addition, we allow for an unknown number of structural breaks in the local means of each spatial locations. The proposed approach jointly estimates the spatial dependence, all structural breaks, and the local mean levels. In addition, it is easy to compute the suggested estimators, because of a convex objective function resulting from a slight simplification. Via simulation studies, we show the finite-sample performance of the estimators and pro…
Effective marine spatial plans require information on the distribution and abundance of biological resources that are potentially vulnerable to anthropogenic change. In North America, spatially-explicit abundance estimates of marine birds are necessary to assess potential impacts from planned offshore wind energy developments (OWED). Sea ducks are particularly relevant in this context as populations of most North American species are below historic levels and European studies suggest OWEDs. We modelled species occupancy using a generalized additive model and conditional abundance with generali…
Friedrich Schiller University Jena（耶拿弗里德里希·席勒大学）；Ludwig-Maximilians-Universität München（慕尼黑路德维希-马克西米利安大学）；TU Dortmund University（多特蒙德工业大学）
Spatial and spatiotemporal machine-learning models require a suitable framework for their model assessment, model selection, and hyperparameter tuning, in order to avoid error estimation bias and over-fitting. This contribution reviews the state-of-the-art in spatial and spatiotemporal cross-validation, and introduces the {R} package {mlr3spatiotempcv} as an extension package of the machine-learning framework {mlr3}. Currently various {R} packages implementing different spatiotemporal partitioning strategies exist: {blockCV}, {CAST}, {skmeans} and {sperrorest}. The goal of {mlr3spatiotempcv} i…
The burst of demand for TNCs has significantly changed the transportation landscape and dramatically disrupted the Vehicle for Hire (VFH) market that used to be dominated by taxicabs for many years. Since first being introduced by Uber in 2009, ridesourcing companies have rapidly penetrated the market. This paper aims to investigate temporal and spatial patterns in taxi and TNC usage based on data at the taxi zone level in New York City. Specifically, we fit suitable time series models to estimate the temporal patterns. Next, we filter out the temporal effects and investigate spatial dependenc…
Modeling the dynamics of real-world physical systems is critical for spatiotemporal prediction tasks, but challenging when data is limited. The scarcity of real-world data and the difficulty in reproducing the data distribution hinder directly applying meta-learning techniques. Although the knowledge of governing partial differential equations (PDE) of data can be helpful for the fast adaptation to few observations, it is mostly infeasible to exactly find the equation for observations in real-world physical systems. In this work, we propose a framework, physics-aware meta-learning with auxilia…
Discovering Latent Causal Graphs from Spatiotemporal Data
Department of Computer Science and Engineering, University of California, San Diego, La Jolla, USA（计算机科学与工程系，加州大学圣地亚哥分校，拉乔拉，美国）；Halıcıoglu Data Science Institute, University of California, San Diego, La Jolla, USA（Halıcıoglu数据科学研究所，加州大学圣地亚哥分校，拉乔拉，美国）；Scripps Institution of Oceanography, University of California, San Diego, La Jolla, USA（斯克里普斯海洋研究所，加州大学圣地亚哥分校，拉乔拉，美国）
Seismic inversion refers to the process of estimating reservoir rock properties from seismic reflection data. Conventional and machine learning-based inversion workflows usually work in a trace-by-trace fashion on seismic data, utilizing little to no information from the spatial structure of seismic images. We propose a deep learning-based seismic inversion workflow that models each seismic trace not only temporally but also spatially. This utilizes information-relatedness in seismic traces in depth and spatial directions to make efficient rock property estimations. We empirically compare our …
ProGen: Revisiting Probabilistic Spatial-Temporal Time Series Forecasting from a Continuous Generative Perspective Using Stochastic Differential Equations
Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
Transformer with Koopman-Enhanced Graph Convolutional Network for Spatiotemporal Dynamics Forecasting
Charles F. Dolan School of Business, Fairfield University（Fairfield大学商学院）；Department of Industrial & Systems Engineering, The University of Tennessee（田纳西大学工业与系统工程系）
A large number of scientific studies and engineering problems involve high-dimensional spatiotemporal data with complicated relationships. In this paper, we focus on a type of space-time interaction named \emph{temporal evolution of spatial dependence (TESD)}, which is a zero time-lag spatiotemporal covariance. For this purpose, we propose a novel Bayesian nonparametric method based on non-stationary spatiotemporal Gaussian process (STGP). The classic STGP has a covariance kernel separable in space and time, failed to characterize TESD. More recent works on non-separable STGP treat location an…
Spatiotemporal gene expression data of the human brain offer insights on the spa- tial and temporal patterns of gene regulation during brain development. Most existing methods for analyzing these data consider spatial and temporal profiles separately with the implicit assumption that different brain regions develop in similar trajectories, and that the spatial patterns of gene expression remain similar at different time points. Al- though these analyses may help delineate gene regulation either spatially or temporally, they are not able to characterize heterogeneity in temporal dynamics across…
Kernel smoothing is a highly flexible and popular approach for estimation of probability density and intensity functions of continuous spatial data. In this role it also forms an integral part of estimation of functionals such as the density-ratio or "relative risk" surface. Originally developed with the epidemiological motivation of examining fluctuations in disease risk based on samples of cases and controls collected over a given geographical region, such functions have also been successfully employed across a diverse range of disciplines where a relative comparison of spatial density funct…
Inverse problems with spatiotemporal observations are ubiquitous in scientific studies and engineering applications. In these spatiotemporal inverse problems, observed multivariate time series are used to infer parameters of physical or biological interests. Traditional solutions for these problems often ignore the spatial or temporal correlations in the data (static model), or simply model the data summarized over time (time-averaged model). In either case, the data information that contains the spatiotemporal interactions is not fully utilized for parameter learning, which leads to insuffici…
Scalable Bayesian Spatiotemporal Tensor Modeling for Censored and Missing Areal Data
Pontificia Universidad Católica de Chile（智利天主教 Pontificia 大学）；National Chung Hsing University（国立中兴大学）；China Medical University（中国医药大学）；University of Connecticut（康涅狄格大学）
Large wildfires pose a major environmental concern, and precise maps of fire risk can improve disaster relief planning. Fosberg Fire Weather Index (FFWI) is often used to measure wildfire risk; FFWI exhibits non-Gaussian marginal distributions as well as strong spatiotemporal extremal dependence and thus, modeling FFWI using geostatistical models like Gaussian processes is questionable. Extreme value theory (EVT)-driven models like max-stable processes are theoretically appealing but are computationally demanding and applicable only for threshold exceedances or block maxima. Disaster managemen…
