Measuring Impacts of Condition Variables in Rule‐Based Models of Space‐Time Choice Behavior: Method and Empirical Illustration

The use of rule‐based systems for modeling space‐time choice has gained increasing research interests over the last years. The potential advantage of the rule‐based approach is that it can handle interactions between a large set of predictors. Decision tree induction methods are available and have been explored for deriving rules from data. However, the complexity of the structures that are generated by such knowledge discovery methods hampers an interpretation of the rule‐set in behavioral terms with as a consequence that the models typically remain a black box. To solve this problem, this paper develops a method for measuring the size and direction of the impact of condition variables on the choice variable as predicted by the model. The paper illustrates the method based on location and transport‐mode choice models that are part of Albatross model—an activity‐based model of space‐time choice.     

A Dynamic Spatial Weight Matrix and Localized Space–Time Autoregressive Integrated Moving Average for Network Modeling

Various statistical model specifications for describing spatiotemporal processes have been proposed over the years, including the space–time autoregressive integrated moving average (STARIMA) and its various extensions. These model specifications assume that the correlation in data can be adequately described by parameters that are globally fixed spatially and/or temporally. They are inadequate for cases in which the correlations among data are dynamic and heterogeneous, such as network data. The aim of this article is to describe autocorrelation in network data with a dynamic spatial weight matrix and a localized STARIMA model that captures the autocorrelation locally (heterogeneity) and dynamically (nonstationarity). The specification is tested with traffic data collected for central London. The result shows that the performance of estimation and prediction is improved compared with standard STARIMA models that are widely used for space–time modeling. En los últimos años, se han propuesto diversas especificaciones de modelado estadístico para describir procesos espacio‐temporales. Esto incluye el modelo espacio‐temporal autorregresivo integrado de media móvil (STARIMA) y sus varios derivados. Estas especificaciones de modelo asumen que la correlación de los datos puede ser adecuadamente descrita por parámetros que se fijan a nivel global en el espacio y/o tiempo. Dichos parámetros son inadecuados para los casos en los que las correlaciones entre los datos son dinámicas y heterogéneas, como en el contexto de los datos de la red. El objetivo de este artículo es describir la autocorrelación en los datos de red con una matriz de ponderación espacial dinámica y un modelo STARIMA localizado (LSTARIMA) que captura la autocorrelación local (heterogeneidad) de forma dinámica (no estacionariedad). La especificación del modelo es evaluada con datos de tráfico recolectados en el centro de Londres. Los resultados demuestran que los rendimientos de estimación y predicción mejoran con el método propuesto en comparación con los modelos STARIMA estándar que son ampliamente utilizados para el modelado de espacio‐temporal. 通过设定多种统计模型来描述地理时空过程已提出多年,包括时空自回归移动平均(STARIMA)及其变形。此类模型通过假设数据相关性可由在时间域或者空间域上全局不变的参数加以充分描述。因此,上述模型不适用于具有动态或异质相关性的数据,如网络数据。本文试图采用一个动态空间权重矩阵与局部时空自回归移动平均(LSTARIMA)模型来描述数据的自相关程度,以此捕捉局域自相关(异质性)和动态自相关(非平稳性)。以伦敦市中心的交通数据作为模型的实证案例的测试结果显示,相对于广泛应用于时空过程分析的标准STARIMA模型,本文的模型在参数估计和预测性能上均有提升。     

Continuous‐Time Modeling with Spatial Dependence

(Spatial) panel data are routinely modeled in discrete time (DT). However, compelling arguments exist for continuous‐time (CT) modeling of (spatial) panel data. Particularly, most social processes evolve in CT, so that statistical analysis in DT is an oversimplification, gives an incomplete representation of reality, and may lead to misinterpretation of estimation results. The most compelling reason for a CT approach is that, in contrast to DT modeling, it allows adequate modeling of dynamic adjustment processes. This article introduces spatial dependence in a CT modeling framework. We propose a nonlinear structural equation model (SEM) with latent variables for estimation of the exact discrete model (EDM), which links CT model parameters to DT observations. The use of a SEM with latent variables enables a specification that accounts for measurement errors in the variables, leading to a reduction of attenuation bias (i.e., disattenuation). The SEM‐CT model with spatial dependence developed here is the first dynamic SEM with spatial dependence. A simple regional labor market model for Germany, comprising changes in unemployment and population as endogenous state variables, and changes in regional average wages and in the structure of the manufacturing sector as exogenous input variables, illustrates this spatial econometric SEM‐CT framework. El modelamiento de datos panel espaciales se realiza habitualmente utilizando una conceptualización del tiempo discreto (TD). Sin embargo, existen argumentos de peso para conceptualizar el tiempo de manera continua (TC). En concreto, la mayoría de procesos sociales se desarrolla en TC, por lo que el análisis estadístico en DT trae como consecuencia una simplificación excesiva de los procesos, da una representación incompleta de la realidad, y puede conducir a una interpretación errónea de los resultados de la estimación. La razón más convincente para el uso de un enfoque CT es que a diferencia de modelos DT, una conceptualización CT permite el modelado adecuado de los procesos de ajuste dinámico (dynamic adjustment). Este artículo incorpora la dependencia espacial en un marco de modelamiento con CT. Los autores proponen un modelo de ecuaciones estructurales no lineal (nonlinear structural equation model ‐SEM) con variables latentes para la estimación del modelo discreto exacto (exact discrete model‐EDM), que vincula los parámetros del modelo CT a las observaciones de DT. El uso de un SEM con variables latentes permite una especificación que da cuenta de los errores de medición en las variables, dando lugar a una reducción del sesgo de atenuación (es decir, “desatenuacion”). El modelo SEM‐CT con dependencia espacial desarrollado en el presente estudio es el primer SEM dinámico con dependencia espacial. Para ilustrar el marco conceptual SEM‐CT los autores presentan un modelo simple del mercado laboral regional de Alemania. El modelo está compuesto por los cambios en el desempleo y la población como variables endógenas de estado, y los cambios en los salarios regionales promedio y en la estructura del sector manufacturero como variables de entrada exógenas. （空间）面板数据通常基于离散时间（DT）进行建模。然而更令人信服的观点是基于连续时间（CT）进行（空间）面板数据建模。特别是多数社会过程均在连续时间中演化,基于离散时间的统计分析可能过度简化,使得对现实状况的表达不完备,并可能导致对估计结果的错误解释。相比于离散时间（DT）建模,连续时间（CT）建模最具说服力的原因在于在建模过程中允许足够多的动态调整。本文介绍了CT模型框架中的空间依赖性。把CT模型参数链接到DT观察值中,我们提出了用于估计精确离散模型（EDM）的包含潜变量的非线性结构方程模型（SEM）。包含潜在变量的SEM提供了变量测量误差的计算方案,使得衰减偏差（如反衰减性）减小。本文了提出的空间相关SEM‐CT模型是第一个动态空间相关的SEM模型,并以德国一个简单的区域劳动力市场模型为例,以失业和人口构成变化为内生状态变量,以区域平均工资和制造业结构部门变化为外生输入变量,阐述了该空间计量SEM‐ CT模型的框架。     

Analyzing Space–Time Crime Incidents Using Eigenvector Spatial Filtering: An Application to Vehicle Burglary

Poisson models generally are utilized in analyzing spatial patterns of crime count data. When spatial autocorrelation is present, these models are extended to account for it. Among various methods, eigenvector spatial filtering (ESF) furnishes an efficient means of analysis. However, because space–time crime data have temporal components as well as spatial components, Poisson models need to be further adjusted to reflect the two types of components simultaneously. This article discusses how the ESF method can be utilized to model space–time crime data, extending the generalized linear mixed model specification for it. This approach is illustrated with an application to space–time vehicle burglary incidents in the city of Plano, Texas, during 2004–2009. Los modelos de Poisson generalmente se utilizan en el análisis de los patrones espaciales de los datos de recuento de crimen. Cuando hay autocorrelación espacial, estos modelos son modificados para dar cuenta de ello. Entre los diversos métodos existentes, el método Eigenvector (autovector, vector propio) de filtrado espacial (Eigenvector Spatial Filtering‐ESF) proporciona un medio eficaz para dicho análisis. Sin embargo, dado que los datos de criminalidad espacio‐temporales tienen tanto componentes temporales como espaciales, los modelos tipo Poisson requieren de un ajuste adicional para reflejar ambos tipos de componentes de manera simultánea. El artículo presente expone cómo el método ESF puede ser utilizado para modelar datos espacio‐temporales sobre delitos mediante la modificación del modelo mixto lineal generalizado (Generalized Linear Mixed Model‐GLMM). El procedimiento propuesto se ilustra con el caso de incidentes espacio‐temporales de robos de vehículos en la ciudad de Plano, Texas, durante 2004–2009. 泊松模型一般用于犯罪计数数据的空间模式分析中,当空间自相关关系呈现时,这类模型可扩展以解释潜在的分布特征。在各种模型中,特征向量空间滤波（ESF）提供了一种有效的分析方法。然而,由于时空犯罪数据包含时间和空间组分,因此泊松模型需要进一步调整以同时反映这两种不同类型的数据。本文讨论了如何利用特征向量空间滤波(ESF)模型对时空犯罪数据进行建模,并采用扩展广义线性混合模型(GLMM)进行规范。最后,以德克萨斯州普莱诺市2004‐2009年的车辆盗窃案数据进行了实证验证。     

Geographically Weighted Extreme Learning Machine: A Method for Space–Time Prediction

Spatial heterogeneity has been regarded as an important issue in space–time prediction. Although some statistical methods of space–time predictions have been proposed to address spatial heterogeneity, the linear assumption makes it difficult for these methods to predict geographical processes accurately because geographical processes always involve complicated nonlinear characteristics. An extreme learning machine (ELM) has the advantage of approximating nonlinear relationships with a rapid learning speed and excellent generalization performance. However, determining how to incorporate spatial heterogeneity into an ELM to predict space–time data is an urgent problem. For this purpose, a new method called geographically weighted ELM (GWELM) is proposed to address spatial heterogeneity based on an ELM in this article. GWELM is essentially a locally varying ELM in which the parameters are regarded as functions of spatial locations, and geographically weighted least squares is applied to estimate the parameters in a local model. The proposed method is used to analyze two groups of different data sets, and the results demonstrate that the GWELM method is superior to the comparative method, which is also developed to address spatial heterogeneity.     

Chronotope,Story, and Historical Geography: Mikhail Bakhtin and the Space‐Time of Narratives

Abstract: This article studies space‐time as revealed in narrative, especially narrative intended to validate truth claims. Narrative plot is uniquely suited to capturing truths about time, causal complexity, and space. Bakhtin's “chronotope” (space‐time), which bridges plot, narrated events, and the real world, is critical to understanding this capacity, whether in fiction, in histories, or in didactic stories, myths, and parables. The chronotope is underutilized in the social sciences, but disputes over indigenous land in Canada exemplify its potential applications. To fully capture these heteroglot (“many‐voiced”) conflicts, factual verification should not be the only test of a narrative's truthfulness.     

MultiLevel Modeling of Space–Time Variations: Exploring Landslide Voting Patterns at United States Presidential Elections, 1992–2016

Much has been written about the polarization of the American electorate and its reflection in its legislatures, but less about its spatial polarization, which Bishop has argued has taken place in parallel with the ideological and behavioral polarization. The extent of that polarization can be assessed, he argues, by identifying the number of landslide counties, those won at presidential elections by margins of 20 percentage points or more. This paper uses a multilevel modeling strategy to explore changes in the number and extent of those landslide counties over the period 1992–2016, relative to both the location of the counties and their population composition. It shows that a county’s population composition was a major determinant of whether it returned a landslide for either party’s candidate at any election—with a clear change in direction over the period for counties according to their level of affluence—but this was by no means the sole determinant. Holding constant those variations there were additional geographies that were more place‐ than people‐specific.     

Space–Time Sequential Similarity for Identifying Factors of Activity‐Travel Pattern Segmentation: A Measure of Sequence Alignment and Path Similarity

The article develops a new method that compares activity‐travel patterns in both terms of the sequential order of activities and the shape of activity‐travel trajectory in time and space. The similarity of the list of activities and their order between activity‐travel patterns are computed by a sequence alignment method. The shape of activity‐travel trajectory is compared between the patterns using a path similarity technique that captures the direction and speed of a movement from the current location and the duration of staying at each location. The comparison results, therefore capture how people move around in three‐dimensional space–time choreography that indicates how people conduct which activities in what order. A total of 1,000 individuals are sampled from the data of 2016 Household Travel Survey, South Korea. The data provide the information of individual activity‐travel behavior and personal characteristics. The suggested method computes the pairwise distance matrix, and Ward clustering algorithm segments the pattern groups of similar activity sequences and space–time trajectories. A CHAID analysis then associates personal and household characteristics with the pattern groups to identify important factors for the segmentation. The analysis provides a significant implication in both terms of research and practice in transportation.     

Nonlinear Multivariate Spatial Modeling Using NLPCA and Pair‐Copulas

A novel geostatistical modeling approach is developed to model nonlinear multivariate spatial dependence using nonlinear principal component analysis (NLPCA) and pair‐copulas. In spatial studies, multivariate measurements are frequently collected at each location. The dependence between such measurements can be complex. In this article, a multivariate geostatistical model is developed that can capture both nonlinear spatial dependence across locations and nonlinear dependence between measurements at a particular location. Nonlinear multivariate dependence between spatial variables is removed using NLPCA. Subsequently, a pair‐copula based model is fitted to each transformed variable to model the univariate nonlinear spatial dependencies. NLPCA and pair‐copulas, within the proposed model, are compared with stepwise conditional transformation (SCT) and conventional kriging. The results show that, for the two case studies presented, the proposed model that utilizes NLPCA and pair‐copulas reproduces nonlinear multivariate structures and univariate distributions better than existing methods based on SCT and kriging.     

Multiplex Network Analysis for Complex Governance Systems Using Surveys and Online Behavior

Text analysis, web scraping, and other computational techniques enable policy network researchers to efficiently obtain objective measures of network connections. However, the extent to which these observational methods differ from traditional survey instrument‐based measures remains an open question. Focusing on a large regional policy network of 221 organizations, this study compares a measure of collaboration generated via survey instrument to two different measures based upon internet hyperlinks and Twitter interactions between network actors. We address two questions: (1) To what extent do objective network measures based upon observed online interactions and subjective measures based upon self‐reported relationships reveal the same inter‐organizational partnerships and structural network dynamics? and (2) How useful are online network measures for supplementing survey‐based network measures? We find a significant, but substantively small, correlation between survey‐based measures and online interactions. Thus, online network measures may complement survey‐based measures, but likely reflect different aspects of the overall policy network. We conclude by discussing the potential for multiplex measures of policy networks that draw upon multiple measures to more fully understand policy network landscapes. These results bridge and help to contextualize prior work on policy network measures and virtual policy networks within the broader context of complex governance systems.     

Using Linear Integer Programming for Multi‐Site Land‐Use Allocation

Research in the area of spatial decision support (SDS) and resource allocation has recently generated increased attention for integrating optimization techniques with GIS. In this paper we address the use of spatial optimization techniques for solving multi‐site land‐use allocation (MLUA) problems, where MLUA refers to the optimal allocation of multiple sites of different land uses to an area. We solve an MLUA problem using four different integer programs (IP), of which three are linear integer programs. The IPs are formulated for a raster‐based GIS environment and are designed to minimize development costs and to maximize compactness of the allocated land use. The preference for either minimizing costs or maximizing compactness has been made operational by including a weighting factor. The IPs are evaluated on their speed and their efficacy for handling large databases. All four IPs yielded the optimal solution within a reasonable amount of time, for an area of 8 × 8 cells. The fastest model was successfully applied to a case study involving an area of 30 × 30 cells. The case study demonstrates the practical use of linear IPs for spatial decision support issues.     

ART‐P‐MAP Neural Networks Modeling of Land‐Use Change: Accounting for Spatial Heterogeneity and Uncertainty

Spatial land‐use models over large geographic areas and at fine spatial resolutions face the challenges of spatial heterogeneity, model predictability, data quality, and of the ensuing uncertainty. We propose an improved neural network model, ART‐Probability‐Map (ART‐P‐MAP), tailored to address these issues in the context of spatial modeling of land‐use change. First, it adaptively forms its own network structure to account for spatial heterogeneity. Second, it explicitly infers posterior probabilities of land conversion that facilitates the quantification of prediction uncertainty. Extensive calibration under various test settings is conducted on the proposed model to optimize its utility in seeking useful information within a spatially heterogeneous environment. The calibration strategy involves building a bagging ensemble for training and stratified sampling with varying category proportions for experimentation. Through a temporal validation approach, we examine models’ performance within a systematic assessment framework consisting of global metrics and cell‐level uncertainty measurement. Compared with two baselines, ART‐P‐MAP achieves consistently good and stable performance across experiments and exhibits superior capability to handle the spatial heterogeneity and uncertainty involved in the land‐use change problem. Finally, we conclude that, as a general probabilistic regression model, ART‐P‐MAP is applicable to a broad range of land‐use change modeling approaches, which deserves future research.     

Robustness of Social‐Ecological Systems: Implications for Public Policy

We conceptualize social‐ecological systems (SESs) as complex adaptive systems where public policy affects and is affected by the biophysical system in which it is embedded. The study of robustness of SESs combines insights from various disciplines including economics, political science, ecology, and engineering. In this paper we present an approach that can be used to explore the implications for public policy when viewed as a component of a complex adaptive system. Our approach leverages the Institutional Analysis and Development framework to provide a platform for interdisciplinary research that focuses on system‐wide outcomes of the policy process beyond just policy change. The main message is that building robustness can create new vulnerabilities. Fail‐free policies cannot be developed, and instead of a focus on the “right” policy, we need to think about policy processes that stimulate experimentation, adaptation, and learning.     

Prediction Models for Age‐at‐Death Estimates for Calves,Using Unfused Epiphyses and Diaphyses

For cattle (Bos taurus), age estimations using dental criteria before the eruption of the first molar (3–8 months) have large error margins. This hampers archaeozoological investigation into perinatal mortality or the putative slaughtering of very young calves for milk exploitation. Previous ageing methods for subjuveniles have focused on the length of unfused bones, but it is rarely possible to use them because they are restricted to foetuses and because of the fragmentation of bones. This paper presents new age prediction models based on length, breadth and depth of post cranial bones produced from a dataset of modern calves (n = 27). This reference collection was compiled from material of known age at death, sex and breed from collections in Britain, France, Germany and Switzerland. Linear regression models were constructed using the modern data for age prediction, and these models were then successfully tested and assessed using a Middle Neolithic assemblage of complete calves' skeletons from Bourguignon‐Lès‐Morey, France. From the assessment, the astragalus and metapodials were determined to be the most reliable bones, and the femur was the worst. Measurements of the epiphyseal and distal elements and depth measurements were the most reliable. For ages before 12 months, these models can provide ±1 month age estimates. Copyright © 2013 John Wiley & Sons, Ltd.     

A Geographic Network Automata Approach for Modeling Dynamic Ecological Systems

Landscape connectivity networks are composed of nodes representing georeferenced habitat patches that link together based on a species’ maximum dispersal distance. These static representations cannot capture the complexity in species dispersal where the network of habitat patch nodes changes structure over time as a function of local dispersal dynamics. Therefore, the objective of this study is to integrate geographic information, complexity, and network science to propose a novel Geographic Network Automata (GNA) modeling approach for the simulation of dynamic spatial ecological networks. The proposed GNA modeling approach is applied to the emerald ash borer (EAB) forest insect infestation using geospatial data sets from Michigan, U.S.A. and simulates the evolution of the EAB spatiotemporal dispersal network structures across a large regional scale. The GNA model calibration and sensitivity analysis are performed. The simulated spatial network structures are quantified using graph theory measures. Results indicate that the spatial distribution of habitat patch nodes across the landscape in combination with EAB dispersal processes generate a highly connected small-world dispersal network that is robust to node removal. The presented GNA model framework is general and flexible so that different types of geospatial phenomena can be modeled, providing valuable insights for management and decision-making.     

A Hybrid Framework for Space–Time Modeling of Environmental Data. 环境数据时空建模的混合框架

The space–time autoregressive integrated moving average (STARIMA) model family provides useful tools for modeling space–time processes that exhibit stationarity (or near stationarity) in space and time. However, a more general method for routine use and efficient computation is needed to model the nonlinearities and nonstationarities of environmental space–time series. This article presents a hybrid framework combining machine learning and statistical methods to address this issue. It uses an artificial neural network (ANN) to extract global deterministic (nonlinear) space–time trends and a STARIMA model to extract local stochastic space–time variations in data. A four‐stage procedure is proposed for analyzing and modeling space–time series. The proposed framework and procedures are applied to forecast annual average temperature at 137 national meteorological stations in China. The results demonstrate that the hybrid framework achieves better forecasting accuracy than the STARIMA model alone. This finding suggests that the combination of machine learning and statistical methods provides a very powerful tool for analyzing and modeling space–time series of environmental data that have strong spatial nonlinear and nonstationary components.     

Meteorological Sub‐divisional Scale Rainfall Monitoring Using Kalpana‐1 VHRR Measurements

Geostationary satellites provide measurements over a wider geographical area with high temporal sampling, while microwave measurements are more accurate but sparse. For continuous monitoring of the Indian monsoon, geostationary platform would be ideal. In this study, INSAT (Indian National Satellite) Multi‐spectral Rainfall Algorithm (IMSRA) has been used for the estimation of rainfall from Kalpana‐1 very high resolution radiometer (VHRR) measurements. IMSRA benefits from the relative advantages of infrared and microwave sensors and is operational at the India Meteorological Department (IMD). In this paper, rainfall is estimated over India at meteorological sub‐divisional scale during the south‐west monsoon season of 2009 using Kalpana‐1 satellite measurements. This is the first experimental attempt to generate meteorological sub‐divisional scale rainfall maps using Kalpana‐1 satellite measurements. The rainfall maps for the south‐west monsoon season over the Indian land region are successfully utilised as a space input for the drought monitoring of the year 2009. The results have been compared with the IMD gauge‐based accumulated rainfall maps at monthly and seasonal time scales. The qualitative comparison suggests that rainfall maps generated using the present methodology is in good agreement with the IMD rainfall maps. The quantitative comparison of the sub‐divisional monthly accumulated rainfall shows a correlation of 0.77 and standard error of 71 mm over the non‐orographic regions, whereas a correlation of 0.60 and standard error of 117 mm is observed over the orographic regions. The present study shows that Kalpana‐1 satellite‐based rainfall estimates (IMSRA technique) can act as a complementary tool for the monsoon monitoring over the Indian meteorological sub‐divisions and can be used for various meteorological and hydrological applications.