Dynamic spatial panels: models, methods, and inferences

This paper provides a survey of the existing literature on the specification and estimation of dynamic spatial panel data models, a collection of models for spatial panels extended to include one or more of the following variables and/or error terms: a dependent variable lagged in time, a dependent variable lagged in space, a dependent variable lagged in both space and time, independent variables lagged in time, independent variables lagged in space, serial error autocorrelation, spatial error autocorrelation, spatial-specific and time-period-specific effects. The survey also examines the reasoning behind different model specifications and the purposes for which they can be used, which should be useful for practitioners.     

Catchment infiltration I: Distribution of variables

Environmental modelling usually requires spatially distributed inputs for model operation. We propose that such inputs are best obtained from field measured data. Geographic information systems (GIS) provide a logical framework to distribute measured inputs spatially, to manipulate ensuing data fields during analysis, and to display the results. This paper describes a study conducted on a 123 km² catchment in Pennsylvania. The purpose was to evaluate how spatial variability of macroporosity affects distribution of other infiltration-related parameters. We measured sorptivity, conductivity and macroporosity at specific points within a catchment, and interpolated their spatial distributions by kriging. The measurements were made with ring and disk infiltrometers, sampling locations were geo-referenced with a global positioning system (GPS), and data were analysed using geostatistical techniques in a GIS context. Field values ( hard data ) were supplemented by soft data derived from cumulative distribution functions (cdfs) and available soil maps. Results showed that, when spatial variability associated with macroporosity was removed, infiltration parameters became less variable. Observed correlation among measured parameters suggested a form of potential transfer functions. We conclude that infiltration can be modelled at either the farm or catchment scale if macroporosity and spatial variability of infiltration parameters are adequately defined, and we suggest approaches which can be used in a GIS context to attain that goal.     

A Comparative Analysis of Areal Interpolation Methods

Over the years many approaches to areal interpolation have been developed and utilized. They range from the simple 2-D areal weighing method which uses only the spatial Z variable being processed, to more sophisticated approaches which use auxiliary variable(s) to provide more specificity to the results. In the research reported here, four promising approaches are implemented and comparatively tested. These approaches have widely varying conceptual foundations, and different auxiliary variables, if used. The areal weighing reflects many earlier methods which assumes uniform distributions of the spatial Z variable, and does not use any auxiliary variable. Tobler's pycnophylactic method uses a volumetric preservation approach, which assumes spatial Z variable is heterogeneously distributed, but does not use any auxiliary variable. The traditional dasymetric method of Wright is used with remote sensing spectral data of land use. Xie's road network hierarchically weighted interpolation uses the road network as the auxiliary variable, and assumes that population density is related to the class of the road, and to the density of the road network. The research design implemented here uses Census population distributions at different levels in the hierarchy as the source and target variables analyzed. The source zone population is taken at the Census Tract level, and the target zones are specified at the Census Block Group level in the hierarchy. The first two tests use only the Census population Z data, and no auxiliary variables, whereas the next uses remotely sensed land use data as the auxiliary data variable, and the fourth test utilizes the road network hierarchy as the auxiliary variable. The paper reports on the findings from these tests, and then interprets them in a spatial setting in terms of accuracy and effectiveness. This research points to the network method as the most accurate of the areal interpolation methods tested in this research.     

Fields as a framework for integrating GIS and environmental process models. Part 1: Representing spatial continuity

Linking a GIS to a spatially distributed, physically-based environmental model offers many advantages. However, the implementation of such linkages is generally problematic. Many problems arise because the relationship between the reality being represented by the mathematical model and the data model used to organize the spatial data in the GIS has not been rigorously defined. In particular, while many environmental models are based on theories that assume continuity and incorporate physical fields as independent variables, current GISs can only represent continuous phenomena in a variety of discrete data models. This paper outlines a strategy in which field variables are used to enable modellers to work directly with the spatial data as spatially continuous phenomena. This allows the manner in which the spatial data has been discretized and the ways in which it can be manipulated to be treated independently from the conceptual modelling of physical processes. Modellers can express their spatial data needs as representations of reality, rather than as elements of a GIS database, and a GIS-independent language for model development may result. By providing a formal linkage between the various models of spatial phenomena, a mechanism is created for the explicit expression of transformation rules between the different spatial data models stored and manipulated by a GIS.     

A Spatial Filtering Specification for an Auto-negative Binomial Model of Anopheles arabiensis Aquatic Habitats

This research accounts for spatial autocorrelation by including latent map pattern components as predictor variables in a malaria mosquito aquatic habitat model specification. The data used to derive the model was from a digitized grid-based algorithm, generated in an ArcInfo database, using QuickBird visible and near-infrared (NIR) data. The Feature Extraction (FX) Module in ENVI 4.4^® was used to categorize individual pixels of field sampled aquatic habitats into separate spectral classes, convert remotely sensed raster layers to vector coverages, and classify output layers to vector format as ESRI shapefiles. These data were used to construct a geographic weights matrix for evaluation of field and remote sampled covariates of Anopheles arabiensis aquatic habitats, a major vector of malaria in East Africa. The principal finding is that synthetic map pattern variables, which are eigenvectors computed for a geographic weights matrix, furnish an alternative way of capturing spatial dependency effects in the mean response term of a regression model. The spatial autocorrelation components suggest the presence of roughly 11 to 28% redundant information in the aquatic habitat larval count samples. The presence of redundant information in the models suggest that the sampling configuration of the An. arabiensis aquatic habitats, in the study sites, may cause field and remote observations of aquatic habitats to be dependent, rather than independent, moving data analysis away from the classical statistical independence model. A Poisson regression model, with a non-constant, gamma-distributed mean, can decompose field and remote sampled An. arabiensis data into positive and negative spatial autocorrelation eigenvectors, which can assess the precision of a malaria mosquito aquatic habitat map and the significance of all factors associated with larval abundance and distribution in a riceland agroecosystem.     

利用搜索引擎数据模拟疾病空间分布

互联网记录了人们的日常生活,对带有位置信息的搜索引擎数据进行分析和挖掘可以获得隐藏于其中的地理信息。本文通过分析中国各省流感月度发病数与相关关键词百度搜索指数之间的相关性,选取相关性较高关键词的百度指数作为解释变量,发病数作为因变量,在采用主成分分析法消除变量共线性后,分别使用普通最小二乘回归（OLS）、地理加权回归（GWR）及时空地理加权回归（GTWR）构建流感发病数的空间分布模型。模型的拟合度能够从OLS的0.737、GWR的0.915提高到GTWR的0.959,赤池信息准则（AIC）也表明,GTWR模型明显优于OLS与GWR模型。验证结果显示,GTWR模型能准确识别流感高发地区,将该方法与搜索引擎数据结合能较好地模拟流感空间分布,为空间流行病学的研究提供预测模型和统计解释。     

Model Building to Investigate the Role of Spatial Location in Classifying Satellite Image Using SVM,CART and mBACT: A Case Study

This paper investigates the importance of spatial location of pixels in terms of row-column as an additional explanatory variable in classification along with available spectral bands of remotely sensed data. In view of this, a forward step-wise variable selection algorithm is used to select significant bands/variables and build an optimal model to extract the maximum accuracy. Author performed a case study on the area of town of Wolfville acquired by LANDSAT 5 TM data containing six 30 m resolution spectral bands and pixel location as an additional variable. Data are classified into seven classes using three advanced classifiers i.e. classification and regression trees (CART), support vector machines (SVM) and multi-class Bayesian additive classification tree (mBACT). Traditionally, it is assumed that addition of more explanatory variables always increase the accuracy of classified satellite images. However, results of this study show that adding more variables may sometimes confuse the classifier, that is, if selected carefully, fewer variables can provide the more accurate classification. Importance of row-column information turns out to be more beneficial for mBACT followed by SVM. Interestingly, spatial locations did not turn out to be useful for CART. Based on the findings of this study, mBACT appears to be a slightly better classifier than SVM and a substantially better than CART.     

空间信息序结构相似性及其度量

空间信息的序列关系体现了空间要素的本质联系,但是在空间分析中尚没有刻画这种序列关系的成熟理论。本文基于有序尺度变量间关联性度量理论提出了空间信息序结构相似性的分析、度量方法,利用古德曼和克拉斯卡尔的度量验证了商业用地的租金与商业用地距商服中心距离的空间序结构的相似性,研究表明利用有序尺度变量关联性度量指标能够计算空间变量序列相似度,从而实现通过已知空间变量的空间序结构推断另一空间变量的空间序结构。     

Spatial models with spatially lagged dependent variables and incomplete data

The purpose of this paper is to suggest estimators for the parameters of spatial models containing a spatially lagged dependent variable, as well as spatially lagged independent variables, and an incomplete data set. The specifications allow for nonstationarity, and the disturbance process of the model is specified non-parametrically. We consider various scenarios concerning the pattern of missing data points. One estimator we suggest is based on a smaller but complete subset of the sample; another is based on a larger but incomplete subset of the sample. We give large sample results for both of these cases.     

An optimal parameters-based geographical detector model enhances geographic characteristics of explanatory variables for spatial heterogeneity analysis: cases with different types of spatial data

ABSTRACT

Spatial heterogeneity represents a general characteristic of the inequitable distributions of spatial issues. The spatial stratified heterogeneity analysis investigates the heterogeneity among various strata of explanatory variables by comparing the spatial variance within strata and that between strata. The geographical detector model is a widely used technique for spatial stratified heterogeneity analysis. In the model, the spatial data discretization and spatial scale effects are fundamental issues, but they are generally determined by experience and lack accurate quantitative assessment in previous studies. To address this issue, an optimal parameters-based geographical detector (OPGD) model is developed for more accurate spatial analysis. The optimal parameters are explored as the best combination of spatial data discretization method, break number of spatial strata, and spatial scale parameter. In the study, the OPGD model is applied in three example cases with different types of spatial data, including spatial raster data, spatial point or areal statistical data, and spatial line segment data, and an R “GD” package is developed for computation. Results show that the parameter optimization process can further extract geographical characteristics and information contained in spatial explanatory variables in the geographical detector model. The improved model can be flexibly applied in both global and regional spatial analysis for various types of spatial data. Thus, the OPGD model can improve the overall capacity of spatial stratified heterogeneity analysis. The OPGD model and its diverse solutions can contribute to more accurate, flexible, and efficient spatial heterogeneity analysis, such as spatial patterns investigation and spatial factor explorations.     

Uses of online geoprocessing technology in analyses and case studies: a systematic analysis of literature

Interpreting spatial data to derive information is a core task in the field of Geographic Information Science and Technology. A logical step following the collection of data in online repositories is to provide geoprocessing technology for analysing data online. Online geoprocessing technology can be employed for providing a specified set of tools in a theme-specific platform, documenting a model or workflow and making it widely available, automating recurring tasks or offering simple tools to a large user group. This systematic analysis of literature evaluates how much available online geoprocessing tools are being used for answering questions in specific application contexts. An initial set of articles is derived from a keyword-based search in the database Scopus. This set of articles is manually filtered to identify applications of online geoprocessing tools. The analysis of application-related articles shows that virtually all applications require further development of tools. Experts outside the spatial information science field are still underrepresented regarding the use of this technology. The required adaptation of technology for user tasks is identified as major barrier for the wide use of online geoprocessing. Further research needs to assess user tasks and how online geoprocessing can provide the required functions in a user-oriented manner.     

Establishing and assessing the Integrated Surface Drought Index (ISDI) for agricultural drought monitoring in mid-eastern China

Accurately monitoring the temporal, spatial distribution and severity of agricultural drought is an effective means to reduce the farmers’ losses. Based on the concept of the new drought index called VegDRI, this paper established a new method, named the Integrated Surface Drought Index (ISDI). In this method, the Palmer Drought Severity Index (PDSI) was selected as the dependent variable; for the independent variables, 12 different combinations of 14 factors were examined, including the traditional climate-based drought indicators, satellite-derived vegetation indices, and other biophysical variables. The final model was established by fully describing drought properties with the smaller average error (relative error) and larger correlation coefficients. The ISDI can be used not only to monitor the main drought features, including precipitation anomalies and vegetation growth conditions but also to indicate the earth surface thermal and water content properties by incorporating temperature information. Then, the ISDI was used for drought monitoring from 2000 to 2009 in mid-eastern China. The results for 2006 (a typical dry year) demonstrate the effectiveness and capability of the ISDI for monitoring drought on both the large and the local scales. Additionally, the multiyear ISDI monitoring results were compared with the actual drought intensity using the agro-meteorological disaster data recorded at the agro-meteorological sites. The investigation results indicated that the ISDI confers advantages in the accuracy and spatial resolution for monitoring drought and has significant potential for drought identification in China.     

Using Contextualized Geographically Weighted Regression to Model the Spatial Heterogeneity of Land Prices in Beijing,China

Geographically Weighted Regression (GWR) is a method of spatial statistical analysis allowing the modeled relationship between a response variable and a set of covariates to vary geographically across a study region. Its use of geographical weighting arises from the expectation that observations close together by distance are likely to share similar characteristics. In practice, however, two points can be geographically close but socially distant because the contexts (or neighborhoods) within which they are situated are not alike. Drawing on a previous study of geographically and temporally weighted regression, in this article we develop what we describe as contextualized Geographically Weighted Regression (CGWR), applying it to the field of hedonic house price modeling to examine spatial heterogeneity in the land parcel prices of Beijing, China. Contextual variables are incorporated into the analysis by adjusting the geographical weights matrix to measure proximity not only by distance but also with respect to an attribute space defined by measures of each observation's neighborhood. Comparing CGWR with GWR suggests that adding the contextual information improves the model fit.     

空间数据处理模型误差和不确定性分析

在GIS应用中,涉及到大量的模型应用,这些模型包括了利用GIS进行空间信息处理的大部分阶段中所用到的模型。模型处理以及分析结果往往是进行下一步应用的基础,因此模型处理结果的误差和不确定性制约了实际的GIS应用。影响空间数据处理模型的误差和不确定性的因素主要包括:定位和特征信息,制图,空间分析,空间数据库以及空间数据处理模型等所具有的误差和不确定性。主要分析了空间数据处理模型误差和不确定性的表达、来源以及分析方法。     

The Scope and Conceptual Content of Analytical Cartography

Over the last three decades analytical cartography has grown from Tobler's concept of "solving cartographic problems" into a broader and deeper scientific specialization that includes the development and expansion of analytical/mathematical spatial theory and model building. In many instances Tobler himself has led the way to these new insights and developments. Fundamental concepts begin with Tobler's cartographic transformations; Nyerges' deep and surface structure and data levels; and Moellering's real and virtual maps; the sampling theorem; and concepts of spatial primitives and objects. This list can be expanded to include additional analytical concepts such as spatial frequencies, spatial surface neighborhood operators, information theory, fractals, Fourier theory, topological network theory, and analytical visualization, to name a few. This base of analytical theory can be employed to analyze and/or develop such things as spatial surfaces, terrain analysis, spatial data schemas, spatial data structures, spatial query languages, spatial overlay and partitioning, shape analysis, surface generalization, cartographic generalization, and analytical visualization. More analytical uses of theory, strategies of analysis, and implementations are being developed and continue to multiply as the field continues to grow and mature. A primary goal is to expand the mathematical/analytical theory of spatial data analysis, and theory building and analytical visualization as analytical cartography takes its place in the geographic information sciences. The research future for this area appears very bright indeed.     

MapGIS向ArcGIS数据转换过程中若干问题

空间数据转换是提高空间数据利用率及减少重复采集的有效办法,研究空间数据格式转换有助于显著提高工作效率。从MapGIS,ArcGIS软件特点的分析入手,重点探索了转换过程中遇到的问题,尤其对于文件对应转换关系、属性字段变化、图廓点三方面出现的问题进行深入分析,找到解决问题的具体方案,充分利用2个软件的优势互补,使数据资源最大化地共享。     

车载GPS道路信息采集和更新系统研究

介绍了车载道路信息采集和更新系统 (CRICUS)的设计和研究进展。该系统利用 3S集成技术采集道路信息并生成数字道路网数据库。初步实验表明 ,该系统的定位精度可达 1m。     

线性参照系在城市交通事故发布系统中的作用及应用

针对城市交通部门事故管理系统中存在道路数据不独立以及发布的事故信息易读性差导致应急部队无法准确定位事故地点进行救援的问题,基于公路的线性特征,结合GIS对地理数据的多样操作功能,提出路段名+特征参考点的一维定位表达方法。将线性参照系理论应用到以综合车道为公路模型的空间数据管理模式中,建立基于线性参照系的城市公路事故信息发布系统,实现二维坐标向一维坐标转换、降低数据冗余、实现事故地点的快速定位以及对定位的事故信息进行发布。