A Novel Hybrid Method for Measuring the Spatial Autocorrelation of Vehicular Crashes: Combining Moran’s Index and Getis-Ord G_i<sup style='margin-left:-7px;'>*</sup>Statistic

Spatial autocorrelation is a measure of the correlation of an observation with other observations through space. Most statistical analyses are based on the assumption that the values of observations are independent of one another. Spatial autocorrelation violates this assumption, because observations at near-by locations are related to each other, and hence, the consideration of spatial autocorrelations has been gaining attention in crash data modeling in recent years, and research have shown that ignoring this factor may lead to a biased estimation of the modeling parameters. This paper examines two spatial autocorrelation indices: Moran’s Index;and Getis-Ord Gi* statistic to measure the spatial autocorrelation of vehicle crashes occurred in Boone County roads in the state of Missouri, USA for the years 2013-2015. Since each index can identify different clustering patterns of crashes, therefore this paper introduces a new hybrid method to identify the crash clustering patterns by combining both Moran’s Index and Gi*?statistic. Results show that the new method can effectively improve the number, extent, and type of crash clustering along roadways.

STUDY ON SPATIAL AUTOCORRELATION OF URBAN LAND PRICE DISTRIBUTION IN CHANGZHOU CITY OF JIANGSU PROVINCE

This paper uses a spatial statistics method based on the calculation of spatial autocorrelation as a possible approach for modeling and quantifying the distribution of urban land price in Changzhou City, Jiangsu Province. GIS and spatial statistics provide a useful way for describing the distribution of urban land price both spatially and temporally, and have proved to be useful for understanding land price distribution pattern better. In this paper, we apply the statistical analysis method to 8379 urban land price samples collected from Changzhou Land Market, and it is turned out that the proposed approach can effectively identify the spatial clusters and local point patterns in dataset and forms a general method for conceptualizing the land price structure. The results show that land price structure in Changzhou City is very complex and that even where there is a high spatial autocorrelation, the land price is still relatively heterogeneous. Furthermore, lands for different uses have different degrees of spatial autocorrelation. Spatial autocorrelation of commercial lands is more intense than that of residential and industrial lands in regional central district. This means that treating land price as integration of homogeneous units can limit analysis of pattern, over-simplifying the structure of land price, but the methods, just as the autocorrelation approaches, are useful tools for quantifying the variables of land price.

Spatial Autocorrelation and Localization of Urban Development

A nonlinear analysis of urban evolution is made by using of spatial autocorrelation theory. A first-order nonlinear autoregression model based on Clark’s negative exponential model is proposed to show urban population density. The new method and model are applied to Hangzhou City, China, as an example. The average distance of population activities, the auto-correlation coefficient of urban population density, and the auto-regressive function values all show trends of gradual increase from 1964 to 2000, but there always is a sharp first-order cutoff in the partial auto- correlations. These results indicate that urban development is a process of localization. The discovery of urban locality is significant to improve the cellular-automata-based urban simulation of modeling spatial complexity.

Spatial autocorrelation analysis of 13 leading malignant neoplasms in Taiwan: a comparison between the 1995-1998 and 2005-2008 periods

Spatial autocorrelation methodologies, including Global Moran’s I and Local Indicators of Spatial Association statistic (LISA), were used to describe and map spatial clusters of 13 leading malignant neoplasms in Taiwan. A logistic regression fit model was also used to identify similar characteristics over time. Two time periods (1995-1998 and 2005-2008) were compared in an attempt to formulate common spatio-temporal risks. Spatial cluster patterns were identified using local spatial autocorrelation analysis. We found a significant spatio-temporal variation between the leading malignant neoplasms and well-documented spatial risk factors. For instance, in Taiwan, cancer of the oral cavity in males was found to be clustered in locations in central Taiwan, with distinct differences between the two time periods. Stomach cancer morbidity clustered in aboriginal townships, where the prevalence of Helicobacter pylori is high and even quite marked differences between the two time periods were found. A method which combines LISA statistics and logistic regression is an effective tool for the detection of space-time patterns with discontinuous data. Spatio-temporal mapping comparison helps to clarify issues such as the spatial aspects of both two time periods for leading malignant neoplasms. This helps planners to assess spatio-temporal risk factors, and to ascertain what would be the most advantageous types of health care policies for the planning and implementation of health care services. These issues can greatly affect the performance and effectiveness of health care services and also provide a clear outline for helping us to better understand the results in depth.

Identifying Vehicular Crash High Risk Locations along Highways via Spatial Autocorrelation Indices and Kernel Density Estimation

Identifying vehicular crash high risk locations along highways is important for understanding the causes of vehicle crashes and to determine effective countermeasures based on the analysis. This paper presents a GIS approach to examine the spatial patterns of vehicle crashes and determines if they are spatially clustered, dispersed, or random. Moran’s I and Getis-Ord Gi* statistic are employed to examine spatial patterns, clusters mapping of vehicle crash data, and to generate high risk locations along highways. Kernel Density Estimation (KDE) is used to generate crash concentration maps that show the road density of crashes. The proposed approach is evaluated using the 2013 vehicle crash data in the state of Indiana. Results show that the approach is efficient and reliable in identifying vehicle crash hot spots and unsafe road locations.

“In Space” or “As Space”?: Spatial Autocorrelation Properties of the Earth’s Interior

In this analysis, natural systems are posed to subsystemize in a manner facilitating both structured information/energy sharing and an entropy maximization process projecting a three-dimensional, spatial outcome. Numerical simulations were first carried out to determine whether n × n input-output matrices could, once entropy-maximized, project a three-dimensional Euclidean metric. Only 4 × 4 matrices could;a small proportion passed the test. Larger proportions passed when grouped random patterns on and within two- and three-dimensional forms were tested. The pattern of structural zonation within the earth was then tested in analogous fashion using spatial autocorrelation measures, and for three time periods: current, 95 million years b.p. and 200 million years b.p. All expected results were obtained;not only do the geometries of zonation project a three-dimensional structure as anticipated, but also do secondary statistical measures reveal levels of equilibrium among the zones in all three cases that are nearly total, distinguishing them from simulations that do not incorporate a varying-surface zone-width element.

基于CSLE的泛第三极地区土壤侵蚀强度空间分布特征

[目的]定量评估泛第三极地区的土壤侵蚀状况,明确土壤侵蚀的分布特征,以期为土壤侵蚀的科学防治提供依据。[方法]基于分层不等概系统抽样方法,共布设31 406个调查单元。利用中国土壤流失方程CSLE计算泛第三极地区土壤侵蚀速率,并利用莫兰指数(I)探讨其分布特征。[结果](1)泛第三极地区平均土壤侵蚀速率为162.73 t/(km^(2)·a),水土流失面积比例为7.75%,土壤侵蚀速率超过500 t/(km^(2)·a)的地区主要位于西亚、东亚和南亚;(2)土壤侵蚀存在明显的空间聚集性(I=0.920 9),以高高型和低低型聚集为主,高高型聚集主要分布在西亚北部、南亚北部和西南部以及中国的东北、黄土高原和西藏南部;(3)草地、灌丛和耕地是土壤侵蚀较严重的土地利用类型,其中>1 000 m的草地、>500 m的灌丛和耕地的土壤侵蚀更严重,超过25%的土地都发生了水土流失,平均土壤侵蚀速率变化于426.85~683.72 t/(km^(2)·a)。[结论]海拔介于1 000~6 000 m的草地、500~4 000 m的灌丛以及1 000~4 000 m的耕地是泛第三极地区土壤侵蚀发生的重点区域,需特别关注。

结合均匀度理论和Moran’s I指数、广义G指数的景观格局全局自相关分析

以塔子沟林场为研究区域,以1997年8月28日和2009年8月25日两期Landsat TM遥感影像为主要数据源,辅助大量非遥感数据,借助ENVI 5.1、Arc GIS 10.3和Geoda095i等软件,将均匀度理论分析方法引入到景观格局空间相关分析中,对研究区域景观格局全局自相关进行了分析,并与Moran’s I、广义G指数的分析方法获得结论进行了对比。经计算,1997年的景观格局均匀度为0.320 7,介于景观均匀度置信区间[0.297 2,0.339 7],景观格局判定为随机分布,2009年的景观格局均匀度为0.288 3,小于下限值0.296 9,景观格局判定为聚集分布。1997年Moran’s I值为-0.11,景观格局判定为分散分布,2009年Moran’s I值为0.42,景观格局判定为聚集分布。1997年研究区域Z Score值为0.92,2009年研究区域Z Score值为2.06,根据景观格局判别可知,2009年研究区域景观格局呈现出明显的高值空间聚集(H-H聚集),即该期景观格局为聚集分布。结果表明3种分析方法得到的结论相同,即从1997—2009年的12年间,研究区域的格局状况由随机格局到聚集格局变化,说明将均匀度理论分析方法引入到景观格局空间相关分析中是可行的。

中国奥运奖牌空间分布区域性差异的Moran's Ⅰ指数分析研究

运用空间统计学方法对我国各省(自治区、直辖市)奥运奖牌的空间分布格局做空间自相关分析(spatial autocorrelation)。全局Moran's Ⅰ表明,我国各省(自治区、直辖市)奥运奖牌分布格局的总体变化趋势虽然出现波动,但是,在大部分年份的地域差异不太明显,省际间的空间相互作用不强,呈现随机分布状态,直至2004年才开始表现出集聚的情况,并且呈现空间自相关关联性减弱的趋势。Moran散点图和LISA集聚图进一步揭示了各省(自治区、直辖市)奥运奖牌分布的空间变化以及对总体趋势的偏移。

基于时空Moran's I指数的全国降雨量自相关分析

对全国160个站点收集的1951年～2000年降雨量数据进行时空自相关分析,探讨了降雨量的时空演变特征.研究结果表明：全国降雨量呈现时空聚集特征,具有明显的时空相关性;在时间维度上,全局时空Moran＇s I指数所反映的趋势,与全国5～9月降雨量上升趋势一致,对于相邻的月份,上个月的降雨量对下个月的降雨量有直接影响,即上个月降雨高聚集的区域也很有可能是下个月降雨高聚集的区域,随着两个月之间相隔的时间越长,这种相关性逐渐减小;空间维度上,局部时空Moran＇s I指数所反映的全国降雨量聚集模式,与5～9月实际降雨空间分布相符.

基于Moran′s I的菜地土壤属性空间分布格局分析

为探讨时空尺度下露天菜地及设施菜地种植模式对土壤属性空间分布格局的影响,采用Moran′s I空间分析方法,对安徽省肥东县2017年采集的375个表层土样数据、2016年的露天菜地数据及2019年的设施菜地数据之间的空间自相关性进行研究。结果表明:研究区内露天菜地种植时间越短,土壤全氮、速效钾的平均值越高,设施菜地种植时间越短,有机质、全氮、有效磷、速效钾、pH 5种土壤属性平均值越高。除速效钾外,露天蔬菜的土壤有机质、全氮、有效磷、pH指标值均低于设施菜地。距离城镇越近,土壤有机质、全氮含量和pH越高。两种菜地分布密度与有机质、全氮空间分布呈高高空间正相关,与有效磷和速效钾呈低高空间负相关,与pH在土壤中呈高低空间负相关。研究结果表明,两种菜地土壤属性指标值因受到种植时间与城镇距离因素的影响而差异明显。因经济利益驱动,设施菜地种植时间较短但土壤养分累积较快。菜地分布密度对土壤属性空间分布格局影响明显,菜地种植与土壤酸化、养分累积具有一定的相关性。通过Moran′s I空间分析,可实现对蔬菜生产区域的管理,为进一步分析土壤属性扩散演化机制提供参考。

基于改进Moran's I指数的成都市PM_(2.5)的空间统计分析

以PM2.5污染的空间分布为研究对象,改进传统Moran＇s I指数,以便适用于大样本数据的空间自相关分析。通过改进Moran＇s I指数推导出期望与方差对改进Moran＇s I指数进行统计意义上的显著性检验,从而对PM2.5污染情况进行空间自相关性的判断与评价,揭示PM2.5污染呈现的空间分布趋势。为说明改进Moran＇s I指数的实际应用价值,采用成都市区7个空气质量监测点（不包括灵岩寺监测点）PM2.5每小时数据,进行改进Moran＇s I指数的计算与分析,绘制改进全局指数时序图和改进局部Moran＇s I指数渲染图。结果表明,成都市区全局Moran＇s I指数的范围为0.728 7-0.998 5,即PM2.5污染整体呈现显著空间聚集趋势,从局部看,PM2.5污染的空间聚集和空间异质特性随着时间转移至不同监测点,地理位置邻近或环境类似的监测点有类似的分布趋势。

基于Moran′s I的林分空间结构量化指标自相关分析

为了研究林分空间单元中对象木与相邻木之间在空间结构指标上的自相关性,分析对象林木与相邻木之间在空间中的逻辑关系。在大围山自然保护区、乌云界自然保护区及芦头林场等区域中设置了25块20m×20m的样地,构建了基于Voronoi图的林木空间单元,确定了每株对象林木的相邻木,并选取混交度、开阔比数、胸径大小比及竞争指数作为林木空间结构量化指标,计算了各指标的值,最后结合全局Moran′s I的基本原理构建了林分空间结构单元指标自相关性分析方案,对研究样地中的林分进行分析。结果表明,研究区域的林分为中度混交混交林,该区域的林木之间处于呈中拥挤状态,研究区域内的对象木和其空间单元内的相邻木胸径大小分布差异性较大,林木之间的竞争相对较强。从空间关系上看,研究区域内林木的混交度、开阔比数与其相邻木在空间上呈正相关,在逻辑上表现为聚集;林木的胸径大小比、竞争指数与其相邻木在空间上呈负相关,在逻辑上表现为离散。此外,调研区域中的林木在空间上与其相邻木的关系主要表现为竞争,林分中林木的混交度和竞争指数可能是导致其与周围相邻木存在负相关的主要空间指标。

基于Moran’s I的安徽省太湖县耕地质量时空格局分析

[目的]探究耕地质量时空格局演变规律,为各级土地管理部门进行耕地分区利用与保护提供决策依据,为提升耕地质量和优化土地空间布局提供参考。[方法]基于安徽省太湖县2008年及2018年耕地质量等级评价成果,以ArcGIS和GeoDa为平台,利用时间序列法和空间自相关分析等研究方法,分别从全局自相关和局部自相关两方面分析太湖县10 a跨度的耕地质量时空格局变异情况,划分制定4类分区管理方案:限制建设区、综合改良区、适度改良区和重点整治区,并有针对地提出符合实际情况的耕地管护措施。[结果]①2008—2018年,太湖县总耕地面积增加6474.45 hm^(2);②2008年及2018年全局自相关Moran’s I分别为:0.419478,0.288328,Z得分分别为:8.677693,5.527830;③在空间分布上太湖县耕地质量空间正相关类型多以“组团”聚类形式出现,负相关类型无明显集中区域。[结论]太湖县10 a时间跨度上耕地面积增加了6474.45 hm^(2),耕地资源的10 a平均变化率P=1.65%,耕地质量平均等级提升1.68等;在空间分布上呈显著空间自相关特征和空间聚集特征。

基于GIS的环巢湖地区土壤养分空间变异特征研究

为探究环巢湖地区土壤养分的空间自相关性及其变异规律,在研究区域共采集8073个土壤样品,基于GIS技术并使用地统计方法和Moran′s I指数法对土壤pH、有机质、全氮、碱解氮、有效磷、速效钾和缓效钾进行了系统分析。结果表明:土壤pH、有机质、全氮、碱解氮、有效磷、速效钾和缓效钾的均值分别为6.07、19.97 g·kg^(-1)、1.16 g·kg^(-1)、112.95 mg·kg^(-1)、18.21 mg·kg^(-1)、130.88 mg·kg^(-1)和378.58 mg·kg^(-1),除有效磷为强变异外,其他养分均为中等程度变异;pH、全氮、有效磷、速效钾和缓效钾半变异函数最佳拟合模型为指数模型,有机质和碱解氮为高斯模型;pH和速效钾为中等空间自相关性,其他养分空间自相关性均较弱,表明养分空间变异主要受人为活动等随机性因素影响;各养分均为极显著空间正相关,其空间相关性大小依次为有效磷>速效钾>pH>缓效钾>全氮>有机质>碱解氮,且有效磷的空间自相关性显著大于其他养分。总体上看,环巢湖地区养分分布较为分散,南北方向有逐渐上升或下降的趋势,且养分高低值聚集区域也有明显的南北分布。

Examining the Relationship Between Spatial Configurations of Urban Impervious Surfaces and Land Surface Temperature

The urban heat island(UHI) effect has significant effects on the quality of life and public health. Numerous studies have addressed the relationship between UHI and the increase in urban impervious surface area(ISA), but few of them have considered the impact of the spatial configuration of ISA on UHI. Land surface temperature(LST) may be affected not only by urban land cover, but also by neighboring land cover. The aim of this research was to investigate the effects of the abundance and spatial association of ISAs on LST. Taking Harbin City, China as an example, the impact of ISA spatial association on LST measurements was examined. The abundance of ISAs and the LST measurements were derived from Landsat Thematic Mapper(TM) imagery of 2000 and 2010, and the spatial association patterns of ISAs were calculated using the local Moran’s I index. The impacts of ISA abundance and spatial association on LST were examined using correlation analysis. The results suggested that LST has significant positive associations with both ISA abundance and the Moran’s I index of ISAs, indicating that both the abundance and spatial clustering of ISAs contribute to elevated values of LST. It was also found that LST is positively associated with clustering of high-ISA-percentage areas(i.e.,>50%) and negatively associated with clustering of low-ISA-percentage areas(i.e.,<25%). The results suggest that, in addition to the abundance of ISAs,their spatial association has a significant effect on UHIs.

Spatial Quantitative Analysis of Garlic Price Data Based on ArcGIS Technology

In order to solve the hidden regional relationship among garlic prices,this paper carries out spatial quantitative analysis of garlic price data based on ArcGIS technology.The specific analysis process is to collect prices of garlic market from 2015 to 2017 in different regions of Shandong Province,using the Moran's Index to obtain monthly Moran indicators are positive,so as to analyze the overall positive relationship between garlic prices;then using the geostatistical analysis tool in ArcGIS to draw a spatial distribution Grid diagram,it was found that the price of garlic has a significant geographical agglomeration phenomenon and showed a multi-center distribution trend.The results showed that the agglomeration centers are Jining,Dongying,Qingdao,and Yantai.At the end of the article,according to the research results,constructive suggestions were made for the regulation of garlic price.Using Moran’s Index and geostatistical analysis tools to analyze the data of garlic price,which made up for the lack of position correlation in the traditional analysis methods and more intuitively and effectively reflected the trend of garlic price from low to high from west to east in Shandong Province and showed a pattern of circular distribution.

Moran’s I指数与DEM网格大小关系的研究

数字高程模型(Digital Elevation Model,简称DEM)作为真实地形的一种数字化模拟,网格间存在着某种空间自相关性.Moran’s I是一种常见的空间自相关程度量化指标.为了研究Moran’s I与DEM网格大小之间的关系,文章在分辨率为30 m×30 m的DEM上随机选取了35个采样点.又以每个采样点为中心,选取n×n(n=3,5,7,…,25)大小的DEM网格,计算并记录对应于每个网格的Moran’s I指数值,绘出各采样点的Moran’s I指数值随n变化的曲线.研究发现:大多数采样点的Moran’s I曲线呈现出一致的变化趋势;同时发现少数采样点的Moran’s I曲线出现局部的变化异常.对这些异常进行分析后发现,Moran’s I值随n变化的趋势与DEM网格高程值的离散程度(地形)有关.

我国生态富民水平测度、动态演进及空间关联

生态富民是推进生态文明建设、培育绿色发展新动能、助力经济高质量发展的重要路径。立足生态和富民两个维度,构建包含物质生态、精神生态、居民收入、居民文化、居民教育、居民医疗、居民就业创业七个二级指标的生态富民水平评价指标体系,测度2013—2022年我国30个省份(未含香港地区、澳门地区、台湾地区和西藏地区)的生态富民水平,并采用核密度估计法、全局莫兰指数和局部莫兰指数分析生态富民水平动态演进和空间关联特征。研究发现:从生态富民水平变化趋势看,在全国层面,我国生态富民水平整体较低但呈快速上升态势,其中2013—2018年增速较慢,2019—2022年增速不断加快,生态、富民两个维度的得分均在不断提升;在地区层面,东部、中部、西部三大地区生态富民水平均呈稳步上升态势,但地区间差距较大。其中,东部地区生态富民综合得分高于全国以及中西部地区水平,中西部地区生态富民综合得分低于全国平均水平。从生态富民水平极化现象和省份间差距看,在全国层面,我国生态富民水平极化现象不断减弱,省份间差距逐渐拉大;在地区层面,东部地区生态富民水平极化现象减弱,省份间差距不断扩大,中部地区生态富民水平极化现象减弱,省份间差距不断缩小,西部地区生态富民水平极化现象始终比较严重,省份间差距变化不明显。从空间关联看,我国各省份生态富民水平空间关联特征显著,东部省份多数属于生态富民水平和空间关联性“双高”的H-H类型,中部省份多数属于生态富民水平或空间关联性“单低”的L-H或H-L类型,西部省份大多属于生态富民水平和空间关联性“双低”的L-L类型,且大多数省份空间关联类型比较稳定。因此,应打通绿色转化通道,助力生态富民水平提升;打造模块化生态富民模式,缩小地区间发展差距;提高生态富民空间关联水平,夯实区域生态存量。

全国能源消费结构低碳化的空间非均衡性及动态演进

剖析中国能源消费结构低碳化趋势、衡量其空间非均衡状态是推进能源革命及绿色发展的关键环节。文章根据2003—2020年我国各省市能源消费的面板数据,利用泰尔指数和空间自相关法,探究全国能源消费结构低碳化的空间非均衡性及动态演进特征。结果显示:1)我国能源消费结构低碳化指数总体呈稳步上升的趋势,由2003年的5.298上升至2020年的5.862;2)全国能源消费结构低碳化分布的空间非均衡性较弱,呈现先升后降态势,即泰尔指数总体呈现先上升后下降发展态势,区域间能源消费结构低碳化的差异对总体差异的影响越来越大;3)全国能源消费结构低碳化存在明显的空间正相关,空间集聚效应现象,且近年来总体空间格局分布变化较小。江浙沪地区始终呈现高高聚集的特征,而西南和华中地区则处于弱弱聚集。根据分析结果,提出构建区域利益共同体,通过技术交流等多种方式互惠互助、合作共赢,共同促进能源低碳化发展;推动产业结构高级化,激发社会创造力和市场活力,破解落后高耗能产业的模式锁定和路径依赖;优化能源产业结构,积极推进能源消费转型等政策建议。