Spatial Prediction of Landslide Hazard Using Logistic Regression and ROC Analysis

An empirical modeling of road related and non‐road related landslide hazard for a large geographical area using logistic regression in tandem with signal detection theory is presented. This modeling was developed using geographic information system (GIS) and remote sensing data, and was implemented on the Clearwater National Forest in central Idaho. The approach is based on explicit and quantitative environmental correlations between observed landslide occurrences, climate, parent material, and environmental attributes while the receiver operating characteristic (ROC) curves are used as a measure of performance of a predictive rule. The modeling results suggest that development of two independent models for road related and non‐road related landslide hazard was necessary because spatial prediction and predictor variables were different for these models. The probabilistic models of landslide potential may be used as a decision support tool in forest planning involving the maintenance, obliteration or development of new forest roads in steep mountainous terrain.     

Spatial Prediction of Landslide Hazard Using Fuzzy k-means and Dempster-Shafer Theory

Landslide databases and input parameters used for modeling landslide hazard often contain imprecisions and uncertainties inherent in the decision‐making process. Dealing with imprecision and uncertainty requires techniques that go beyond classical logic. In this paper, methods of fuzzy k‐means classification were used to assign digital terrain attributes to continuous landform classes whereas the Dempster‐Shafer theory of evidence was used to represent and manage imprecise information and to deal with uncertainties. The paper introduces the integration of the fuzzy k‐means classification method and the Dempster‐Shafer theory of evidence to model landslide hazard in roaded and roadless areas illustrated through a case study in the Clearwater National Forest in central Idaho, USA. Sample probabilistic maps of landslide hazard potential and uncertainties are presented. The probabilistic maps are intended to help decision‐making in effective forest management and planning.     

基于影像多种特征的决策树分类方法

阐述了决策树分类CART算法原理,将纹理信息、NDVI指数引入决策树方法对影像进行分类,并将分类结果与最大似然分类结果进行比较,研究表明决策树分类方法相对传统分类方法总体精度提高了8.9148%,Kappa系数提高了0.1074。     

基于多元逻辑回归的兰坪县崩塌滑坡敏感性评价

通过卫星遥感影像解译和地面调查,获取了云南省兰坪县崩塌滑坡灾害的空间分布,利用Arc GIS软件空间分析方法对该县崩塌滑坡分布规律进行了统计分析,最后运用多元逻辑回归方法对该县未来崩塌滑坡发生的空间位置进行了易发性评价。分析结果确认了极高易发性区域地理位置,其中,极高易发性区域面积为345.1 km~2,占研究区面积的7.90%;高易发性区域面积为429.3 km~2,占研究区总面积的9.82%。所得到的兰坪县崩塌滑坡易发性分布对进一步的防灾减灾工作具有指示作用。     

灰色最小二乘支持向量机在滑坡变形预测中的应用

结合灰色系统思想与最小二乘支持向量机构成灰色最小二乘支持向量机,根据目前灰色模型与最小二乘支持向量机结合的方法,提出并联型、串联型和残差型三种预测模型的结构.将上述三种灰色最小二乘支持向量机模型用于对三峡库区石佛寺滑坡垂直位移进行预测,模型精度和预测结果比较理想,优于单一预测模型.试验表明:灰色最小二乘支持向量机可提高预测精度,用于滑坡变形预测是有效可行的.     

GIS支持的常州市区域经济空间集聚特征研究

以常州市为研究区域，运用特尔菲法选择反映区域经济社会发展的基本分析变量，通过主成分分析将其简化为概括性因子，然后采用GIS与统计软件动态集成的方法对其进行空间相关性分析，探讨常州市区域经济社会发展的空间集聚特征。     

基于ArcGIS的协同克里金法预测燃气管网空间分布

燃气低压管网的合理高效规范化管理是燃气普及、管线巡查、实时预警和应急响应的基本保障。我国燃气管网发展虽然迅速,但终端用户的低压管网仍存在很多规划和管理上的不足。互联网大数据时代的兴起为燃气行业终端用户的智能管理提供了潜在机会。本文基于GIS空间分析功能,把燃气管网系统扩展深入到街道级管理模式,分析区域管理中低压管网的空间分布及影响因素,采用协同克里金插值预测城郊和乡镇区域低压管网空间分布态势,并对预测结果进行了精度评价。实验区验证结果表明,预测模型较好,其平均误差、均方根误差、标准化均方根误差均在容错范围内。该研究可为燃气管网规划和市场开发等工作提供决策依据,为智慧燃气服务民生提供思路和方案。     

Spatial Interpolation Using Fuzzy Reasoning

Spatial interpolation is an important feature of a Geographic Information System, which is the procedure used to estimate values at unknown locations within the area covered by existing observations. In this paper, we describe a conservative spatial interpolation technique that incorporates the advantages of local interpolation, Euclidean interpolation, and conservative fuzzy reasoning, and a dynamic fuzzy–reasoning–based function estimator with parameters optimised by a genetic algorithm. The main objective of this paper is to formulate a computationally efficient spatial interpolation technique similar to the IDWA technique that can be used in real time application. The main feature of our spatial interpolation technique is a capability for spatial interpolation and extrapolation in a higher–dimensional space. Examples from a rainfall spatial interpolation problem are used to illustrate the applicability of the proposed technique.     

基于ARIMA模型的地球自转变化预报

准确预报地球自转变化对于精密定位、空间飞行器的跟踪与正常运行,具有重要的科学意义和实用价值。根据周日变化（UT1-UTC）和极移变化（PM）的特性,用最小二乘法,建立了适合于UT1-UTC和PM趋势项和周期项观测数据的拟合模型。对于UT1-UTC残差序列采用差分自回归移动平均（ARIMA）模型进行预报,对于PM残差采用季节性自回归移动平均（SARMA）模型进行预报。实例结果表明：我们的UT卜UTC预报结果比地球自转服务（IERS）产品好,而PM比IERS要差一些。当大气角动量（AAM）和海洋角动量（OAM）数据参与计算后,对UT卜UTC的预报有细微改善,对PM无改善。     

矿山开采沉陷预计空间插值方法分析研究

文章首先对GIS中5种常用的空间插值方法原理进行了详细阐述,采用交叉验证法来对比分析不同插值方法的精度。应用反距离权重法、克里金法、自然邻域法、样条函数法、趋势面法5种常用的空间插值方法对兖矿集团济三煤矿1308工作面开采沉陷预计数据进行插值,对比分析了各种插值方法的精度,并对插值的误差影响因素进行了实验分析。结果表明：5种常用的空间插值方法中,克里金插值和样条函数插值精度最高,自然邻域插值和反距离权重插值精度居中,趋势面插值精度最低;对插值结果造成影响的因素与沉陷预计点的数量和密度有关,沉陷预计点的密度越大、数量越多,空间插值结果的精度就越高。研究成果可为矿山开采沉陷预计插值方法的选取提供借鉴。     

Spatial Modeling of Geotechnical Information Using GML

Geotechnical data characterizes the geometry and physical properties of soil deposits, which are determined from field observations, in-situ and laboratory tests, and engineering analyses. Until now, geotechnical information was mainly described and exchanged as relational data, which occasionally included spatial characteristics. Hereafter, the spatial features of geotechnical data are investigated by invoking the geotechnical data model of the Association of Geotechnical and Geoenvironmental Specialists (AGS), which is widely used in the United Kingdom to exchange geotechnical data in engineering practice. The basic geometric objects in AGS geotechnical data are first identified. These geometric objects are mapped to basic geometric features of the Geography Markup Language (GML). AGS data can therefore be fully rendered using GML-conformant schemas, which make geotechnical data readily importable into GML-aware applications. The data can be also imported to mainstream GIS applications using Extensible Markup Language (XML) transformations. This article demonstrates the rendition of AGS data format to a GML-conformant schema and illustrates the implementation of the new format through a few geotechnical examples.     

利用LSTM网络预测月球物理天平动参数

利用中国探月甚长基线干涉测量(very long baseline interferometry, VLBI)观测数据改进月球物理天平动参数的预测精度,对于着陆器和巡视器的精密定位具有重要意义。利用VLBI单点定位模型解算得到“嫦娥三号”(Chang’E-3,CE-3)着陆器的坐标和物理天平动,分别采用循环神经网络(recursive neural network,RNN)和长短期记忆(long-short term memory,LSTM)网络进行物理天平动的预测。选取月球着陆器的坐标和VLBI观测量作为输入量,将3个欧拉角Ω,i,μ作为输出量,将11 323个样本用于训练,2 315个样本用于测试,2 315个样本用于验证,1 000个样本用作与预测结果进行对比。结果显示,验证集的数据经过1 000次训练和9次迭代训练后的梯度约为6.2×10^-5(″)/s,证明了LSTM网络与RNN的可靠性。LSTM网络和RNN的3个欧拉角的预测精度分别达到了97.8%、99.7%、97.2%和95.2%、98.5%、95.8%,LSTM网络的预测精度更高。与DE421星历对...     

基于半变异函数的土壤有机碳空间预测方法

基于半变异函数原理,通过GS+和Variowin确定最优模型,对土壤有机碳进行空间预测,同时与反距离加权方法的空间插值结果进行预测精度和模型拟合效果对比。结果表明,基于半变异函数的土壤有机碳空间插值的均方根误差RMSE最小,比反距离加权方法提高了14%,预测精度和空间模拟效果要高于反距离加权方法的预测结果。基于半变异函数的空间插值方法要更适合土壤有机碳数据的空间预测,为其他土壤数据空间准确预测提供支持。     

Using Spatial Analysis to Understand the Spatial Heterogeneity of Disability Employment in China

During the formulation of employment disability policy, policymakers are often interested in regional variations of disability employment. Decision‐makers are required to distinguish between various geographical factors. However, few previous studies take spatial heterogeneity into account and most of them conducted only a qualitative analysis. Geographical detectors based on spatial variation analyses of identified factors were applied in the study to establish connections between regional features and the disability employment rate, and to identify the city groups with significantly higher and lower percentage rates of disability employment. It is the first application of spatial statistics in studying the employment problem of the disabled. The findings can help the government formulate reasonable adjustments to both job opportunities for, and work roles of, disabled people.     

基于FME的城镇地籍空间数据转换研究

分析了目前城镇地籍空间数据ArcGIS格式向MapGIS格式转换的主要途径,并总结了这些方法的优劣,同时利用通用转换器FME语义转换的优点,实现了ArcGIS格式数据向MapInfo格式数据的高效转换。     

改进的修正预测法预报电离层

利用自回归移动平均ARMA模型的线性最小方差预测法预报电高层存在的主要问题是极值点处预测误差较大.通过对模型阶数上限及定阶准则的选取进行实验分析,确定了合适的模型阶数并建立了相应模型.修正预测法可利用新信息对线性最小方差预测法的预测结果进行修正.这是一种短期预报方法,每次向前预测一步即2 h,但结果并不理想.考虑到电离...     

利用崇明岛地区的时间序列地形图进行预测分析

通过对上海崇明岛地区的时间序列地形图进行量测和对比分析,得出一组关于崇明岛面积的时间序列数据.因其面积有逐年增大的趋势,根据这些时间序列数据,采用灰色系统理论对这种增长趋势进行预测,做定量研究.     

利用几何校正法进行不同影像间空间配准

在影像数据融合、动态变化监测等遥感影像集成分析和应用中，将来自不同传感器、不同时相获取的影像高精度快速配准是其中的关键技术之一。介绍利用几何校正法进行不同影像间空间配准的过程，在不同影像上选取同名点作为控制点，用最近邻、双线性内插或三次卷积内插运算法对分辨率较小的影像进行重采样，完成配准。并采用Landsat TM影像和SPOT pan影像进行实验，结果表明配准精度在1个像素之内，为进一步的遥感影像融合．分类作好数据准备。     

GIS支持下应用PSO-SVM模型预测滑坡易发性

滑坡灾害易发性预测是滑坡监测、预警与评估的关键技术。如何有效地选取评价因子和构建预测模型是滑坡灾害定量预测研究中的难题。本文以三峡库区长江干流岸坡作为研究区,通过地形、地质和遥感等多源数据融合,提取滑坡孕灾环境和诱发因素的信息作为评价因子。在此基础上,针对滑坡灾害的非线性和不确定性特征,采用粒子群算法对支持向量机模型参数进行全局寻优,构建粒子群算法(particle swarm optimization, PSO)-支持向量机(support vector machine, SVM)模型,定量预测滑坡易发性。最后通过分类精度比较分析基于格网单元和对象单元的滑坡易发性预测精度,结果表明,基于对象单元的PSO-SVM预测精度较高,其曲线下面积为0.841 5,Kappa系数为0.849 0,预测结果与野外实际调查情况较为一致,可为三峡库区滑坡防灾减灾工作提供参考。