遗传算法在城镇土地定级权重确定中的应用

在总结前人研究成果的基础上引入遗传算法。该算法是一种改进后的客观确权法,它避免了其他客观分析方法的限制性因素,通过设定不同的目标,不断优化对数据集的拟合,找到因素之间的相互关系以及权重排序。遗传算法能够挖掘出同一地块的最优权重组合,发现单一因素对地价高低的影响变化趋势,从而划分因素所属的类型。实例验证了该方法的可行性和科学性,取得了很好的效果。     

新源县汇水域单元滑坡灾害易发性评价

针对滑坡灾害易发性难以定量评价的问题,提出了以汇水域为基本统计单元,层次分析法与信息量法相结合的滑坡易发性评价模型。该模型是在综合分析已有监测数据的基础上,建立了坡度、黄土分布、土地表覆被、水系、断层、高程、地表粗糙度、坡向等8类要素与滑坡稳定性的相关性,根据评价结果将滑坡易发性划分为5个不同的等级。基于新疆新源县滑坡易发性评价的实验结果表明,该模型评价结果与滑坡实际分布情况相符,能够准确对不同汇水域灾害易发性进行分级评价,可以为相关部门进行防灾、预警提供一定的数据支持。提出了一种主观判断与客观分析相结合的方法,回答了"什么地方最容易发生地质灾害"的问题。     

基于ArcObjects的简单建筑物三维建模方法研究

基于城市建筑物三维可视化的研究背景,以COM接口为基础,设计了一套适合ArcObjects三维建模的数据采集方法。该方法的前提是建筑物可进行分割,建筑物由普通房屋、人字形房屋、尖顶房屋、圆柱形（包括椭圆柱）房屋、圆台形房屋、圆环房屋、棱台形房屋、以及截球（包括椭球和球）8类标准几何体组件构成。探讨这8类标准几何体组件的构建方法,以及建模过程中一些关键问题的解决方案。     

A novel framework for detecting non-recurrent road traffic anomalies by combining a temporal graph convolutional network and hierarchical time memory detector

A non-recurrent road traffic anomaly refers to a sudden change in the capacity of a road segment, which deviates from the general traffic patterns, and is usually caused by abnormal traffic events such as traffic accidents and unexpected road maintenance. Timely and accurate detection of non-recurrent road traffic anomalies facilitates immediate handling to reduce the wastage of resources and the risk of secondary accidents. Compared with other types of traffic anomaly detection methods, prediction algorithms are suitable for detecting non-recurrent anomalies for their potential ability to distinguish non-recurrent anomalies from recurrent congestion (e.g., rush hours). A typical prediction algorithm detects an anomaly when the difference between the predicted traffic parameter (i.e., speed) and the actual one is greater than a threshold. However, the subjective setting of thresholds in many prediction algorithms greatly affects the detection performance. This study proposes a novel framework for non-recurrent road traffic anomaly detection (NRRTAD). The temporal graph convolutional network (T-GCN) model acts as the predictor to learn the general traffic patterns of road segments by capturing both the topological effects and temporal patterns of traffic flows, and to predict the “normal” traffic speeds. The hierarchical time memory detector (HTM-detector) algorithm acts as the detector to evaluate the differences between the predicted speeds and the actual speeds to detect non-recurrent anomalies without setting a threshold. In the experiments with traffic datasets of Beijing, NRRTAD outperformed other methods, not only achieving the highest detection rates but also exhibiting higher resilience to noise. The main advantages of NRRTAD are as follows: (1) adopting the T-GCN with a weighted graph to integrate differentiated connection strengths of multiple types of topological relations between road segments as well as temporal traffic patterns improves the prediction performance; and (2) utilizing a flexible mechanism in the HTM-detector to adapt to changing stream data not only avoids subjective setting of a threshold, but also improves the accuracy and robustness of anomaly detection.     

基于百度地图的武汉市老地名时空分析系统

针对目前老地名消失现象严重,无法实现地图检索,地名文化遗产亟待保护的现状,文中基于百度地图API,以武汉地方志和武汉市地名区划网的老地名数据为基础,设计一个能够实现武汉老地名查询、导航和时空变化分析的方法,弥补目前老地名数据无法支持空间可视化表达的缺陷,分析武汉市老地名的时空变迁规律,为地名文化遗产保护提供有效参考。     

区域天顶对流层延迟时空变化特性及其建模研究

介绍几种常用的全球对流层延迟改正模型和几种区域对流层延迟模型的建立方法,再利用美国密歇根州的8个测站天顶对流层延迟数据对天顶对流层延迟进行研究,得出天顶对流层延迟在时间尺度及空间尺度上的变化规律,与经度和纬度相关性一般,与高程强相关。通过美国密歇根州的4个测站数据分别计算3种区域对流层延迟模型,得出各个模型的精度,并比较它们的优劣,结论是一次线性插值模型是三者中精度最高的模型。     

A name‐led approach to profile urban places based on geotagged Twitter data

Place is a concept that is fundamental to how we orientate and communicate space in our everyday lives. Crowdsourced social media data present a valuable opportunity to develop bottom‐up inferences of places that are integral to social activities and settings. Conventional location‐led approaches use a predefined spatial unit to associate data and space with places, which cannot capture the richness of urban places (i.e., spatial extents and their dynamic functions). This article develops a name‐led framework to overcome these limitations in using social media data to study urban places. The framework first derives place names from georeferenced Twitter data combining text mining and spatial point pattern analysis, then estimates the spatial extents by spatial clustering, and further extracts their dynamic functions with time, which makes up a complete place profile. The framework is tested on a case study in Camden Borough, London and the results are evaluated through comparisons to the Foursquare point of interest data. This name‐led approach enables the shift from space‐based analysis to place‐based analysis of urban space.     

Places of the Holocaust: Towards a model of GIS of place

Progress toward developing a GIS of place can only follow from an understanding of what place is, and this understanding draws on geographical theory. Here—following Agnew, Tuan, and others—we consider place as being made up of three components—location, locale, and sense of place—which are recognizable at multiple scales and vary historically as a product of social and political processes. Using the testimonies of two survivors of the Holocaust, we sketch the components of a model for a GIS of place that allows for this theory of place to be visualized and analyzed. The model is, crucially, both multi‐scalar and sensitive to uncertainty, as a GIS of place needs to be able to zoom in and out of the different scales at which place is experienced, as well as capture both uncertain data and uncertainty as data. We see potential in the representations proposed for scaling up from the anecdotal to the general in the sense that any narrative can be grouped and classified according to places and scales as shown here. The challenge in developing a GIS of place along the lines we propose here is to design a new set of functionalities that can do so.     

A Test Environment for Location-Based Services Applications

Location‐Based Services (LBS) are the delivery of information to mobile devices customised to location and context of the user. Some research has focused on data content, while other studies have emphasised the role of multimedia communication. However, very few objective tests have been carried out concerning usage and behaviour. In this paper, a conceptual model and a LBS test environment are presented which aim to study the behaviour and interaction between environments, individuals and mobile devices. The test environment was created, for this purpose, with three main components: urban VR models that allow individuals to ‘walk around’ at street level, a mobile device as information source which simulates LBS applications, and software for recording participant actions and reactions within the test environment. Multi‐source data were collected regarding movement tracking, information accessed through mobile device and participant observations using a combination of automated and semi‐automated methods. A case study on pedestrian wayfinding in urban settings is presented. This illustrates how the test environment can be used for LBS applications and how the data collected can be analysed. The research presented in this paper provides a novel approach in studying and understanding the interaction between environments, individuals and mobile devices.     

知识驱动下的水文模型参数智能化设置方法

水文模型的参数设置涉及专业领域的知识和繁琐的操作步骤,是水文建模面临的一大难题,在一定程度上限制了模型的应用和推广。基于知识驱动的方法,将水文模型参数设置知识分为参数提取知识和取值范围知识两类,分别对其进行形式化表达和自动推理,初步实现了水文模型参数智能化设置;结合Web Service、工作流和参数自动率定等技术,研发了水文智能建模原型系统;最后,以TOPMODEL模型的参数设置为例,对知识驱动方法进行了验证。结果表明,知识驱动的方法能在保证模拟精度的前提下有效简化水文模型的参数设置流程,降低水文建模难度。     

基于金字塔模型的规则格网数据可视化交互编辑

分析了规则格网数据分块的原则和方法,提出了规则格网数据金字塔模型的构建方法;系统论述了基于金字塔模型的规则格网数据可视化编辑原理、方法和实现过程,特别对格网数据编辑结果向金字塔模型中其他数据层的传播进行了全面研究,编程实践了单点和区域两种方式对基于金字塔模型的规则格网数据的可视化交互编辑。     

城镇基准地价评估的人工神经网络模型研究

在我国的城镇基准地价评估中,通常采用回归统计模型。这类模型属确定型数学模型,受主观影响较大,不能全面准确地模拟地价与其影响因素之间复杂的非线性关系,且评估工作量大,不易实现评估自动化。在此探讨了应用人工神经网络技术建立城镇基准地价评估模型的理论、方法和步骤,分析和研究了模型优化方法,并通过实例验证了模型的适用性和可靠性。研究表明,3层结构的基于误差反传算法的BP网络模型,能较好地模拟城镇基准地价与其影响因素之间的复杂关系。     

A measure of average error variance of line features

This article presents a new development in measuring the positional error of line features in Geographic Information Systems (GIS), in the form of a new measure for estimating the average error variance of line features, including line segment, polyline, polygon, and curved lines. This average error measure is represented in the form of a covariance matrix derived by an analytical approach. Corresponding error indicators are derived from this matrix. The error of line features mainly results from two factors: (1) an error propagated from the original component points of line features and (2) a model error of interpolation between these points. In this study, a method of average error estimation has been derived regarding the first type error of line features that are interpolated by either linear or cubic interpolation methods. The main contribution of the research is the provision of an error measure to assess the quality of spatial data in application settings. The proposed error models for estimating average error variance of line features in a GIS are illustrated by both simulated and practical experiments. The results show that the line accuracy from a linear interpolation is better than a line interpolated using a cubic model.     

城镇基准地价评估的人工神经网络模型研究

在我国的城镇基准地价评估中,通常采用回归统计模型.这类模型属确定型数学模型,受主观影响较大,不能全面准确地模拟地价与其影响因素之间复杂的非线性关系,且评估工作量大,不易实现评估自动化.在此探讨了应用人工神经网络技术建立城镇基准地价评估模型的理论、方法和步骤,分析和研究了模型优化方法,并通过实例验证了模型的适用性和可靠性.研究表明,3层结构的基于误差反传算法的BP网络模型,能较好地模拟城镇基准地价与其影响因素之间的复杂关系.     

Interpolating Spatial Interaction Data1

Spatial interpolation has been widely used to improve the spatial granularity of data, or to mediate between inconsistent zoning schemes of spatial data. Traditional areal interpolation methods translate values of source zones to those of target zones. These methods have difficulty in dealing with flow data, as each instance is associated with a pair of zones. This study develops a new concept, flow line interpolation, to fill the abovementioned gap. We also develop a first flow line interpolation method to estimate commuting flow data between spatial units in a target zoning scheme based on such data in a source zoning scheme. Three models (i.e., areal‐weighted, intelligent, and gravity‐type flow line interpolation) are presented. To test the estimation accuracy and the application potential of these models, a case study of Fulton County in Georgia is conducted. The results reveal that both the areal‐weighted and intelligent models are very promising flow line interpolation methods.     

Optimal dispersion and central places

This paper presents research into optimal dispersion models as applied to central places. The literature regarding location optimization and central places is reviewed and the motivation for employing dispersion models is identified. Models that employ the objective of maximal dispersion in the context of central places are formulated and solved in the context of both single- and multiple-good systems. Two methods for generating multiple-good systems are presented: a multiple-type dispersion model and a K-value constraint set formulation. Sequential solutions to dispersion models demonstrate how a system of central places could develop over time. The solutions to these models generate the patterns of central places expected under the organizing principles of central place theory. The objective of maximal dispersion is posited as both a motivating factor in central place location decisions, and as the optimal outcome of a mature system of central places.      

Visual-Semantic Modeling in Content-Based Geospatial Information Retrieval Using Associative Mining Techniques

Automatic learning of geospatial intelligence is challenging due to the complexity of articulating knowledge from visual patterns and to the ever-increasing quantities of image data generated on a daily basis. In this setting, human inspection and annotation is subjective and, more importantly, impractical. In this letter, we propose a knowledge-discovery algorithm that uses content-based methods to link low-level image features with high-level visual semantics in an effort to automate the process of retrieving semantically similar images. Our algorithm represents geospatial images by using a high-dimensional feature vector and generates a set of association rules that correlate semantic terms with visual patterns represented by discrete feature intervals. We also provide a mathematical model to customize the relevance of feature measurements to semantic assignments as well as methods of querying by semantics and by example.      

基于快鸟遥感影像的农地分类方法研究

遥感影像的解译精度受客观因素和主观因素的影响,各种不同解译方法的分类结果精度不一样,并且不同解译方法所适用的地物类型不相同。本文以咸阳市长武县的快鸟遥感影像数据源,运用不同的分类方法,对遥感数据进行解译,并对解译结果进行分析,评价不同解译方法的精度及所适用的地物类型。结果表明,决策树分类方法较适合农地分类。     

A set-membership approach for high integrity height-aided satellite positioning

A Robust Set-Inversion via Interval Analysis method in a bounded-error framework is used to compute three-dimensional location zones in real time, at a given confidence level. This approach differs significantly from the usual Gaussian error model paradigm, since the satellite positions and the pseudorange measurements are represented by intervals encompassing the true value with a particular level of confidence. The method computes a location zone recursively, using contractions and bisections of an arbitrarily large initial location box. Such an approach can also handle an arbitrary number of erroneous measurements using a q-relaxed solver and allows the integration of geographic and cartographic information such as digital elevation models or three-dimensional maps. With enough data redundancy, inconsistent measurements can be detected and even rejected. The integrity risk of the location zone comes only from the measurement bounds settings, since the solver is guaranteed. A method for setting these bounds for a particular location zone confidence level is proposed. An experimental validation using real L1 code measurements and a digital elevation model is also reported in order to illustrate the performance of the method on real data.     

Exploring nationally and regionally defined models for large area population mapping

Interactions between humans, diseases, and the environment take place across a range of temporal and spatial scales, making accurate, contemporary data on human population distributions critical for a variety of disciplines. Methods for disaggregating census data to finer-scale, gridded population density estimates continue to be refined as computational power increases and more detailed census, input, and validation datasets become available. However, the availability of spatially detailed census data still varies widely by country. In this study, we develop quantitative guidelines for choosing regionally-parameterized census count disaggregation models over country-specific models. We examine underlying methodological considerations for improving gridded population datasets for countries with coarser scale census data by investigating regional versus country-specific models used to estimate density surfaces for redistributing census counts. Consideration is given to the spatial resolution of input census data using examples from East Africa and Southeast Asia. Results suggest that for many countries more accurate population maps can be produced by using regionally-parameterized models where more spatially refined data exists than that which is available for the focal country. This study highlights the advancement of statistical toolsets and considerations for underlying data used in generating widely used gridded population data.