Distributed geospatial information processing: sharing distributed geospatial resources to support Digital Earth

Abstract

This paper introduces a new concept, distributed geospatial information processing (DGIP), which refers to the process of geospatial information residing on computers geographically dispersed and connected through computer networks, and the contribution of DGIP to Digital Earth (DE). The DGIP plays a critical role in integrating the widely distributed geospatial resources to support the DE envisioned to utilise a wide variety of information. This paper addresses this role from three different aspects: 1) sharing Earth data, information, and services through geospatial interoperability supported by standardisation of contents and interfaces; 2) sharing computing and software resources through a GeoCyberinfrastructure supported by DGIP middleware; and 3) sharing knowledge within and across domains through ontology and semantic searches. Observing the long-term process for the research and development of an operational DE, we discuss and expect some practical contributions of the DGIP to the DE.     

需求驱动兵团空间数据本体语义的描述

针对兵团空间信息集成与共享异构数据语义的广泛性和复杂性,本文依据其领域特性和共享需求,采用本体作为兵团空间数据表示的方法,从应用领域出发,以需求来驱动兵团空间数据本体框架构建,提出了兵团空间数据的本体工程构建方法,研究了本体领域、概念类型、语义关系,并对空间数据本体进行了语义描述。评估表明该方法构建的兵团空间数据本体有效,有利于数据共享与互操作。     

Building extraction from LIDAR based semantic analysis

Extraction of buildings from LIDAR data has been an active research field in recent years. A scheme for building detection and reconstruction from LIDAR data is presented with an object-oriented method which is based on the buildings' semantic rules. Two key steps are discussed: how to group the discrete LIDAR points into single objects and how to establish the buildings' semantic rules. In the end, the buildings are reconstructed in 3D form and three common parametric building models (flat, gabled, hipped) are implemented.     

Geostatistical approaches to refinement of digital elevation data

Data refinement refers to the processes by which a dataset’s resolution, in particular, the spatial one, is refined, and is thus synonymous to spatial downscaling. Spatial resolution indicates measurement scale and can be seen as an index for regular data support. As a type of change of scale, data refinement is useful for many scenarios where spatial scales of existing data, desired analyses, or specific applications need to be made commensurate and refined. As spatial data are related to certain data support, they can be conceived of as support-specific realizations of random fields, suggesting that multivariate geostatistics should be explored for refining datasets from their coarser-resolution versions to the finer-resolution ones. In this paper, geostatistical methods for downscaling are described, and were implemented using GTOPO30 data and sampled Shuttle Radar Topography Mission data at a site in northwest China, with the latter’s majority grid cells used as surrogate reference data. It was found that proper structural modeling is important for achieving increased accuracy in data refinement; here, structural modeling can be done through proper decomposition of elevation fields into trends and residuals and thereafter. It was confirmed that effects of semantic differences on data refinement can be reduced through properly estimating and incorporating biases in local means.     

基于语义网的地名本体服务框架研究

本文在总结地名本体的基本概念基础上,根据基于地理空间语义网的日常地理信息查询需要,进行了地名本体的概念设计.地名本体的设计可以分为两个阶段,第一阶段主要偏重于初级本体的设计,它主要支持地理对象的标示和检索等较为初级的任务.第二阶段将支持更多高级的任务,例如空间推理等.本文通过地名本体模型的构建,探讨了基于语义网的地名本...     

地质灾害领域本体的研究与应用

引入了由斯坦福大学医学院开发的七步法,并采用OWL DL语言描述本体,利用目前成熟的且流行的本体可视化构建工具Protégé完成地质灾害信息领域本体库的构建。基于行业标准、地质灾害信息处理标准、专家知识等相关标准,建立地质灾害领域本体。用OWL形式化描述基于多层结构的地质灾害空间数据本体应用模型来实现三层地质灾害本体。以具有优势的三峡库区丰富地质灾害资料为依托,以地质灾害多源异构空间信息集成与共享为主线,引入本体理论和GeoSciML,研究建立基于顶级、领域及应用多层本体的地质灾害空间数据语义集成和共享模型,实现地质灾害信息系统数据集成和应用集成,目标是解决横向各部门间的有效沟通和信息共享,以及单体灾害和群体灾害发生时的应急指挥和决策支持等问题。     

基于街景影像和手机信令数据的城市街道安全性研究

城市化进程加快导致街道安全性问题突出,已有研究利用城市视觉要素刻画街道安全感空间分布,忽略了街道真实安全性与安全感间的差异。该文利用街景影像和手机信令数据,结合K-means聚类算法与笛卡尔积运算模型减少“安全感知差异”,以长沙市主城区为研究案例,得到白天、夜晚及总体城市街道安全性分布:1)长沙市主城区安全感指数随圈层数增加呈波动递减趋势,主要原因是建筑视觉要素占比下降较快以及天空视觉要素占比逐步上升;2)长沙市主城区呈双圈层结构,白天高安全性、夜晚低安全性以及总体安全性最低的区域主要分布在主城区中心,具有明显的聚集现象。该研究通过对城市街道安全性和低安全性街道的分析提出街道优化建议,为城市规划提供参考。     

Semantic interoperability:a metadata mediator approach

1 IntroductionWith fast development of infonnahon technology (IT), such as network and collUnbocation teClmology, itis necesseq to sharing geographical information (GI) through network. There are a lot of GI resourcesconnected by the netWork, which giVes good chance for accessing GI, but how to get the infonnationwhich we Wanted is a Challenge. That is because data is not only a Symbol, but it also needs to indiCate themeaning which it eXPresses. Due to the shared data coining from dif…     

顾及地理-语义动态的城市热点预测框架

城市热点时空预测是城市管理和智慧城市建设的一项长期而富有挑战性的任务。准确地进行城市热点时空预测可以提高城市规划、调度和安全保障能力并降低资源消耗。现有的区域级深度时空预测方法主要利用基于地理网格的图像、给定的网络结构或额外的数据来获取时空动态。通过从原始数据中挖掘出潜在的自语义信息,并将其与基于地理空间的网格图像融合,也可以提高时空预测的性能,基于此,本文提出了一种新的深度学习方法地理语义集成神经网络(GSEN),将地理预测神经网络和语义预测神经网络相叠加。GSEN模型综合了预测递归神经网络(PredRNN)、图卷积预测递归神经网络(GCPredRNN)和集成层的结构,从不同的角度捕捉时空动态。并且该模型还可以与现实世界中一些潜在的高层动态进行关联,而不需要任何额外的数据。最终在3个不同领域的实际数据集上对本文提出的模型进行了评估,均取得了很好的预测效果,实验结果表明GSEN模型在不同城市热点时空预测任务中的推广性和有效性,利用该模型可以更好地进行城市热点时空预测,解决一系列如犯罪、火灾、网约车预订等等现代城市发展中亟需解决的相关问题。     

居民出行与轨迹行为交互模式挖掘与关联技术

出租车是居民出行的重要交通工具,其轨迹数据蕴含着丰富的居民出行信息.原始出租车轨迹数据因缺少语义信息无法直观反映居民出行规律.通过轨迹数据挖掘技术处理之后的出租车轨迹数据能够反映居民活动规律和行为模式,从而为城市规划决策提供参考依据.本文重点研究了基于语义的交互模式度量,通过出租车停留点推断其语义信息;然后根据语义信息...