VGTrust: measuring trust for volunteered geographic information

Volunteered Geographic Information (VGI) has emerged as a large, up-to-date, and easily accessible data source. VGI can allow authoritative mapping agencies to undertake continuous improvement of their own data, adding a currency dimension previously unattainable due to high associated costs. VGI also benefits scientific and social research by facilitating quick and low-cost research data capture by the public. VGI, however, through its diversity of authorship, presents a quality assurance risk to the use of this data. This research presents a formulaic model that addresses VGI quality issues, by quantifying trust in VGI. Our ‘VGTrust’ model assesses information about a data author, and the spatial and temporal trust associated with the data they create, to produce an overall VGTrust rating metric. This metric is both easy to understand and interpret. A facilitated case study, ‘Building Our Footprints’ is presented which tests the feasibility of VGTrust model in a real-world data capture exercise run by Land Information New Zealand, New Zealand’s mapping organisation. By overcoming the trust issues in VGI, this research will allow the integration of VGI and authoritative data and potentially expand the application of VGI, thereby leveraging the power of the crowd for productive and innovative re-use.     

A methodology with a distributed algorithm for large-scale trajectory distribution prediction

In this paper, we propose a method for predicting the distributions of people’s trajectories on the road network throughout a city. Specifically, we predict the number of people who will move from one area to another, their probable trajectories, and the corresponding likelihoods of those trajectories in the near future, such as within an hour. With this prediction, we will identify the hot road segments where potential traffic jams might occur and reveal the formation of those traffic jams. Accurate predictions of human trajectories at a city level in real time is challenging due to the uncertainty of people’s spatial and temporal mobility patterns, the complexity of a city level’s road network, and the scale of the data. To address these challenges, this paper proposes a method which includes several major components: (1) a model for predicting movements between neighboring areas, which combines both latent and explicit features that may influence the movements; (2) different methods to estimate corresponding flow trajectory distributions in the road network; (3) a MapReduce-based distributed algorithm to simulate large-scale trajectory distributions under real-time constraints. We conducted two case studies with taxi data collected from Beijing and New York City and systematically evaluated our method.     

“一带一路”若干区域社会发展态势大数据分析

“一带一路”倡议已成为中国的基本国际政策,及时掌握沿线国家的社会发展态势,对确保该倡议的稳步推进与顺利实施至关重要。为此,论文将GDELT数据库作为数据来源,获取了“一带一路”沿线25个国家近5 a的英文新闻全文数据,引入主题模型,结合无监督方法(LDA)与监督方法(Labeled LDA)挖掘新闻数据中蕴含的主题,构建社会稳定度模型,分析各国社会发展态势。研究发现：① 沿线国家社会发展态势不均衡,可划分为4类,即稳定型,如阿曼、越南等;较稳定型,如乌兹别克斯坦、伊朗等;较高风险型,如科威特、约旦、巴基斯坦、缅甸;高风险型,如叙利亚、阿富汗等。② 通过新闻主题时空挖掘,可有效发现热点区域,例如论文发现安集延对中亚地区社会发展与稳定具有重要影响。③ 利用监督主题模型,能够发现乌兹别克斯坦经济产业结构,识别出重大社会事件,发现其社会安全风险及变化趋势。采用论文方法可有效挖掘新闻事件时空变化规律,发现各国潜在风险,支撑对沿线国家社会发展态势的实时动态监控,为“一带一路”倡议的实施提供辅助决策支持,具有重要的应用价值。     

国土资源大数据整合与更新关键技术研究与应用

以广东省国土资源大数据建设为案例,基于国土数据整合与更新的新技术、新方法,结合重大工程实践,探讨了基于统一数据模型的数据整合和更新技术。     

智慧城市时空大数据云平台建设技术大纲研究

基于智慧城市时空大数据与云平台建设技术大纲要求,研究支持智慧城市时空基础设施建设的核心与框架内容,为加强顶层设计、有序推进时空基础设施建设提供有益参考。     

自然资源基础大数据服务平台研究

基于国家基础大数据、服务平台建设现状和自然资源管理需求,综合盘点自然资源数据家底,通过对自然资源多源异构数据的同构、同化、同步处理,实现不同数据的集成、融合,形成自然资源基础大数据。结合时空大数据和政务大数据主流技术和基础平台,建立了统一的自然资源大数据综合管理与服务平台,为自然资源大数据相关体系架构和标准化建设提供技术参考。     

基于大数据方法和SOFM聚类的中国经济-环境综合分区研究

研究使用经济和环境多源大数据,建立包含人口、GDP等经济指标和空气质量等环境指标的中国经济-环境关联体系,识别各指标的热点、冷点时空变化特征,采用人工神经网络聚类方法对中国现阶段经济-环境进行综合分区。研究结果如下：① 灯光平均强度较高的省份主要集中在沿海地区,经济以长三角、珠三角和环渤海区域为主要拉动引擎,呈东南高西北低的发展态势,东部沿海地区经济发展优于东北、中部和西南地区。② PM2.5浓度呈现先增后减趋势,高污染区主要集中在华北、华中等区域;东北方向逐步扩散,污染热点地区从辽东半岛、山海关一线向东北扩张;南方地区基本保持稳定态势。③ 采用自组织特征映射模型对2015年全国各地级市OLS灯光指数、人口、城市自然边界和年均PM2.5浓度4类指标进行聚类,第I类为经济极发达-环境恶化地区,主要位于华北平原和长江三角洲;第II类为经济发达-环境趋恶化地区,主要分布在第I类区域周边,特别是京津冀周边地区;第III类为经济发达-环境良好地区,广东、海南、江西、福建以及重庆等省市多属此类型;第IV类为经济不发达-环境优质地区,主要分布于东北地区北部、内蒙古、甘肃、贵州、新疆、青海、西藏等地。     

基于手机信令数据的南京市旅游客源地网络层级结构及区域分异研究

游客源地和目的地之间构成了一张动态的空间网络,流空间视角下的客源网络研究有助于更为真实地反映客流空间结构和客源地区位结构特征。以南京市51个景区的监测客源大数据为例,分别选取元旦、清明节、劳动节、端午节和中秋节5个时段的游客数据,采用社会空间网络聚类分析方法和空间区域划分模型,从地级市层面展开客源地网络层次结构和区域分异模式分析。结果表明：① 地市层面的客流强度表现出显著的空间层次结构特征,高等级节点主要位于南京的最邻近区域和次邻近区域,外生网络效应明显;② 不同小长假客源网络节点在全局上呈现相似的层次结构和分布模式,局部区域差异显著;③ 区域化的客源流量表现为南北分异模式,而区域化的客流强度则呈现东西分异模式。     

基于微博大数据的2010～2018年中国桃花观赏日期时空格局研究

从新浪微博中检索到2 952 828条有关桃花观赏活动的微博,按照数据筛选、时空匹配、检验校准的流程,筛选出843 034条表述“桃花开了”的可采信微博,从中提取并构建了2010~2018年全国293个城市的桃花观赏日期数据集。之后使用物候站点观测数据、气温数据和物候模型模拟数据验证了桃花观赏日期数据集,得出基于微博大数据提取的中国桃花观赏日期数据集符合物候站点观测的桃花花期变化规律,符合桃花开花前气温升高则花期提前的基本规律,并与物候模型模拟的桃花花期基本一致,可以作为物候站点观测数据的重要补充。基于提取出的桃花观赏日期数据集,进一步分析了中国桃花观赏日期的时空格局,结果表明,纬度每升高1°,桃花观赏日期推迟1.78 d,其中北亚热带桃花观赏日期对纬度变化最为敏感,纬度每升高1°,桃花观赏日期推迟2.56 d。过去9 a全国大部分城市的桃花观赏日期提前。     

Quality control of marine big data——a case study of real-time observation station data in Qingdao

Offshore waters provide resources for human beings,while on the other hand,threaten them because of marine disasters.Ocean stations are part of offshore observation networks,and the quality of their data is of great significance for exploiting and protecting the ocean.We used hourly mean wave height,temperature,and pressure real-time observation data taken in the Xiaomaidao station(in Qingdao,China)from June 1,2017,to May 31,2018,to explore the data quality using eight quality control methods,and to discriminate the most effective method for Xiaomaidao station.After using the eight quality control methods,the percentages of the mean wave height,temperature,and pressure data that passed the tests were 89.6%,88.3%,and 98.6%,respectively.With the marine disaster(wave alarm report)data,the values failed in the test mainly due to the influence of aging observation equipment and missing data transmissions.The mean wave height is often affected by dynamic marine disasters,so the continuity test method is not effective.The correlation test with other related parameters would be more useful for the mean wave height.