Combining machine-learning topic models and spatiotemporal analysis of social media data for disaster footprint and damage assessment

Current disaster management procedures to cope with human and economic losses and to manage a disaster’s aftermath suffer from a number of shortcomings like high temporal lags or limited temporal and spatial resolution. This paper presents an approach to analyze social media posts to assess the footprint of and the damage caused by natural disasters through combining machine-learning techniques (Latent Dirichlet Allocation) for semantic information extraction with spatial and temporal analysis (local spatial autocorrelation) for hot spot detection. Our results demonstrate that earthquake footprints can be reliably and accurately identified in our use case. More, a number of relevant semantic topics can be automatically identified without a priori knowledge, revealing clearly differing temporal and spatial signatures. Furthermore, we are able to generate a damage map that indicates where significant losses have occurred. The validation of our results using statistical measures, complemented by the official earthquake footprint by US Geological Survey and the results of the HAZUS loss model, shows that our approach produces valid and reliable outputs. Thus, our approach may improve current disaster management procedures through generating a new and unseen information layer in near real time.     

面向“数字城市”多源数据整合和分析的空间数据立方体研究

本论文面向"数字城市"的多源数据整合和分析,定义了空间数据立方体地理空间维、专题维和时间维分别包含的数据种类和内容,设计了它们的维和维层次数据结构;表述了维构成空间数据立方体的方法;确定了维的多维数组组织及存储策略;描述了空间度量的聚集概念,结合具体的图例讲述了点状、线状、面状空间度量的聚集过程。     

SinoGrids: a practice for open urban data in China

ABSTRACT

In the past decade, an explosion of data has taken place in Chinese cities due to widespread use of mobile Internet devices, Web 2.0 applications, and the development of the “Wired City.” With advances in data storage and high-performance computing, big/open urban data have opened up important avenues for urban studies, planning practice, and commercial consultancy. Urban researchers and planners are eager to make use of these abundant, sophisticated, and dynamic data to deepen their understanding on urban form and functions. However, in practice, access to such urban data is limited in China due to institutional constraints on data distribution and data holders’ hesitation to share data. And this hampers urban analytics. To draw reliable conclusions about the workings of complex urban systems, efficient and effective interoperation of multisource urban datasets is needed. Also, dealing with the heterogeneity between datasets is an equally critical challenge, especially for urban planners and government officers. They would derive value from data analytics, but have little data processing experience. To address these issues, we initiated SinoGrids (Plan Xu Xiake), a crowdsourcing platform that standardizes (or “downscales”) microscale urban data in China to facilitate its sharing and interoperation. To assess the performance evaluation of SinoGrids, we propose field-testing with actual urban data and their potential users. Digital desert, a son project of SinoGrids is also included.     

基于GIS的城市内涝灾害分析模型研究

根据气象、水文、水利等专业知识,利用GIS的空间分析技术,结合城市地理数据库和数学计算模型及城市暴雨强度经验公式,建立城市内涝灾害分析模型。该模型是城市内涝积水计算和模拟的基础,能够根据城市降雨分布情况,模拟和预测城市的内涝灾害有关特征数据,如内涝积水的空间分布、深度分布、淹没面积和淹没时间等,模拟结果可为防灾减灾部门制定防灾减灾措施提供依据。     

基于格网GIS的地质灾害地形因子危险评估方法

针对地质灾害的复杂性和不确定性,利用格网GIS技术和数学算法对地质灾害的地形危险进行评估研究。以新源县为实验区,创建500m×500m的格网覆盖研究区,选取高程、坡度、岩性、断层等地质地貌条件作为评价因子,运用GIS统计分析、叠置分析等功能将指标格网化和标准化,最后运用熵值法确定权重,进行综合评估。实验结果表明,新源县较高危险和高危险区主要集中在北部、中部及西南部的山区,共包含90.17%的灾害点,表明将格网GIS技术应用到地质灾害危险评估具有一定的实践意义。     

Quantifying the building stock from optical high-resolution satellite imagery for assessing disaster risk

This study uses high-resolution (HR) satellite imagery to quantify the stock of buildings, referred herein as building stock. The risk assessment requires information on the natural hazards and on the element at risk, that is the building stock in this article. This study combines (1) texture-based image processing to map built-up areas, (2) statistical sampling that allows locating the building samples and (3) photo-interpretation to encoding building footprints. Statistical inference is then used to quantify the building stock per class of building size. Legaspi in the Philippines is used as a case study. The results show that texture-based computer algorithms provide accurate area estimations of the built-up, that the detail of HR imagery allows the mapping of single buildings using photo-interpretation, and that a systematic sampling approach that uses building encoding and built-up maps can be used to quantify the building stock.     

Evaluating urban public facilities of Shenzhen by application of open source data

Abstract

This article applies open source data of public facilities through data mining, not only to evaluate the public facilities from an objective dimension, but also to reflect the sensory opinions of the group factually, eventually realizing the evaluation measurement of urban public facilities. The research takes Shenzhen city as an empirical case and chooses typical public facilities to mine data, resolve address and weight to explore the application of public facilities evaluation under dimension reduction of open source data. The empirical study consists of three parts. First, as the objective evaluation, we estimate the density distribution and per capita of public facility through data mining and address resolution. Second, as the subjective evaluation, we carry on the location analysis to high-score public facility through attention and satisfaction data of Internet evaluation. Finally, as mentioned above, we calculate the weight of objective and subjective evaluation of public facility, eventually formatting the comprehensive evaluation of public facilities.     

Show me the code: spatial analysis and open source

This paper considers the intersection of academic spatial analysis with the open source revolution. Its basic premise is that the potential for cross-fertilization between the two is rich, yet some misperceptions about these two communities pose challenges to realizing these opportunities. The paper provides a primer on the open source movement for academicians with an eye towards correcting these misperceptions. It identifies a number of ways in which increased adoption of open source practices in spatial analysis can enhance the development of the next generation of tools and the wider practice of scientific research and education.

In-depth examination of spatiotemporal figures in open reproducible research

ABSTRACT

Figures such as maps and time series are essential means to visualize spatiotemporal results in scientific papers. Being able to recompute them using the underlying source code and data is thus a core aspect in reproducible research. However, many scientists see the preparation of code and data for publication as an additional burden without immediate benefits. In this work, we investigate advantages and new capabilities of reproducible research papers. Our key contributions are (i) the extension of a geoscientist’s workflow while examining papers including reproducible figures such as maps and (ii) the prototypical implementation of the workflow as a web application. The workflow is based on current practices of geoscientists and encapsulates benefits of reproducible figures. It is informed by ideas and needs identified by geoscientists in a survey, interviews, and a focus group. Based on their statements, we first extend the traditional workflow steps Discovery and Inspection by additional capabilities and propose two new steps: Manipulation of the content of a spatiotemporal figure and Substitution of the underlying code and data. The extended workflow and its implementation might facilitate in-depth examination and reusability of geoscientific results.     

地灾监测的大数据信息平台研究及应用

重点对地灾监测方面的方案研究进行了阐述,在构建大数据信息平台的设计方案时,以实现高度自动化的全方位监测功能为导向,依托导航卫星数据接收机和多源传感器,集成构建大数据信息平台的系统解决方案,主要包括扼流圈卫星天线、GNSS数据接收机、MEMS传感器、环境测量单元、防雷区域单元等功能元件的组成、多传感器的系统集成,以及全方位监测的功能实现。按照地灾监测大数据信息平台建设、构建大数据平台关键技术突破及检测数据解算软件功能实现的顺序,完成了GNSS实时监测预警应用网络系统HCmonitor的研发。综合应用多种手段实现地灾监测的功能升级,为解决重大灾害预警提供了新的思路和解决方案,该项成果在甘肃舟曲的灾后重建工程得到应用与推广。     

GIS数据分析中权重确定的粗集方法研究

介绍了粗集方法的基本概念,将其中的属性重要性与GIS中常用的权重分析相结合,提出了基于粗集分类思想在GIS数据分析的权重确定中的应用方法。与传统的多因子分析中的权重确定方法相比,该方法是一种基于数据自适应的方法,不需要人为干预,具有智能高效等优点。     

基于统计分析的数据挖掘中数据处理综述

数据是一切数据挖掘工作的前提。文章将基于统计分析的数据挖掘中的数据处理工作分为前期处理和后期处理两部分,对其过程和处理方法作了综合论述,并通过实例比较分析进一步证明了数据处理对于知识发现的必要性和重要性。     

结合空间位置和语义匹配的多源房屋灾害数据融合

自然灾害综合风险普查工作中,房屋灾害信息数据来源众多,为调查底库快速建库带来很大挑战。本文针对多源房屋数据难以快速提取融合的问题,基于地理空间位置的信息匹配和基于地理空间语义的信息匹配等技术,通过空间数据提取、房屋建筑增补绘、属性信息匹配、属性信息选择,实现了房屋建筑多源信息快速自动融合,为自然灾害普查工作提供了可靠翔实的房屋建筑数据底板。实践证明,该技术成果数据准确可靠,可有效提升自然灾害风险普查工作效率,大量降低人工成本。     

利用ArcGIS Mobile的地震灾情速报系统设计与实现

为满足地震灾情速报工作的需要,本文利用ArcGIS Mobile技术,基于PDA设计和开发了移动地震灾情速报系统.结合地震灾情速报工作的特殊性,设计出灾情速报基础空间数据库,实现了灾情信息编辑、灾情区域绘制、灾情速报员GPS定位、灾情同步等功能.     

重大自然灾害空间信息协同服务机制研究

结合重大自然灾害应急管理的业务需求,分析了国外数据共享实践经验与案例,基于国家灾害管理实践工作经验,提出了中国建设重大自然灾害空间信息协同服务机制的构想。在进行职责任务划分的基础上,设立了包括指令中枢、数据中枢和信息中枢的立体化体制架构,并结合国家灾害管理业务工作的实际情况,制定了服务机制的业务关系流程,设定应急与常规相结合的运行模式,并对所需的保障配套机制进行了研究和分析。目前,重大自然灾害空间信息协同服务机制已经在国家灾害管理部门得到了一定范围的实践和检验,取得了较好的应用效果和社会经济效益。     

国产高分辨率卫星数据在黄河防凌监测中应用

自2002～2003年度首次启用遥感技术监测黄河凌情以来,到目前已连续进行了10个年度.10个年度的生产实践表明:国产高分辨率卫星遥感数据能够有效跟踪黄河凌情的发展过程,实现黄河凌情的日动态监测、重点时段的精细监测和突发凌汛灾害时的实时监测.黄河凌情尤其在封开河阶段,日变化非常显著,中巴资源卫星作为国产高分辨率可见光民用遥感卫星的代表,以其大视场、高空间、高时间分辨率的特点,动态监测凌情,基本做到每天实现一次全覆盖监测的能力,配合其他如中国遥感卫星等高分辨率可见光、雷达数据,初步实现了凌情发展预估、开河前的河道槽蓄水量计算、封开河期间冰凌险情监测以及发生凌汛灾害时灾情信息采集与评估,为黄河防凌     

Sparse representation-based correlation analysis of non-stationary spatiotemporal big data

As the basic data of digital city and smart city research, Spatiotemporal series data contain rich geographic information. Alongside the accumulation of spatial time-series data, we are also encountering new challenges related to analyzing and mining the correlations among the data. Because the traditional methods of analysis also have their own suitable condition restrictions for the new features, we propose a new analytical framework based on sparse representation to describe the time, space, and spatial-time correlation. First, before analyzing the correlation, we discuss sparse representation based on the K-singular value decomposition (K-SVD) algorithm to ensure that the sparse coefficients are in the same sparse domain. We then present new computing methods to calculate the time, spatial, and spatial-time correlation coefficients in the sparse domain; we then discuss the functions' properties. Finally, we discuss change regulations for the gross domestic product (GDP), population, and Normalized Difference Vegetation Index (NDVI) spatial time-series data in China's Jing-Jin-Ji region to confirm the effectiveness and adaptability of the new methods.     

三峡库区地质灾害数据管理平台元数据编辑器的设计与实现

本文探讨了建立空间元数据管理系统所涉及的一些标准和技术,重点介绍了ArcCatalog中的元数据管理和XML技术及其在元数据系统中的作用.针对ArcCatalog空间数据管理的特点及开放的扩展机制,深入讨论了用户定制的元数据编辑器开发的步骤、主要技术等,并设计开发出一种基于XML的空间数据元数据编辑器,为地球空间元数据...     

基于多分辨率分析的LiDAR数据处理与可视化

基于多分辨率分析的数据滤波算法对于地形变化单一但地物和地形区别明显的场景,地形多变但连续且地物和地形区别明显的场景具有非常优越的滤波效果.研究基于多分辨率分析的数据滤波算法的基本原理,在Visual C++6.0平台上编程实现该算法,建立LiDAR数据处理与可视化系统,详细介绍各功能模块的实现方法和功能,实现由LiDA...     

基于高光谱数据的壁画底稿信息提取

壁画底稿有助于探测壁画艺术的历史信息,具有重要的研究价值,本文设计了半自动提取壁画底稿信息的“三步法”:针对高光谱数据量大、相邻波段相关性高的特点,利用主成分分析实现原始数据的降维;选出含底稿信息量大的特征波段;并利用最大似然分类法实现基于特征波段合成影像的壁画底稿信息提取.结果表明,该方法能够减少数据处理量,提高分类效率与分类精度,明显恢复壁画的底稿轮廓,为以后的文化遗产保护工作提供一个可行的方案.