多源地理大数据支撑下的地理事件建模与分析

doi:10.11821/dlxb202111018

摘要/Abstract

摘要：

地理事件作为描述地理过程的基本单元,逐渐成为地理信息科学（GIS）核心研究内容。由于受人类活动数据获取限制,GIS对地理事件的建模和分析主要关注事件所引起的地理空间要素变化及要素之间的相互影响与作用机制。然而,近年来随着基于位置服务数据（LBS）爆炸式的增长和人类活动大数据定量刻画手段的快速发展,地理事件对人类活动的影响以及公众对地理事件的网络参与度都引起了多个领域的广泛关注,对地理事件的时空认知、建模方法和分析框架提出了巨大的挑战。对此,本文首先深入分析了大数据时代地理事件的概念与分类体系;其次,基于地理事件的时空语义给出了基于图模型的事件数据建模,建立了事件本体及其次生或级联事件的“节点—边”表达结构,开展了事件自身时空演化及其前“因”后“果”的形式化描述;第三,从时空数据分析与挖掘的角度,给出了大数据时代地理事件建模与分析的整体框架,拟突破传统“地理实体空间”事件探测与分析方法的局限性,融合“虚拟空间”事件发现与传播模拟思路,实现多源地理大数据支撑下的面向地理事件的人类活动多尺度时空响应与区域差异分析;最后,本文以城市暴雨事件为例诠释了本文所提出的地理事件建模与分析方法,从城市和城市内部两个尺度进行了暴雨事件与人类活动的一致性响应及区域差异分析,得到了明确的结论,验证了前文分析框架的可行性与实用性。

关键词: 地理事件, 图数据模型, 地理大数据, 人类活动响应

Abstract:

Geographic events, as a basic construct in geographic process description, have become a core content of geographic information system (GIS). Due to the limitation of acquiring human activity data, GIS modeling and analysis of geographic events has long been focused on the event-induced changes of geospatial objects and the interaction between the objects. However, in recent years, with the explosive growth of location-based service data and the rapid development of quantitative depiction of human activities, the impact of geographic events on human activities and online social participation in geographic events have aroused wide concern in many fields, which poses great challenges to the space-time cognition, modeling methods and analysis framework of geographic events. In this regard, this study discussed the conceptualization and categorization of geographic events in the context of big data, and then introduced the space-time semantics and graph-based data model for geographic events. The "node-edge" graph data structure is used to establish event ontology, the secondary or cascading events, the evolution process, and the "cause-effect" interaction. The spatiotemporal data mining approaches for geographical events were also summarized, which are limited to conventional event detection in "physical space". Integrating "virtual space" event discovery and propagation simulation ideas into data mining approaches is essential for recognizing multi-scale spatiotemporal responses and understanding regional difference of human activities under diverse geographic events. Finally, the study used urban rainstorm events as an example to examine the conceptualization and modeling method of geographic events. Social responses to urban rainstorms and regional differences were examined at inter-urban and intra-urban scales. The case study proved the concept and verified the feasibility and practicability of the proposed framework.

Key words: geographic event, graph model, geographic big data, human activity response

杜云艳, 易嘉伟, 薛存金, 千家乐, 裴韬. 多源地理大数据支撑下的地理事件建模与分析[J]. 地理学报, 2021, 76(11): 2853-2866.

DU Yunyan, YI Jiawei, XUE Cunjin, QIAN Jiale, PEI Tao. Modeling and analysis of geographic events supported by multi-source geographic big data[J]. Acta Geographica Sinica, 2021, 76(11): 2853-2866.

图/表 9

图1

图2

图3

图4

图5

图6

图7

图8

图9

参考文献 69

[1]	Nelson K. Event Knowledge: Structure and Function in Development. London: Psychology Press, 1986.
[2]	Zhou Wen, Liu Zongtian, Kong Qingping. A survey of event-based knowledge processing. Computer Science, 2008(2):160-162, 184.
	[周文, 刘宗田, 孔庆苹. 基于事件的知识处理研究综述. 计算机科学, 2008(2):160-162, 184.]
[3]	Langran G. Issues of implementing a spatiotemporal system. International Journal of Geographical Information Science, 1993, 7(4):305-314.
[4]	Peuquet D J, Niu D. An event-based spatiotemporal data model (ESTDM) for temporal analysis of geographical data. International Journal of Geographical Information Systems, 1995, 9(1):7-24. doi: 10.1080/02693799508902022
[5]	Garcia Alvarez M, Morales J, Kraak M J. Integration and exploitation of sensor data in smart cities through event-driven applications. Sensors, 2019, 19(6):1372. DOI: 10.3390/s19061372. doi: 10.3390/s19061372
[6]	Gebbert S, Pebesma E. The GRASS GIS temporal framework. International Journal of Geographical Information Science, 2017, 31(7):1273-1292. doi: 10.1080/13658816.2017.1306862
[7]	Zhao Y J, Zhou X G, Li G Q, et al. A spatio-temporal VGI model considering trust-related information. ISPRS International Journal of Geo-Information, 2016, 5(2):10. DOI: 10.3390/ijgi5020010. doi: 10.3390/ijgi5020010
[8]	Xie Pan, Wang Yanglin, Liu Yanxu, et al. Incorporating social vulnerability to assess population health risk due to heat stress in China. Acta Geographica Sinica, 2015, 70(7):1041-1051. doi: 10.11821/dlxb201507002
	[谢盼, 王仰麟, 刘焱序, 等. 基于社会脆弱性的中国高温灾害人群健康风险评价. 地理学报, 2015, 70(7):1041-1051.]
[9]	Yu M Z, Yang C W, Li Y. Big data in natural disaster management: A review. Geosciences, 2018, 8(5):165. DOI: 10.3390/geosciences8050165. doi: 10.3390/geosciences8050165
[10]	Ji M, Liu L, Buchroithner M. Identifying collapsed buildings using post-earthquake satellite imagery and convolutional neural networks: A case study of the 2010 Haiti earthquake. Remote Sensing, 2018, 10(11):1689. DOI: 10.3390/rs10111689. doi: 10.3390/rs10111689
[11]	Voigt S, Giulio F, Lyons J, et al. Global trends in satellite-based emergency mapping. Science, 2016, 353(6296):247-252. doi: 10.1126/science.aad8728
[12]	Tong X H, Hong Z H, Liu S J, et al. Building-damage detection using pre- and post-seismic high-resolution satellite stereo imagery: A case study of the May 2008 Wenchuan earthquake. ISPRS Journal of Photogrammetry & Remote Sensing, 2012, 68(3):13-27.
[13]	Worthem A B, Madore G, Imahori J, et al. Emergency response imagery related to hurricanes Harvey, Irma, Maria. American Geophysical Union, Fall Meeting 2017: NH23E-2842.
[14]	Cervone G, Schnebele E, Waters N, et al. Using social media and satellite data for damage assessment in urban areas during emergencies. Seeing Cities Through Big Data, 2017: 443-457.
[15]	Jiang J H, Qu J H, Xu D Z, et al. Application of geographical information system technology to epidemiological surveillance and prevention and cure decision-making for SARS. Journal of Medical Colleges of PLA, 2006(3):186-188.
[16]	Deng Jiqiu, Wu Qianhong, Liu Aizhong. Analysis about environmental factor of SARS epidemic based on GIS logical information method. Chinese Journal of Health Statistics, 2006, 23(4):301-305.
	[邓吉秋, 吴堑虹, 刘爱忠. 基于GIS逻辑信息法的SARS流行环境因素分析. 中国卫生统计, 2006, 23(4):301-305.]
[17]	Yu X. Research and preliminary construction of GIS-based epidemiological monitoring platform[D]. Guizhou: Guizhou University of Finance and Economics, 2013.
[18]	Cheng Changxiu, Shi Peijun, Song Changqing, et al. Geographic big-data: A new opportunity for geography complexity study. Acta Geographica Sinica, 2018, 73(8):1397-1406. doi: 10.11821/dlxb201808001
	[程昌秀, 史培军, 宋长青, 等. 地理大数据为地理复杂性研究提供新机遇. 地理学报, 2018, 73(8):1397-1406.]
[19]	Pei Tao, Liu Yaxi, Guo Sihui, et al. Principle of big geodata mining. Acta Geographica Sinica, 2019, 74(3):586-598. doi: 10.11821/dlxb201903014
	[裴韬, 刘亚溪, 郭思慧, 等. 地理大数据挖掘的本质. 地理学报, 2019, 74(3):586-598.]
[20]	Zhou Chenghu. The value of spatial data in the era of big data: Review of "theory and application of spatial data mining. Acta Geographica Sinica, 2016, 71(7):1281.
	[周成虎. 大数据时代的空间数据价值: 《空间数据挖掘理论与应用》评介. 地理学报, 2016, 71(7):1281.]
[21]	Cole T, Wanik D, Molthan A, et al. Synergistic use of nighttime satellite data, electric utility infrastructure, and ambient population to improve power outage detections in urban areas. Remote Sensing, 2017, 9(3):286. DOI: 10.3390/rs9030286. doi: 10.3390/rs9030286
[22]	Zhao X Z, Yu B L, Liu Y, et al. NPP-VIIRS DNB daily data in natural disaster assessment: Evidence from selected case studies. Remote Sensing, 2018, 10(10):1526. DOI: 10.3390/rs10101526. doi: 10.3390/rs10101526
[23]	Román M, Stokes E, Shrestha R, et al. Satellite-based assessment of electricity restoration efforts in Puerto Rico after Hurricane Maria. PLOS ONE, 2019, 14(6):e0218883. DOI: 10.1371/journal.pone.0218883. doi: 10.1371/journal.pone.0218883
[24]	Wilson R, Erbach-Schoenberg E Z, Albert M, et al. Rapid and near real-time assessments of population displacement using mobile phone data following disasters: The 2015 Nepal Earthquake. PLoS Currents, 2016, 8. DOI: 10.1371/currents.dis.d073fbece328e4c39087bc086d694b5c. doi: 10.1371/currents.dis.d073fbece328e4c39087bc086d694b5c
[25]	Panteras G, Cervone G. Enhancing the temporal resolution of satellite-based flood extent generation using crowdsourced data for disaster monitoring. International Journal of Remote Sensing, 2018, 39:1459-1474. doi: 10.1080/01431161.2017.1400193
[26]	Balakrishnan S, Zhang Z M, Machemehl R, et al. Mapping resilience of Houston freeway network during Hurricane Harvey using extreme travel time metrics. International Journal of Disaster Risk Reduction, 2020, 47:101565. DOI: 10.1016/j.ijdrr.2020.101565. doi: 10.1016/j.ijdrr.2020.101565
[27]	Mudigonda S, Ozbay K, Bartin B. Evaluating the resilience and recovery of public transit system using big data: Case study from New Jersey. Journal of Transportation Safety & Security, 2019, 11(5):491-519.
[28]	Yuan M. Geographical information science for the United Nations' 2030 agenda for sustainable development. International Journal of Geographical Information Science, 2020, 35(1). DOI: 10.1080/13658816.2020.1766244. doi: 10.1080/13658816.2020.1766244
[29]	Ma T, Pei T, Song C, et al. Understanding geographical patterns of a city' diurnal rhythm from aggregate data of location-aware services. Transactions in GIS, 2019, 23(1):104-117. doi: 10.1111/tgis.v23.1
[30]	Heckmann T, Schwanghart W, Phillips J D. Graph theory: Recent developments of its application in geomorphology. Geomorphology, 2015, 243:130-146. doi: 10.1016/j.geomorph.2014.12.024
[31]	Siabato W, Claramunt C, Ilarri S, et al. A survey of modelling trends in temporal GIS. ACM Computing Surveys, 2018, 51(2):1-41.
[32]	Liu W B, Li X G, Rahn D A. Storm event representation and analysis based on a directed spatiotemporal graph model. International Journal of Geographical Information Science, 2016, 30(5):948-969. doi: 10.1080/13658816.2015.1081910
[33]	Del Mondo G, Rodríguez M A, Claramunt C, et al. Modeling consistency of spatio-temporal graphs. Data & Knowledge Engineering, 2013, 84:59-80. doi: 10.1016/j.datak.2012.12.007
[34]	Pokorný J. Graph Databases: Their power and limitations. International Conference on Computer Information Systems and Industrial Management, 2015. DOI: 10.1007/978-3-319-24369-6_5. doi: 10.1007/978-3-319-24369-6_5
[35]	Robinson I, Webber J, Eifrem E. Graph Database. 2nd ed. Sebastopol: O'Reilly Media Inc., 2015.
[36]	Zhu R, Guilbert E, Wong M S. Object-oriented tracking of the dynamic behavior of urban heat islands. International Journal of Geographical Information Science, 2017, 31(2):405-424. doi: 10.1080/13658816.2016.1211282
[37]	Xue C J, Wu C B, Liu J Y, et al. A novel process-oriented graph storage for dynamic geographic phenomena. ISPRS International Journal of Geo-Information, 2019, 8(2). DOI: 10.3390/ijgi8020100. doi: 10.3390/ijgi8020100
[38]	Stell J, Del Mondo G, Thibaud R, et al. Spatio-temporal evolution as bigraph dynamics. International Conference on Spatial Information Theory, 2011. DOI: 10.1007/978-3-642-23196-4_9. doi: 10.1007/978-3-642-23196-4_9
[39]	Liu Yuefeng, Lu Min, Yang Zhongzhi. Modeling dynamic networks in temporal GIS and realization methods. Acta Scientiarum Naturalium Universitatis Pekinensis, 2012, 48(3):451-458.
	[刘岳峰, 陆忞, 杨忠智. 时态GIS中动态网络建模及实现方法. 北京大学学报(自然科学版), 2012, 48(3):451-458.]
[40]	Zhang Zhonggui, Wu Xincai. A general network spatiotemporal data model. Computer Applications and Software, 2015, 32(9):84-87.
	[张忠贵, 吴信才. 一种通用的网络时空数据模型. 计算机应用与软件, 2015, 32(9):84-87.]
[41]	Thibaud R, Del Mondo G, Garlan T, et al. A spatio-temporal graph model for marine dune dynamics analysis and representation. Transactions in GIS, 2013, 17(5):742-762.
[42]	Xie Jiong, Liu Renyi, Liu Nan. Study of land use multi-level change model and its transaction processing mechanism. Journal of Zhejiang University(Science Edition), 2007(4):469-475.
	[谢炯, 刘仁义, 刘南. 土地利用现状管理信息系统中土地利用多级变更模型的建立及其事务处理机制设计. 浙江大学学报(理学版), 2007(4):469-475.]
[43]	Zheng Y, Zhang H C, Yu Y. Detecting collective anomalies from multiple spatio-temporal datasets across different domains. Proceedings of the 23rd SIGSPATIAL International Conference on Advances in Geographic Information Systems. ACM Press, Bellevue, Washington, 2015: 2(1). DOI: 10.1145/2820783.2820813. doi: 10.1145/2820783.2820813
[44]	Xue C J, Song W J, Qin L J, et al. A spatiotemporal mining framework for abnormal association patterns in marine environments with a time series of remote sensing images. International Journal of Applied Earth Observation & Geoinformation, 2015, 38:105-114.
[45]	Xu Z H, Bian F L. Spatio-temporal GIS data model based on event semantics. Geo-spatial Information Science, 2003, 6(3):43-47.
[46]	Chen J, Jiang J. An event-based approach to spatio-temporal data modeling in land subdivision systems. GeoInformatica, 2000, 4(4):387-402. doi: 10.1023/A:1026565929263
[47]	Lin G, Feng X, Wang L, et al. An event-centric object oriented spatio-temporal data model. Acta Geographica et Cartographica Sinica, 2002(1):71-76.
[48]	Ikezaki M, Watanabe T. Event-based specification for managing change history of geographic information. International Journal of Computer Science and Network Security, 2006, 6(6):106-110.
[49]	Yi J W, Du Y Y, Liang F Y, et al. A representation framework for studying spatiotemporal changes and interactions of dynamic geographic phenomena. International Journal of Geographical Information Science, 2014, 28(5):1010-1027. doi: 10.1080/13658816.2014.890201
[50]	Luo W, Peuquet D J, Robinson A C, et al. A method for discovery and analysis of temporal patterns in complex event data. International Journal of Geographical Information Science, 2015, 29(9):1588-1611. doi: 10.1080/13658816.2015.1042380
[51]	Liu Yu. Revisiting several basic geographical concepts: A social sensing perspective. Acta Geographica Sinica, 2016, 71(4):564-575.
	[刘瑜. 社会感知视角下的若干人文地理学基本问题再思考. 地理学报, 2016, 71(4):564-575.]
[52]	Liu Z, Du Y, Yi J, et al. Quantitative estimates of collective geo-tagged human activities in response to typhoon Hato using location-aware big data. International Journal of Digital Earth, 2020, 13(9):1072-1092. doi: 10.1080/17538947.2019.1645894
[53]	Wang N, Du Y Y, Liang F Y, et al. Spatiotemporal changes of urban rainstorm-related micro-blogging activities in response to rainstorms: A case study in Beijing, China. Applied Sciences, 2019, 9(21):4629. DOI: 10.3390/app9214629. doi: 10.3390/app9214629
[54]	Liu J Y, Xue C J, He Y W, et al. Dual-constraint spatiotemporal clustering approach for exploring marine anomaly patterns using remote sensing products. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018, 11(11):3963-3976. doi: 10.1109/JSTARS.4609443
[55]	Cheng T, Wicks T. Event detection using Twitter: A spatio-temporal approach. PLOS ONE, 2014, 9(6):e97807. DOI: 10.1371/journal.pone.0097807. doi: 10.1371/journal.pone.0097807
[56]	Shiode S, Shiode N. Network-based space-time search-window technique for hotspot detection of street-level crime incidents. International Journal of Geographical Information Science, 2013, 27(5):866-882. doi: 10.1080/13658816.2012.724175
[57]	Nakaya T, Yano K. Visualising crime clusters in a space-time cube. Transactions in GIS, 2010, 14(3):223-239. doi: 10.1111/j.1467-9671.2010.01194.x
[58]	Pang L X, Chawla S, Liu W, et al. On detection of emerging anomalous traffic patterns using GPS data. Data & Knowledge Engineering. 2013, 87(9):357-373. doi: 10.1016/j.datak.2013.05.002
[59]	Shi Y, Deng M, Yang X X, et al. A framework for discovering evolving domain related spatio-temporal patterns in Twitter. ISPRS International Journal of Geo-Information, 2016, 5(10):193. DOI: 10.3390/ijgi5100193. doi: 10.3390/ijgi5100193
[60]	Telang A, Deepak P, Joshi S, et al. Detecting localized homogeneous anomalies over spatio-temporal data. Data Mining and Knowledge Discovery, 2014, 28(5/6):1480-1502. doi: 10.1007/s10618-014-0366-x
[61]	Lee C H. Mining spatio-temporal information on microblogging streams using a density-based online clustering method. Expert Systems with Applications, 2012, 39(10):9623-9641. doi: 10.1016/j.eswa.2012.02.136
[62]	Feng W, Zhang C, Zhang W, et al. STREAMCUBE: Hierarchical spatio-temporal hashtag clustering for event exploration over the Twitter stream. IEEE 31st International Conference on Data Engineering, Seoul, South Korea, 2015: 1561-1572.
[63]	Liu Z, Du Y Y, Yi J W, et al. Quantitative association between nighttime lights and geo-tagged human activity dynamics during Typhoon Mangkhut. Remote Sensing, 2019, 11(18):2091. DOI: 10.3390/rs11182091. doi: 10.3390/rs11182091
[64]	Yao Y, Wu D Q, Hong Y, et al. Analyzing the effects of rainfall on urban traffic-congestion bottlenecks. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 13:504-512. doi: 10.1109/JSTARS.4609443
[65]	Robinson C, Hohman F, Dilkina B. A deep learning approach for population estimation from satellite imagery. Proceedings of the 1st ACM SIGSPATIAL Workshop on Geospatial Humanities, 2017: 47-54.
[66]	Liu Y J, Racah E, Prabhat, et al. Application of deep convolutional neural networks for detecting extreme weather in climate datasets. International Conference on Advances in Big Data Analytics and Data Processing, 2016.
[67]	Racah E, Beckham C, Maharaj T, et al. Extreme weather: A large-scale climate dataset for semi-supervised detection, localization, and understanding of extreme weather events. Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017.
[68]	Yi Jiawei, Wang Nan, Qian Jiale, et al. Spatio-temporal responses of urban road traffic and human activities in an extreme rainfall event using big data. Acta Geographica Sinica, 2020, 75(3):497-508. doi: 10.11821/dlxb202003005
	[易嘉伟, 王楠, 千家乐, 等. 基于大数据的极端暴雨事件下城市道路交通及人群活动时空响应. 地理学报, 2020, 75(3):497-508.]
[69]	Yi J W, Du Y Y, Liang F Y, et al. Anomalies of dwellers' collective geotagged behaviors in response to rainstorms: A case study of eight cities in China using smartphone location data. Natural Hazards and Earth System Sciences, 2019, 19(10):2169-2182.